Generates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC allows users to get suggested rubrics based on provided prompt, which can then be reviewed and used for subsequent evaluations.
generateSyntheticData(location, body=None, x__xgafv=None)
Generates synthetic data based on the provided configuration.
+Generates synthetic (artificial) data based on a description
Gets information about a location.
@@ -339,7 +339,7 @@generateSyntheticData(location, body=None, x__xgafv=None)
- Generates synthetic data based on the provided configuration.
+ Generates synthetic (artificial) data based on a description
Args:
- location: string, Required. The resource name of the Location to run the job. Format: `projects/{project}/locations/{location}` (required)
+ location: string, Required. The geographic location where the synthetic data generation request is processed. This should be in the format `projects/{project}/locations/{location}`. For example, `projects/my-project/locations/us-central1`. (required)
body: object, The request body.
The object takes the form of:
-{ # Request message for DataFoundryService.GenerateSyntheticData.
- "count": 42, # Required. The number of synthetic examples to generate. For this stateless API, the count is limited to a small number.
- "examples": [ # Optional. A list of few-shot examples to guide the model's output style and format.
- { # Represents a single synthetic example, composed of multiple fields. Used for providing few-shot examples in the request and for returning generated examples in the response.
+{ # Request message for DataFoundryService.GenerateSyntheticData. It contains the settings and information needed to generate synthetic data.
+ "count": 42, # Required. The number of synthetic examples to generate. For this stateless API, you can generate up to 50 examples in a single request.
+ "examples": [ # Optional. A list of few-shot examples that help the model understand the desired style, tone, and format of the generated synthetic data. Providing these few-shot examples can significantly improve the quality and relevance of the output.
+ { # A single instance of generated synthetic data. Each example is made up of one or more named fields, as defined in `OutputFieldSpec`. These examples are used as few-shot examples to show the model what you want (in `GenerateSyntheticDataRequest.examples`) and to return generated examples in the response (in `GenerateSyntheticDataResponse.synthetic_examples`).
"fields": [ # Required. A list of fields that constitute an example.
- { # Represents a single named field within a SyntheticExample.
- "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the field.
+ { # Represents a single named field within a synthetic example, consisting of a name and the actual content.
+ "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -5430,11 +5430,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -5447,8 +5447,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -5488,20 +5488,20 @@ Method Details
],
"role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'.
},
- "fieldName": "A String", # Optional. The name of the field.
+ "fieldName": "A String", # Optional. The name of the specific field, such as "product_name" or "review_text".
},
],
},
],
- "outputFieldSpecs": [ # Required. The schema of the desired output, defined by a list of fields.
- { # Defines a specification for a single output field.
- "fieldName": "A String", # Required. The name of the output field.
+ "outputFieldSpecs": [ # Required. Defines the schema of each synthetic example to be generated, defined by a list of fields.
+ { # Specifies the properties of a single field that are included in each generated synthetic example. This helps the model understand what kind of data to generate for each field.
+ "fieldName": "A String", # Required. The name of this field in the generated synthetic data, such as "email_subject" or "customer_review".
"fieldType": "A String", # Optional. The data type of the field. Defaults to CONTENT if not set.
- "guidance": "A String", # Optional. Optional, but recommended. Additional guidance specific to this field to provide targeted instructions for the LLM to generate the content of a single output field. While the LLM can sometimes infer content from the field name, providing explicit guidance is preferred.
+ "guidance": "A String", # Optional. Specific instructions for the large language model on how to generate content for this particular field. While the LLM can sometimes infer content from the field name, providing explicit guidance is preferred. For example, for a field named "review", the guidance could be "A positive review about a coffee maker."
},
],
- "taskDescription": { # Defines a generation strategy based on a high-level task description. # Generate data from a high-level task description.
- "taskDescription": "A String", # Required. A high-level description of the synthetic data to be generated.
+ "taskDescription": { # Defines a generation strategy based on a general task description. # Generates synthetic data based on a high-level description of the task or data you want.
+ "taskDescription": "A String", # Required. A general description of the type of synthetic data you want to generate. For example, "Generate customer reviews for a new smartphone."
},
}
@@ -5513,19 +5513,19 @@ Method Details
Returns:
An object of the form:
- { # The response containing the generated data.
- "syntheticExamples": [ # A list of generated synthetic examples.
- { # Represents a single synthetic example, composed of multiple fields. Used for providing few-shot examples in the request and for returning generated examples in the response.
+ { # The response message for the `GenerateSyntheticData` method, containing the synthetic examples generated by the Gen AI evaluation service.
+ "syntheticExamples": [ # A list of generated synthetic examples, each containing a complete synthetic data instance generated based on your request.
+ { # A single instance of generated synthetic data. Each example is made up of one or more named fields, as defined in `OutputFieldSpec`. These examples are used as few-shot examples to show the model what you want (in `GenerateSyntheticDataRequest.examples`) and to return generated examples in the response (in `GenerateSyntheticDataResponse.synthetic_examples`).
"fields": [ # Required. A list of fields that constitute an example.
- { # Represents a single named field within a SyntheticExample.
- "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the field.
+ { # Represents a single named field within a synthetic example, consisting of a name and the actual content.
+ "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -5534,11 +5534,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -5551,8 +5551,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -5592,7 +5592,7 @@ Method Details
],
"role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'.
},
- "fieldName": "A String", # Optional. The name of the field.
+ "fieldName": "A String", # Optional. The name of the specific field, such as "product_name" or "review_text".
},
],
},
diff --git a/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html
index 3504e9084e..1c8de8653d 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html
@@ -135,11 +135,11 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -148,11 +148,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -165,8 +165,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -250,11 +250,11 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -263,11 +263,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -280,8 +280,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -442,11 +442,11 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -455,11 +455,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -472,8 +472,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -515,7 +515,7 @@ Method Details
},
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
- "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
+ "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
},
"computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations.
"environment": "A String", # Required. The environment being operated.
@@ -765,11 +765,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content to be embedded.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -778,11 +778,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -795,8 +795,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -836,6 +836,14 @@ Method Details
],
"role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'.
},
+ "embedContentConfig": { # Configurations for the EmbedContent API. # Optional. Configuration for the EmbedContent request.
+ "audioTrackExtraction": True or False, # Optional. Whether to extract audio from video content.
+ "autoTruncate": True or False, # Optional. Whether to silently truncate the input content if it's longer than the maximum sequence length. Only applicable to text-only embedding models.
+ "documentOcr": True or False, # Optional. Whether to enable OCR for document content.
+ "outputDimensionality": 42, # Optional. Reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end.
+ "taskType": "A String", # Optional. The task type of the embedding. Only applicable to text-only embedding models.
+ "title": "A String", # Optional. The title for the text. Only applicable to text-only embedding models.
+ },
"outputDimensionality": 42, # Optional. Deprecated: Please use EmbedContentConfig.output_dimensionality instead. Reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end.
"taskType": "A String", # Optional. Deprecated: Please use EmbedContentConfig.task_type instead. The task type of the embedding.
"title": "A String", # Optional. Deprecated: Please use EmbedContentConfig.title instead. The title for the text.
@@ -949,11 +957,11 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -962,11 +970,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -979,8 +987,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -1151,11 +1159,11 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -1164,11 +1172,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -1181,8 +1189,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -1224,11 +1232,11 @@ Method Details
},
"toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
"functionCallingConfig": { # Function calling config. # Optional. Function calling config.
- "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
+ "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided.
"A String",
],
"mode": "A String", # Optional. Function calling mode.
- "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field.
+ "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field.
},
"retrievalConfig": { # Retrieval config. # Optional. Retrieval config.
"languageCode": "A String", # The language code of the user.
@@ -1240,7 +1248,7 @@ Method Details
},
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
- "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
+ "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
},
"computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations.
"environment": "A String", # Required. The environment being operated.
@@ -1487,11 +1495,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -1500,11 +1508,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -1517,8 +1525,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -2072,11 +2080,11 @@ Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -2085,11 +2093,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -2102,8 +2110,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -2274,11 +2282,11 @@ Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -2287,11 +2295,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -2304,8 +2312,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -2347,11 +2355,11 @@ Method Details
},
"toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
"functionCallingConfig": { # Function calling config. # Optional. Function calling config.
- "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
+ "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided.
"A String",
],
"mode": "A String", # Optional. Function calling mode.
- "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field.
+ "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field.
},
"retrievalConfig": { # Retrieval config. # Optional. Retrieval config.
"languageCode": "A String", # The language code of the user.
@@ -2363,7 +2371,7 @@ Method Details
},
"tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
{ # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
- "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
+ "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation.
},
"computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations.
"environment": "A String", # Required. The environment being operated.
@@ -2610,11 +2618,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -2623,11 +2631,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -2640,8 +2648,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.html b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.html
index f7a388bf9e..a4fbf25e7f 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.html
@@ -152,7 +152,10 @@ Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context.
"memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine.
"customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope.
- { # Configuration for organizing memories for a particular scope.
+ { # Represents configuration for organizing memories for a particular scope.
+ "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together.
+ "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered.
+ },
"enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.")
"generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope.
{ # An example of how to generate memories for a particular scope.
@@ -162,11 +165,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -175,11 +178,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -192,8 +195,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -499,7 +502,10 @@ Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context.
"memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine.
"customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope.
- { # Configuration for organizing memories for a particular scope.
+ { # Represents configuration for organizing memories for a particular scope.
+ "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together.
+ "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered.
+ },
"enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.")
"generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope.
{ # An example of how to generate memories for a particular scope.
@@ -509,11 +515,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -522,11 +528,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -539,8 +545,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -777,7 +783,10 @@ Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context.
"memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine.
"customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope.
- { # Configuration for organizing memories for a particular scope.
+ { # Represents configuration for organizing memories for a particular scope.
+ "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together.
+ "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered.
+ },
"enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.")
"generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope.
{ # An example of how to generate memories for a particular scope.
@@ -787,11 +796,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -800,11 +809,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -817,8 +826,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
@@ -1025,7 +1034,10 @@ Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context.
"memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine.
"customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope.
- { # Configuration for organizing memories for a particular scope.
+ { # Represents configuration for organizing memories for a particular scope.
+ "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together.
+ "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered.
+ },
"enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.")
"generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope.
{ # An example of how to generate memories for a particular scope.
@@ -1035,11 +1047,11 @@ Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event.
"parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part.
{ # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
- "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode.
+ "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode.
"outcome": "A String", # Required. Outcome of the code execution.
"output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
},
- "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed.
+ "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed.
"code": "A String", # Required. The code to be executed.
"language": "A String", # Required. Programming language of the `code`.
},
@@ -1048,11 +1060,11 @@ Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage.
"mimeType": "A String", # Required. The IANA standard MIME type of the source data.
},
- "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
- "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+ "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function.
+ "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details.
"a_key": "", # Properties of the object.
},
- "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name].
+ "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name.
"partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally.
{ # Partial argument value of the function call.
"boolValue": True or False, # Optional. Represents a boolean value.
@@ -1065,8 +1077,8 @@ Method Details
],
"willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow.
},
- "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
- "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+ "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted.
+ "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name.
"parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types.
{ # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes.
"fileData": { # URI based data for function response. # URI based data.
diff --git a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.memories.html b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.memories.html
index 9805c84c51..fd71aed8b7 100644
--- a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.memories.html
+++ b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.memories.html
@@ -88,7 +88,7 @@ Instance Methods
close()
Close httplib2 connections.
- create(parent, body=None, x__xgafv=None)
+ create(parent, body=None, memoryId=None, x__xgafv=None)
Create a Memory.
@@ -124,7 +124,7 @@ Method Details
create(parent, body=None, x__xgafv=None)
+ create(parent, body=None, memoryId=None, x__xgafv=None)
Create a Memory. Args: @@ -166,6 +166,7 @@Method Details
"updateTime": "A String", # Output only. Timestamp when this Memory was most recently updated. } + memoryId: string, Optional. The user defined ID to use for memory, which will become the final component of the memory resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format @@ -246,11 +247,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single piece of content from which to generate memories. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -259,11 +260,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -276,8 +277,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.events.html b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.events.html index 747ce26473..dcc2519a33 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.events.html +++ b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.events.html @@ -129,11 +129,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -142,11 +142,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -159,8 +159,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -313,6 +313,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. }, ], diff --git a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.html b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.html index 86ab40efd0..eacfd09d51 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.html +++ b/docs/dyn/aiplatform_v1.projects.locations.reasoningEngines.sessions.html @@ -91,7 +91,7 @@Instance Methods
close()Close httplib2 connections.
-
+create(parent, body=None, x__xgafv=None)create(parent, body=None, sessionId=None, x__xgafv=None)Creates a new Session.
@@ -137,11 +137,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -150,11 +150,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -167,8 +167,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -321,6 +321,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. } @@ -342,7 +345,7 @@Method Details
create(parent, body=None, x__xgafv=None)
+ create(parent, body=None, sessionId=None, x__xgafv=None)
Creates a new Session. Args: @@ -366,6 +369,7 @@Method Details
"userId": "A String", # Required. Immutable. String id provided by the user } + sessionId: string, Optional. The user defined ID to use for session, which will become the final component of the session resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format diff --git a/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html b/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html index 1b7886c825..adcff101e5 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html +++ b/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html @@ -868,11 +868,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -881,11 +881,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -898,8 +898,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -946,11 +946,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -959,11 +959,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -976,8 +976,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1070,11 +1070,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1083,11 +1083,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1100,8 +1100,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1935,11 +1935,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1948,11 +1948,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1965,8 +1965,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2013,11 +2013,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2026,11 +2026,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2043,8 +2043,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2137,11 +2137,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2150,11 +2150,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2167,8 +2167,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3009,11 +3009,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3022,11 +3022,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3039,8 +3039,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3087,11 +3087,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3100,11 +3100,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3117,8 +3117,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3211,11 +3211,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3224,11 +3224,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3241,8 +3241,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4089,11 +4089,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4102,11 +4102,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4119,8 +4119,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4167,11 +4167,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4180,11 +4180,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4197,8 +4197,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4291,11 +4291,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4304,11 +4304,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4321,8 +4321,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5184,11 +5184,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5197,11 +5197,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5214,8 +5214,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5262,11 +5262,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5275,11 +5275,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5292,8 +5292,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5386,11 +5386,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5399,11 +5399,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5416,8 +5416,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1.publishers.models.html b/docs/dyn/aiplatform_v1.publishers.models.html index 84e972dbc1..9ffabc74e8 100644 --- a/docs/dyn/aiplatform_v1.publishers.models.html +++ b/docs/dyn/aiplatform_v1.publishers.models.html @@ -121,11 +121,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -134,11 +134,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -151,8 +151,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -236,11 +236,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -249,11 +249,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -266,8 +266,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -428,11 +428,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -441,11 +441,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -458,8 +458,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -501,7 +501,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -794,11 +794,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -807,11 +807,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -824,8 +824,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -996,11 +996,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1009,11 +1009,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1026,8 +1026,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1069,11 +1069,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1085,7 +1085,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1332,11 +1332,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1345,11 +1345,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1362,8 +1362,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1618,7 +1618,7 @@Method Details
"A String", ], "launchStage": "A String", # Optional. Indicates the launch stage of the model. - "name": "A String", # Output only. The resource name of the PublisherModel. + "name": "A String", # Output only. Identifier. The resource name of the PublisherModel. "openSourceCategory": "A String", # Required. Indicates the open source category of the publisher model. "predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # Optional. The schemata that describes formats of the PublisherModel's predictions and explanations as given and returned via PredictionService.Predict. "instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access. @@ -2264,11 +2264,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2277,11 +2277,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2294,8 +2294,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2466,11 +2466,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2479,11 +2479,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2496,8 +2496,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2539,11 +2539,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2555,7 +2555,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2802,11 +2802,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2815,11 +2815,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2832,8 +2832,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1.reasoningEngines.html b/docs/dyn/aiplatform_v1.reasoningEngines.html index b24e91ccdd..af6526b26d 100644 --- a/docs/dyn/aiplatform_v1.reasoningEngines.html +++ b/docs/dyn/aiplatform_v1.reasoningEngines.html @@ -142,7 +142,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -152,11 +155,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -165,11 +168,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -182,8 +185,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -490,7 +493,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -500,11 +506,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -513,11 +519,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -530,8 +536,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -733,7 +739,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -743,11 +752,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -756,11 +765,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -773,8 +782,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -981,7 +990,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -991,11 +1003,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1004,11 +1016,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1021,8 +1033,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1.v1.html b/docs/dyn/aiplatform_v1.v1.html index d0c7e8d854..74c3636d1c 100644 --- a/docs/dyn/aiplatform_v1.v1.html +++ b/docs/dyn/aiplatform_v1.v1.html @@ -777,11 +777,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -790,11 +790,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -807,8 +807,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -858,7 +858,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1086,11 +1086,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1099,11 +1099,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1116,8 +1116,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1167,7 +1167,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1391,11 +1391,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1404,11 +1404,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1421,8 +1421,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1471,11 +1471,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1484,11 +1484,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1501,8 +1501,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1547,7 +1547,7 @@Method Details
"tools": { # Deprecated: Use `agent_eval_data` instead. Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1769,7 +1769,7 @@Method Details
{ # A single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1987,11 +1987,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2000,11 +2000,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2017,8 +2017,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2069,7 +2069,7 @@Method Details
}, ], }, - "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. + "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. If a key conflicts with a field in the EvaluationInstance (e.g. `prompt`), the value of the field will take precedence over the value in other_data. "mapInstance": { # Optional. Map of instance data. "a_key": { # Instance data used to populate placeholders in a metric prompt template. "contents": { # List of standard Content messages from Gemini API. # List of Gemini content data. @@ -2077,11 +2077,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2090,11 +2090,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2107,8 +2107,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2160,11 +2160,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2173,11 +2173,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2190,8 +2190,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2241,11 +2241,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2254,11 +2254,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2271,8 +2271,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2322,11 +2322,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2335,11 +2335,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2352,8 +2352,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2743,11 +2743,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2756,11 +2756,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2773,8 +2773,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2865,11 +2865,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2878,11 +2878,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2895,8 +2895,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3502,11 +3502,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3515,11 +3515,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3532,8 +3532,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3583,7 +3583,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3804,11 +3804,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3817,11 +3817,11 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3834,8 +3834,8 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.endpoints.html b/docs/dyn/aiplatform_v1beta1.endpoints.html index d0db801dab..0186be11f6 100644 --- a/docs/dyn/aiplatform_v1beta1.endpoints.html +++ b/docs/dyn/aiplatform_v1beta1.endpoints.html @@ -128,11 +128,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -141,12 +141,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -159,9 +159,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -245,11 +245,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -258,12 +258,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -276,9 +276,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -442,11 +442,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -455,12 +455,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -473,9 +473,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -517,7 +517,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -817,11 +817,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -830,12 +830,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -848,9 +848,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1024,11 +1024,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1037,12 +1037,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1055,9 +1055,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1099,11 +1099,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1115,7 +1115,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1369,11 +1369,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1382,12 +1382,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1400,9 +1400,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1731,11 +1731,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1744,12 +1744,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1762,9 +1762,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1938,11 +1938,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1951,12 +1951,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1969,9 +1969,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2013,11 +2013,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2029,7 +2029,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2283,11 +2283,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2296,12 +2296,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2314,9 +2314,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.cachedContents.html b/docs/dyn/aiplatform_v1beta1.projects.locations.cachedContents.html index bb0b01e94f..ef9e4259be 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.cachedContents.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.cachedContents.html @@ -115,11 +115,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -128,12 +128,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -146,9 +146,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -200,11 +200,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -213,12 +213,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -231,9 +231,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -275,11 +275,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -291,7 +291,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -536,11 +536,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -549,12 +549,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -567,9 +567,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -621,11 +621,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -634,12 +634,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -652,9 +652,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -696,11 +696,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -712,7 +712,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -982,11 +982,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -995,12 +995,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1013,9 +1013,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1067,11 +1067,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1080,12 +1080,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1098,9 +1098,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1142,11 +1142,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1158,7 +1158,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1414,11 +1414,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1427,12 +1427,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1445,9 +1445,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1499,11 +1499,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1512,12 +1512,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1530,9 +1530,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1574,11 +1574,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1590,7 +1590,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1854,11 +1854,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1867,12 +1867,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1885,9 +1885,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1939,11 +1939,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1952,12 +1952,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1970,9 +1970,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2014,11 +2014,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2030,7 +2030,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2276,11 +2276,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2289,12 +2289,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2307,9 +2307,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2361,11 +2361,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input only. Immutable. Developer set system instruction. Currently, text only "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2374,12 +2374,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2392,9 +2392,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2436,11 +2436,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Input only. Immutable. Tool config. This config is shared for all tools "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2452,7 +2452,7 @@Method Details
}, "tools": [ # Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.datasets.html b/docs/dyn/aiplatform_v1beta1.projects.locations.datasets.html index 9a9287c74b..22c755770a 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.datasets.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.datasets.html @@ -170,11 +170,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -183,12 +183,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -201,9 +201,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -378,11 +378,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -391,12 +391,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -409,9 +409,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -453,11 +453,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -469,7 +469,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -752,11 +752,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -765,12 +765,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -783,9 +783,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -960,11 +960,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -973,12 +973,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -991,9 +991,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1035,11 +1035,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1051,7 +1051,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html index 960dd04efc..b94ca052b4 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html @@ -205,11 +205,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -218,12 +218,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -236,9 +236,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -322,11 +322,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -335,12 +335,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -353,9 +353,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -519,11 +519,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -532,12 +532,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -550,9 +550,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -594,7 +594,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1984,11 +1984,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1997,12 +1997,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2015,9 +2015,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2191,11 +2191,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2204,12 +2204,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2222,9 +2222,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2266,11 +2266,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2282,7 +2282,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2536,11 +2536,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2549,12 +2549,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2567,9 +2567,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4643,11 +4643,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4656,12 +4656,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4674,9 +4674,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4850,11 +4850,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4863,12 +4863,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4881,9 +4881,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4925,11 +4925,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -4941,7 +4941,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -5195,11 +5195,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5208,12 +5208,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5226,9 +5226,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationItems.html b/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationItems.html index d4d6cff1f9..dd7657d794 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationItems.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationItems.html @@ -140,7 +140,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -369,7 +369,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -594,11 +594,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -607,12 +607,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -625,9 +625,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -692,11 +692,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -705,12 +705,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -723,9 +723,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -783,7 +783,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1012,7 +1012,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1237,11 +1237,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1250,12 +1250,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1268,9 +1268,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1335,11 +1335,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1348,12 +1348,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1366,9 +1366,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1425,7 +1425,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1654,7 +1654,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1879,11 +1879,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1892,12 +1892,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1910,9 +1910,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1968,11 +1968,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1981,12 +1981,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1999,9 +1999,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2110,7 +2110,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2339,7 +2339,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2564,11 +2564,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2577,12 +2577,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2595,9 +2595,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2662,11 +2662,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2675,12 +2675,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2693,9 +2693,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2753,7 +2753,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2982,7 +2982,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3207,11 +3207,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3220,12 +3220,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3238,9 +3238,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3305,11 +3305,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3318,12 +3318,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3336,9 +3336,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3395,7 +3395,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3624,7 +3624,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3849,11 +3849,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3862,12 +3862,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3880,9 +3880,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3938,11 +3938,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3951,12 +3951,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3969,9 +3969,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4080,7 +4080,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4309,7 +4309,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4534,11 +4534,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4547,12 +4547,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4565,9 +4565,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4632,11 +4632,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4645,12 +4645,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4663,9 +4663,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4723,7 +4723,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4952,7 +4952,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -5177,11 +5177,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5190,12 +5190,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5208,9 +5208,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5275,11 +5275,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5288,12 +5288,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5306,9 +5306,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5365,7 +5365,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -5594,7 +5594,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -5819,11 +5819,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5832,12 +5832,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5850,9 +5850,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5908,11 +5908,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5921,12 +5921,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5939,9 +5939,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6050,7 +6050,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -6279,7 +6279,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -6504,11 +6504,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6517,12 +6517,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6535,9 +6535,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6602,11 +6602,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6615,12 +6615,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6633,9 +6633,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6693,7 +6693,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -6922,7 +6922,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -7147,11 +7147,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -7160,12 +7160,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -7178,9 +7178,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -7245,11 +7245,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -7258,12 +7258,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -7276,9 +7276,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -7335,7 +7335,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -7564,7 +7564,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -7789,11 +7789,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -7802,12 +7802,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -7820,9 +7820,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -7878,11 +7878,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -7891,12 +7891,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -7909,9 +7909,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -8062,7 +8062,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -8291,7 +8291,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -8516,11 +8516,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -8529,12 +8529,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -8547,9 +8547,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -8614,11 +8614,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -8627,12 +8627,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -8645,9 +8645,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -8705,7 +8705,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -8934,7 +8934,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -9159,11 +9159,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -9172,12 +9172,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -9190,9 +9190,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -9257,11 +9257,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -9270,12 +9270,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -9288,9 +9288,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -9347,7 +9347,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -9576,7 +9576,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -9801,11 +9801,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -9814,12 +9814,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -9832,9 +9832,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -9890,11 +9890,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -9903,12 +9903,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -9921,9 +9921,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -10032,7 +10032,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -10261,7 +10261,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -10486,11 +10486,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -10499,12 +10499,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -10517,9 +10517,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -10584,11 +10584,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -10597,12 +10597,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -10615,9 +10615,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -10675,7 +10675,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -10904,7 +10904,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -11129,11 +11129,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -11142,12 +11142,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -11160,9 +11160,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -11227,11 +11227,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -11240,12 +11240,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -11258,9 +11258,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -11317,7 +11317,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -11546,7 +11546,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -11771,11 +11771,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -11784,12 +11784,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -11802,9 +11802,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -11860,11 +11860,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -11873,12 +11873,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -11891,9 +11891,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -12015,7 +12015,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -12244,7 +12244,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -12469,11 +12469,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -12482,12 +12482,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -12500,9 +12500,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -12567,11 +12567,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -12580,12 +12580,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -12598,9 +12598,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -12658,7 +12658,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -12887,7 +12887,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -13112,11 +13112,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -13125,12 +13125,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -13143,9 +13143,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -13210,11 +13210,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -13223,12 +13223,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -13241,9 +13241,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -13300,7 +13300,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -13529,7 +13529,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -13754,11 +13754,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -13767,12 +13767,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -13785,9 +13785,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -13843,11 +13843,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -13856,12 +13856,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -13874,9 +13874,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -13985,7 +13985,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -14214,7 +14214,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -14439,11 +14439,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -14452,12 +14452,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -14470,9 +14470,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -14537,11 +14537,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -14550,12 +14550,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -14568,9 +14568,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -14628,7 +14628,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -14857,7 +14857,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -15082,11 +15082,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -15095,12 +15095,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -15113,9 +15113,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -15180,11 +15180,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -15193,12 +15193,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -15211,9 +15211,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -15270,7 +15270,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -15499,7 +15499,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -15724,11 +15724,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -15737,12 +15737,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -15755,9 +15755,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -15813,11 +15813,11 @@Method Details
"a_key": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -15826,12 +15826,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -15844,9 +15844,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationRuns.html b/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationRuns.html index 45095762ce..d73e3f7edb 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationRuns.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.evaluationRuns.html @@ -289,6 +289,11 @@Method Details
}, "sampleCount": 42, # Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. }, + "datasetCustomMetrics": [ # Optional. Specifications for custom dataset-level aggregations. + { # Defines a custom dataset-level aggregation. + "displayName": "A String", # Optional. A display name for this custom summary metric. Used to prefix keys in the output summaryMetrics map. If not provided, a default name like "dataset_custom_metric_1", "dataset_custom_metric_2", etc., will be generated based on the order in the repeated field. + }, + ], "metrics": [ # Required. The metrics to be calculated in the evaluation run. { # The metric used for evaluation runs. "computationBasedMetricSpec": { # Specification for a computation based metric. # Spec for a computation based metric. @@ -1305,15 +1310,15 @@Method Details
"evaluationSetSnapshot": "A String", # Output only. The specific evaluation set of the evaluation run. For runs with an evaluation set input, this will be that same set. For runs with BigQuery input, it's the sampled BigQuery dataset. "inferenceConfigs": { # Optional. The candidate to inference config map for the evaluation run. The candidate can be up to 128 characters long and can consist of any UTF-8 characters. "a_key": { # An inference config used for model inference during the evaluation run. - "agentConfig": { # Configuration that describes an agent. # Optional. Agent config used to generate responses. + "agentConfig": { # Configuration that describes an agent. # Optional. Deprecated: Use `agents` instead. Agent config used to generate responses. "developerInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The developer instruction for the agent. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1322,12 +1327,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1340,9 +1345,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1384,7 +1389,7 @@Method Details
}, "tools": [ # Optional. The tools available to the agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1722,7 +1727,7 @@Method Details
"topK": 3.14, # Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a `top_k` of 40 means the model will choose the next word from the 40 most likely words. "topP": 3.14, # Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least `top_p`. This helps generate more diverse and less repetitive responses. For example, a `top_p` of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or `top_p`, but not both. }, - "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` + "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Anthropic and Llama third-party models are also supported through Model Garden. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Third-party model format: `projects/{project}/locations/{location}/publishers/anthropic/models/{model}` `projects/{project}/locations/{location}/publishers/llama/models/{model}` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` }, }, "labels": { # Optional. Labels for the evaluation run. @@ -1891,6 +1896,11 @@Method Details
}, "sampleCount": 42, # Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. }, + "datasetCustomMetrics": [ # Optional. Specifications for custom dataset-level aggregations. + { # Defines a custom dataset-level aggregation. + "displayName": "A String", # Optional. A display name for this custom summary metric. Used to prefix keys in the output summaryMetrics map. If not provided, a default name like "dataset_custom_metric_1", "dataset_custom_metric_2", etc., will be generated based on the order in the repeated field. + }, + ], "metrics": [ # Required. The metrics to be calculated in the evaluation run. { # The metric used for evaluation runs. "computationBasedMetricSpec": { # Specification for a computation based metric. # Spec for a computation based metric. @@ -2907,15 +2917,15 @@Method Details
"evaluationSetSnapshot": "A String", # Output only. The specific evaluation set of the evaluation run. For runs with an evaluation set input, this will be that same set. For runs with BigQuery input, it's the sampled BigQuery dataset. "inferenceConfigs": { # Optional. The candidate to inference config map for the evaluation run. The candidate can be up to 128 characters long and can consist of any UTF-8 characters. "a_key": { # An inference config used for model inference during the evaluation run. - "agentConfig": { # Configuration that describes an agent. # Optional. Agent config used to generate responses. + "agentConfig": { # Configuration that describes an agent. # Optional. Deprecated: Use `agents` instead. Agent config used to generate responses. "developerInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The developer instruction for the agent. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2924,12 +2934,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2942,9 +2952,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2986,7 +2996,7 @@Method Details
}, "tools": [ # Optional. The tools available to the agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3324,7 +3334,7 @@Method Details
"topK": 3.14, # Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a `top_k` of 40 means the model will choose the next word from the 40 most likely words. "topP": 3.14, # Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least `top_p`. This helps generate more diverse and less repetitive responses. For example, a `top_p` of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or `top_p`, but not both. }, - "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` + "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Anthropic and Llama third-party models are also supported through Model Garden. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Third-party model format: `projects/{project}/locations/{location}/publishers/anthropic/models/{model}` `projects/{project}/locations/{location}/publishers/llama/models/{model}` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` }, }, "labels": { # Optional. Labels for the evaluation run. @@ -3535,6 +3545,11 @@Method Details
}, "sampleCount": 42, # Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. }, + "datasetCustomMetrics": [ # Optional. Specifications for custom dataset-level aggregations. + { # Defines a custom dataset-level aggregation. + "displayName": "A String", # Optional. A display name for this custom summary metric. Used to prefix keys in the output summaryMetrics map. If not provided, a default name like "dataset_custom_metric_1", "dataset_custom_metric_2", etc., will be generated based on the order in the repeated field. + }, + ], "metrics": [ # Required. The metrics to be calculated in the evaluation run. { # The metric used for evaluation runs. "computationBasedMetricSpec": { # Specification for a computation based metric. # Spec for a computation based metric. @@ -4551,15 +4566,15 @@Method Details
"evaluationSetSnapshot": "A String", # Output only. The specific evaluation set of the evaluation run. For runs with an evaluation set input, this will be that same set. For runs with BigQuery input, it's the sampled BigQuery dataset. "inferenceConfigs": { # Optional. The candidate to inference config map for the evaluation run. The candidate can be up to 128 characters long and can consist of any UTF-8 characters. "a_key": { # An inference config used for model inference during the evaluation run. - "agentConfig": { # Configuration that describes an agent. # Optional. Agent config used to generate responses. + "agentConfig": { # Configuration that describes an agent. # Optional. Deprecated: Use `agents` instead. Agent config used to generate responses. "developerInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The developer instruction for the agent. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4568,12 +4583,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4586,9 +4601,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4630,7 +4645,7 @@Method Details
}, "tools": [ # Optional. The tools available to the agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4968,7 +4983,7 @@Method Details
"topK": 3.14, # Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a `top_k` of 40 means the model will choose the next word from the 40 most likely words. "topP": 3.14, # Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least `top_p`. This helps generate more diverse and less repetitive responses. For example, a `top_p` of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or `top_p`, but not both. }, - "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` + "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Anthropic and Llama third-party models are also supported through Model Garden. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Third-party model format: `projects/{project}/locations/{location}/publishers/anthropic/models/{model}` `projects/{project}/locations/{location}/publishers/llama/models/{model}` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` }, }, "labels": { # Optional. Labels for the evaluation run. @@ -5150,6 +5165,11 @@Method Details
}, "sampleCount": 42, # Optional. Number of samples for each instance in the dataset. If not specified, the default is 4. Minimum value is 1, maximum value is 32. }, + "datasetCustomMetrics": [ # Optional. Specifications for custom dataset-level aggregations. + { # Defines a custom dataset-level aggregation. + "displayName": "A String", # Optional. A display name for this custom summary metric. Used to prefix keys in the output summaryMetrics map. If not provided, a default name like "dataset_custom_metric_1", "dataset_custom_metric_2", etc., will be generated based on the order in the repeated field. + }, + ], "metrics": [ # Required. The metrics to be calculated in the evaluation run. { # The metric used for evaluation runs. "computationBasedMetricSpec": { # Specification for a computation based metric. # Spec for a computation based metric. @@ -6166,15 +6186,15 @@Method Details
"evaluationSetSnapshot": "A String", # Output only. The specific evaluation set of the evaluation run. For runs with an evaluation set input, this will be that same set. For runs with BigQuery input, it's the sampled BigQuery dataset. "inferenceConfigs": { # Optional. The candidate to inference config map for the evaluation run. The candidate can be up to 128 characters long and can consist of any UTF-8 characters. "a_key": { # An inference config used for model inference during the evaluation run. - "agentConfig": { # Configuration that describes an agent. # Optional. Agent config used to generate responses. + "agentConfig": { # Configuration that describes an agent. # Optional. Deprecated: Use `agents` instead. Agent config used to generate responses. "developerInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The developer instruction for the agent. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6183,12 +6203,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6201,9 +6221,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6245,7 +6265,7 @@Method Details
}, "tools": [ # Optional. The tools available to the agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -6583,7 +6603,7 @@Method Details
"topK": 3.14, # Optional. Specifies the top-k sampling threshold. The model considers only the top k most probable tokens for the next token. This can be useful for generating more coherent and less random text. For example, a `top_k` of 40 means the model will choose the next word from the 40 most likely words. "topP": 3.14, # Optional. Specifies the nucleus sampling threshold. The model considers only the smallest set of tokens whose cumulative probability is at least `top_p`. This helps generate more diverse and less repetitive responses. For example, a `top_p` of 0.9 means the model considers tokens until the cumulative probability of the tokens to select from reaches 0.9. It's recommended to adjust either temperature or `top_p`, but not both. }, - "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` + "model": "A String", # Optional. The fully qualified name of the publisher model or endpoint to use. Anthropic and Llama third-party models are also supported through Model Garden. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Third-party model format: `projects/{project}/locations/{location}/publishers/anthropic/models/{model}` `projects/{project}/locations/{location}/publishers/llama/models/{model}` Endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` }, }, "labels": { # Optional. Labels for the evaluation run. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.exampleStores.html b/docs/dyn/aiplatform_v1beta1.projects.locations.exampleStores.html index df848af1fe..07c7914252 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.exampleStores.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.exampleStores.html @@ -245,11 +245,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -258,12 +258,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -276,9 +276,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -324,11 +324,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single step's content. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -337,12 +337,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -355,9 +355,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -607,11 +607,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -620,12 +620,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -638,9 +638,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -718,11 +718,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -731,12 +731,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -749,9 +749,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -797,11 +797,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single step's content. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -810,12 +810,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -828,9 +828,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -907,11 +907,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -920,12 +920,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -938,9 +938,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -986,11 +986,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single step's content. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -999,12 +999,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1017,9 +1017,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1094,11 +1094,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1107,12 +1107,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1125,9 +1125,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1173,11 +1173,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single step's content. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1186,12 +1186,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1204,9 +1204,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html index d1eb498cd7..ae8fe58cd0 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html @@ -1148,11 +1148,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1161,12 +1161,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1179,9 +1179,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1238,11 +1238,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1251,12 +1251,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1269,9 +1269,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.html b/docs/dyn/aiplatform_v1beta1.projects.locations.html index 243a555e2c..282ffbc086 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.html @@ -341,7 +341,7 @@Instance Methods
Generates rubrics for a given prompt. A rubric represents a single testable criterion for evaluation. One input prompt could have multiple rubrics This RPC allows users to get suggested rubrics based on provided prompt, which can then be reviewed and used for subsequent evaluations.
-
generateSyntheticData(location, body=None, x__xgafv=None)Generates synthetic data based on the provided configuration.
+Generates synthetic (artificial) data based on a description
Gets information about a location.
@@ -402,7 +402,7 @@Method Details
}, "tools": [ # Optional. The tools to use for AskContexts. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -695,7 +695,7 @@Method Details
}, "tools": [ # Optional. The tools to use for AskContexts. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -961,11 +961,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -974,12 +974,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -992,9 +992,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1089,11 +1089,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1102,12 +1102,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1120,9 +1120,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1201,11 +1201,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Input content to corroborate, only text format is supported for now. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1214,12 +1214,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1232,9 +1232,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2355,11 +2355,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2368,12 +2368,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2386,9 +2386,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2438,7 +2438,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2673,11 +2673,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2686,12 +2686,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2704,9 +2704,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2756,7 +2756,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2987,11 +2987,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3000,12 +3000,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3018,9 +3018,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3069,11 +3069,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3082,12 +3082,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3100,9 +3100,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3147,7 +3147,7 @@Method Details
"tools": { # Deprecated: Use `agent_eval_data` instead. Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3376,7 +3376,7 @@Method Details
{ # A single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3601,11 +3601,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3614,12 +3614,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3632,9 +3632,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3697,7 +3697,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3926,7 +3926,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4151,11 +4151,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4164,12 +4164,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4182,9 +4182,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4235,7 +4235,7 @@Method Details
}, ], }, - "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. + "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. If a key conflicts with a field in the EvaluationInstance (e.g. `prompt`), the value of the field will take precedence over the value in other_data. "mapInstance": { # Optional. Map of instance data. "a_key": { # Instance data used to populate placeholders in a metric prompt template. "contents": { # List of standard Content messages from Gemini API. # List of Gemini content data. @@ -4243,11 +4243,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4256,12 +4256,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4274,9 +4274,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4328,11 +4328,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4341,12 +4341,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4359,9 +4359,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4411,11 +4411,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4424,12 +4424,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4442,9 +4442,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4494,11 +4494,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4507,12 +4507,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4525,9 +4525,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4923,11 +4923,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4936,12 +4936,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4954,9 +4954,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5047,11 +5047,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5060,12 +5060,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5078,9 +5078,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5687,11 +5687,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5700,12 +5700,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5718,9 +5718,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5770,7 +5770,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -5998,11 +5998,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6011,12 +6011,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6029,9 +6029,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6235,27 +6235,27 @@Method Details
generateSyntheticData(location, body=None, x__xgafv=None)-Generates synthetic data based on the provided configuration. +Generates synthetic (artificial) data based on a description Args: - location: string, Required. The resource name of the Location to run the job. Format: `projects/{project}/locations/{location}` (required) + location: string, Required. The geographic location where the synthetic data generation request is processed. This should be in the format `projects/{project}/locations/{location}`. For example, `projects/my-project/locations/us-central1`. (required) body: object, The request body. The object takes the form of: -{ # Request message for DataFoundryService.GenerateSyntheticData. - "count": 42, # Required. The number of synthetic examples to generate. For this stateless API, the count is limited to a small number. - "examples": [ # Optional. A list of few-shot examples to guide the model's output style and format. - { # Represents a single synthetic example, composed of multiple fields. Used for providing few-shot examples in the request and for returning generated examples in the response. +{ # Request message for DataFoundryService.GenerateSyntheticData. It contains the settings and information needed to generate synthetic data. + "count": 42, # Required. The number of synthetic examples to generate. For this stateless API, you can generate up to 50 examples in a single request. + "examples": [ # Optional. A list of few-shot examples that help the model understand the desired style, tone, and format of the generated synthetic data. Providing these few-shot examples can significantly improve the quality and relevance of the output. + { # A single instance of generated synthetic data. Each example is made up of one or more named fields, as defined in `OutputFieldSpec`. These examples are used as few-shot examples to show the model what you want (in `GenerateSyntheticDataRequest.examples`) and to return generated examples in the response (in `GenerateSyntheticDataResponse.synthetic_examples`). "fields": [ # Required. A list of fields that constitute an example. - { # Represents a single named field within a SyntheticExample. - "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the field. + { # Represents a single named field within a synthetic example, consisting of a name and the actual content. + "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6264,12 +6264,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6282,9 +6282,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6324,20 +6324,20 @@Method Details
], "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'. }, - "fieldName": "A String", # Optional. The name of the field. + "fieldName": "A String", # Optional. The name of the specific field, such as "product_name" or "review_text". }, ], }, ], - "outputFieldSpecs": [ # Required. The schema of the desired output, defined by a list of fields. - { # Defines a specification for a single output field. - "fieldName": "A String", # Required. The name of the output field. + "outputFieldSpecs": [ # Required. Defines the schema of each synthetic example to be generated, defined by a list of fields. + { # Specifies the properties of a single field that are included in each generated synthetic example. This helps the model understand what kind of data to generate for each field. + "fieldName": "A String", # Required. The name of this field in the generated synthetic data, such as "email_subject" or "customer_review". "fieldType": "A String", # Optional. The data type of the field. Defaults to CONTENT if not set. - "guidance": "A String", # Optional. Optional, but recommended. Additional guidance specific to this field to provide targeted instructions for the LLM to generate the content of a single output field. While the LLM can sometimes infer content from the field name, providing explicit guidance is preferred. + "guidance": "A String", # Optional. Specific instructions for the large language model on how to generate content for this particular field. While the LLM can sometimes infer content from the field name, providing explicit guidance is preferred. For example, for a field named "review", the guidance could be "A positive review about a coffee maker." }, ], - "taskDescription": { # Defines a generation strategy based on a high-level task description. # Generate data from a high-level task description. - "taskDescription": "A String", # Required. A high-level description of the synthetic data to be generated. + "taskDescription": { # Defines a generation strategy based on a general task description. # Generates synthetic data based on a high-level description of the task or data you want. + "taskDescription": "A String", # Required. A general description of the type of synthetic data you want to generate. For example, "Generate customer reviews for a new smartphone." }, } @@ -6349,19 +6349,19 @@Method Details
Returns: An object of the form: - { # The response containing the generated data. - "syntheticExamples": [ # A list of generated synthetic examples. - { # Represents a single synthetic example, composed of multiple fields. Used for providing few-shot examples in the request and for returning generated examples in the response. + { # The response message for the `GenerateSyntheticData` method, containing the synthetic examples generated by the Gen AI evaluation service. + "syntheticExamples": [ # A list of generated synthetic examples, each containing a complete synthetic data instance generated based on your request. + { # A single instance of generated synthetic data. Each example is made up of one or more named fields, as defined in `OutputFieldSpec`. These examples are used as few-shot examples to show the model what you want (in `GenerateSyntheticDataRequest.examples`) and to return generated examples in the response (in `GenerateSyntheticDataResponse.synthetic_examples`). "fields": [ # Required. A list of fields that constitute an example. - { # Represents a single named field within a SyntheticExample. - "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the field. + { # Represents a single named field within a synthetic example, consisting of a name and the actual content. + "content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The actual content or value for this field. This can be text, images, or other types of data. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6370,12 +6370,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6388,9 +6388,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6430,7 +6430,7 @@Method Details
], "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'. }, - "fieldName": "A String", # Optional. The name of the field. + "fieldName": "A String", # Optional. The name of the specific field, such as "product_name" or "review_text". }, ], }, diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html index a545d7029d..0a05ccb18e 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html @@ -147,11 +147,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -160,12 +160,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -178,9 +178,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -264,11 +264,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -277,12 +277,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -295,9 +295,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -461,11 +461,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -474,12 +474,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -492,9 +492,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -536,7 +536,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -793,11 +793,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content to be embedded. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -806,12 +806,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -824,9 +824,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -866,6 +866,14 @@Method Details
], "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. If not set, the service will default to 'user'. }, + "embedContentConfig": { # Configurations for the EmbedContent API. # Optional. Configuration for the EmbedContent request. + "audioTrackExtraction": True or False, # Optional. Whether to extract audio from video content. + "autoTruncate": True or False, # Optional. Whether to silently truncate the input content if it's longer than the maximum sequence length. Only applicable to text-only embedding models. + "documentOcr": True or False, # Optional. Whether to enable OCR for document content. + "outputDimensionality": 42, # Optional. Reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end. + "taskType": "A String", # Optional. The task type of the embedding. Only applicable to text-only embedding models. + "title": "A String", # Optional. The title for the text. Only applicable to text-only embedding models. + }, "outputDimensionality": 42, # Optional. Deprecated: Please use EmbedContentConfig.output_dimensionality instead. Reduced dimension for the output embedding. If set, excessive values in the output embedding are truncated from the end. "taskType": "A String", # Optional. Deprecated: Please use EmbedContentConfig.task_type instead. The task type of the embedding. "title": "A String", # Optional. Deprecated: Please use EmbedContentConfig.title instead. The title for the text. @@ -1052,11 +1060,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1065,12 +1073,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1083,9 +1091,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1259,11 +1267,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1272,12 +1280,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1290,9 +1298,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1334,11 +1342,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1350,7 +1358,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1604,11 +1612,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1617,12 +1625,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1635,9 +1643,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2282,11 +2290,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2295,12 +2303,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2313,9 +2321,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2489,11 +2497,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2502,12 +2510,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2520,9 +2528,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2564,11 +2572,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -2580,7 +2588,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2834,11 +2842,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2847,12 +2855,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2865,9 +2873,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.html index 5d0cc70454..ff96f53bcc 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.html @@ -99,6 +99,11 @@Instance Methods
Returns the operations Resource.
+ +Returns the runtimeRevisions Resource.
+ @@ -167,7 +172,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -177,11 +185,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -190,12 +198,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -208,9 +216,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -520,7 +528,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -530,11 +541,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -543,12 +554,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -561,9 +572,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -804,7 +815,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -814,11 +828,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -827,12 +841,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -845,9 +859,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1058,7 +1072,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -1068,11 +1085,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1081,12 +1098,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1099,9 +1116,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.memories.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.memories.html index a4e064ff55..702bbe1182 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.memories.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.memories.html @@ -88,7 +88,7 @@Instance Methods
close()Close httplib2 connections.
-
+create(parent, body=None, x__xgafv=None)create(parent, body=None, memoryId=None, x__xgafv=None)Create a Memory.
@@ -124,7 +124,7 @@Method Details
-create(parent, body=None, x__xgafv=None)+create(parent, body=None, memoryId=None, x__xgafv=None)Create a Memory. Args: @@ -166,6 +166,7 @@Method Details
"updateTime": "A String", # Output only. Timestamp when this Memory was most recently updated. } + memoryId: string, Optional. The user defined ID to use for memory, which will become the final component of the memory resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format @@ -246,11 +247,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single piece of content from which to generate memories. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -259,12 +260,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -277,9 +278,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.html new file mode 100644 index 0000000000..9c4a3bc0da --- /dev/null +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.html @@ -0,0 +1,91 @@ + + + +Vertex AI API . projects . locations . reasoningEngines . runtimeRevisions
+Instance Methods
++
+operations()+Returns the operations Resource.
+ ++
+close()Close httplib2 connections.
+Method Details
+++ + \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.operations.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.operations.html new file mode 100644 index 0000000000..c79b04fe94 --- /dev/null +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.runtimeRevisions.operations.html @@ -0,0 +1,272 @@ + + + +close()+Close httplib2 connections.+Vertex AI API . projects . locations . reasoningEngines . runtimeRevisions . operations
+Instance Methods
+ +Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`.
++
+close()Close httplib2 connections.
+ +Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.
+ +Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
++
+list(name, filter=None, pageSize=None, pageToken=None, returnPartialSuccess=None, x__xgafv=None)Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.
+ +Retrieves the next page of results.
++
+wait(name, timeout=None, x__xgafv=None)Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done.
+Method Details
+++ +cancel(name, x__xgafv=None)+Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`. + +Args: + name: string, The name of the operation resource to be cancelled. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } +}+++ +close()+Close httplib2 connections.+++ +delete(name, x__xgafv=None)+Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. + +Args: + name: string, The name of the operation resource to be deleted. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } +}+++ +get(name, x__xgafv=None)+Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service. + +Args: + name: string, The name of the operation resource. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, +}+++ +list(name, filter=None, pageSize=None, pageToken=None, returnPartialSuccess=None, x__xgafv=None)+Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. + +Args: + name: string, The name of the operation's parent resource. (required) + filter: string, The standard list filter. + pageSize: integer, The standard list page size. + pageToken: string, The standard list page token. + returnPartialSuccess: boolean, When set to `true`, operations that are reachable are returned as normal, and those that are unreachable are returned in the ListOperationsResponse.unreachable field. This can only be `true` when reading across collections. For example, when `parent` is set to `"projects/example/locations/-"`. This field is not supported by default and will result in an `UNIMPLEMENTED` error if set unless explicitly documented otherwise in service or product specific documentation. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # The response message for Operations.ListOperations. + "nextPageToken": "A String", # The standard List next-page token. + "operations": [ # A list of operations that matches the specified filter in the request. + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + }, + ], + "unreachable": [ # Unordered list. Unreachable resources. Populated when the request sets `ListOperationsRequest.return_partial_success` and reads across collections. For example, when attempting to list all resources across all supported locations. + "A String", + ], +}+++ +list_next()+Retrieves the next page of results. + + Args: + previous_request: The request for the previous page. (required) + previous_response: The response from the request for the previous page. (required) + + Returns: + A request object that you can call 'execute()' on to request the next + page. Returns None if there are no more items in the collection. ++++ + \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.events.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.events.html index 2c6a028a3a..921fd09d03 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.events.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.events.html @@ -129,11 +129,11 @@wait(name, timeout=None, x__xgafv=None)+Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done. + +Args: + name: string, The name of the operation resource to wait on. (required) + timeout: string, The maximum duration to wait before timing out. If left blank, the wait will be at most the time permitted by the underlying HTTP/RPC protocol. If RPC context deadline is also specified, the shorter one will be used. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, +}+Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -142,12 +142,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -160,9 +160,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -318,6 +318,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. }, ], diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.html b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.html index c7bc9fb403..0fb21688fa 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.reasoningEngines.sessions.html @@ -91,7 +91,7 @@Instance Methods
close()Close httplib2 connections.
-
+create(parent, body=None, x__xgafv=None)create(parent, body=None, sessionId=None, x__xgafv=None)Creates a new Session.
@@ -137,11 +137,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -150,12 +150,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -168,9 +168,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -326,6 +326,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. } @@ -347,7 +350,7 @@Method Details
-create(parent, body=None, x__xgafv=None)+create(parent, body=None, sessionId=None, x__xgafv=None)Creates a new Session. Args: @@ -371,6 +374,7 @@Method Details
"userId": "A String", # Required. Immutable. String id provided by the user } + sessionId: string, Optional. The user defined ID to use for session, which will become the final component of the session resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.tuningJobs.html b/docs/dyn/aiplatform_v1beta1.projects.locations.tuningJobs.html index 350013204e..883518a5fb 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.tuningJobs.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.tuningJobs.html @@ -894,11 +894,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -907,12 +907,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -925,9 +925,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1067,11 +1067,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1080,12 +1080,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1098,9 +1098,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1147,11 +1147,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1160,12 +1160,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1178,9 +1178,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1273,11 +1273,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1286,12 +1286,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1304,9 +1304,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2178,11 +2178,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2191,12 +2191,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2209,9 +2209,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2351,11 +2351,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2364,12 +2364,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2382,9 +2382,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2431,11 +2431,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2444,12 +2444,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2462,9 +2462,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2557,11 +2557,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2570,12 +2570,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2588,9 +2588,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3469,11 +3469,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3482,12 +3482,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3500,9 +3500,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3642,11 +3642,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3655,12 +3655,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3673,9 +3673,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3722,11 +3722,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3735,12 +3735,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3753,9 +3753,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3848,11 +3848,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3861,12 +3861,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3879,9 +3879,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4766,11 +4766,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4779,12 +4779,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4797,9 +4797,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4939,11 +4939,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4952,12 +4952,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4970,9 +4970,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5019,11 +5019,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5032,12 +5032,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5050,9 +5050,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5145,11 +5145,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5158,12 +5158,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5176,9 +5176,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5320,11 +5320,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the prompt to optimize. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5333,12 +5333,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5351,9 +5351,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -5408,11 +5408,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The optimized prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -5421,12 +5421,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -5439,9 +5439,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6255,11 +6255,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6268,12 +6268,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6286,9 +6286,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6428,11 +6428,11 @@Method Details
"completion": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Single turn completion for the given prompt. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6441,12 +6441,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6459,9 +6459,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6508,11 +6508,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6521,12 +6521,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6539,9 +6539,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -6634,11 +6634,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -6647,12 +6647,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -6665,9 +6665,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.publishers.models.html b/docs/dyn/aiplatform_v1beta1.publishers.models.html index e8eb79e1fb..70c794b27e 100644 --- a/docs/dyn/aiplatform_v1beta1.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.publishers.models.html @@ -127,11 +127,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -140,12 +140,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -158,9 +158,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -244,11 +244,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -257,12 +257,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -275,9 +275,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -441,11 +441,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -454,12 +454,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -472,9 +472,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -516,7 +516,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -816,11 +816,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -829,12 +829,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -847,9 +847,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1023,11 +1023,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1036,12 +1036,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1054,9 +1054,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1098,11 +1098,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -1114,7 +1114,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1368,11 +1368,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1381,12 +1381,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1399,9 +1399,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1660,7 +1660,7 @@Method Details
"A String", ], "launchStage": "A String", # Optional. Indicates the launch stage of the model. - "name": "A String", # Output only. The resource name of the PublisherModel. + "name": "A String", # Output only. Identifier. The resource name of the PublisherModel. "openSourceCategory": "A String", # Required. Indicates the open source category of the publisher model. "parent": { # The information about the parent of a model. # Optional. The parent that this model was customized from. E.g., Vision API, Natural Language API, LaMDA, T5, etc. Foundation models don't have parents. "displayName": "A String", # Required. The display name of the parent. E.g., LaMDA, T5, Vision API, Natural Language API. @@ -2276,7 +2276,7 @@Method Details
"A String", ], "launchStage": "A String", # Optional. Indicates the launch stage of the model. - "name": "A String", # Output only. The resource name of the PublisherModel. + "name": "A String", # Output only. Identifier. The resource name of the PublisherModel. "openSourceCategory": "A String", # Required. Indicates the open source category of the publisher model. "parent": { # The information about the parent of a model. # Optional. The parent that this model was customized from. E.g., Vision API, Natural Language API, LaMDA, T5, etc. Foundation models don't have parents. "displayName": "A String", # Required. The display name of the parent. E.g., LaMDA, T5, Vision API, Natural Language API. @@ -2973,11 +2973,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2986,12 +2986,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3004,9 +3004,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3180,11 +3180,11 @@Method Details
"systemInstruction": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3193,12 +3193,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3211,9 +3211,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3255,11 +3255,11 @@Method Details
}, "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request. "functionCallingConfig": { # Function calling config. # Optional. Function calling config. - "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided. + "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match FunctionDeclaration.name. With mode set to ANY, model will predict a function call from the set of function names provided. "A String", ], "mode": "A String", # Optional. Function calling mode. - "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the [FunctionCall.partial_args] field. + "streamFunctionCallArguments": True or False, # Optional. When set to true, arguments of a single function call will be streamed out in multiple parts/contents/responses. Partial parameter results will be returned in the `FunctionCall.partial_args` field. }, "retrievalConfig": { # Retrieval config. # Optional. Retrieval config. "languageCode": "A String", # The language code of the user. @@ -3271,7 +3271,7 @@Method Details
}, "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -3525,11 +3525,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Output only. The content of the candidate. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3538,12 +3538,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3556,9 +3556,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.html index 8149d6bd62..ed616ef3e4 100644 --- a/docs/dyn/aiplatform_v1beta1.reasoningEngines.html +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.html @@ -99,6 +99,11 @@Instance Methods
Returns the operations Resource.
+ +Returns the runtimeRevisions Resource.
+ @@ -157,7 +162,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -167,11 +175,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -180,12 +188,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -198,9 +206,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -511,7 +519,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -521,11 +532,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -534,12 +545,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -552,9 +563,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -760,7 +771,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -770,11 +784,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -783,12 +797,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -801,9 +815,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1014,7 +1028,10 @@Method Details
"contextSpec": { # Configuration for how Agent Engine sub-resources should manage context. # Optional. Configuration for how Agent Engine sub-resources should manage context. "memoryBankConfig": { # Specification for a Memory Bank. # Optional. Specification for a Memory Bank, which manages memories for the Agent Engine. "customizationConfigs": [ # Optional. Configuration for how to customize Memory Bank behavior for a particular scope. - { # Configuration for organizing memories for a particular scope. + { # Represents configuration for organizing memories for a particular scope. + "consolidationConfig": { # Represents configuration for customizing how memories are consolidated. # Optional. Represents configuration for customizing how memories are consolidated together. + "revisionsPerCandidateCount": 42, # Optional. The maximum number of revisions to consider for each candidate memory. If not set, then the default value (1) will be used, which means that only the latest revision will be considered. + }, "enableThirdPersonMemories": True or False, # Optional. If true, then the memories will be generated in the third person (i.e. "The user generates memories with Memory Bank."). By default, the memories will be generated in the first person (i.e. "I generate memories with Memory Bank.") "generateMemoriesExamples": [ # Optional. Examples of how to generate memories for a particular scope. { # An example of how to generate memories for a particular scope. @@ -1024,11 +1041,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1037,12 +1054,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1055,9 +1072,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.memories.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.memories.html index ce0003d760..319ab63307 100644 --- a/docs/dyn/aiplatform_v1beta1.reasoningEngines.memories.html +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.memories.html @@ -88,7 +88,7 @@Instance Methods
close()Close httplib2 connections.
-
+create(parent, body=None, x__xgafv=None)create(parent, body=None, memoryId=None, x__xgafv=None)Create a Memory.
@@ -124,7 +124,7 @@Method Details
-create(parent, body=None, x__xgafv=None)+create(parent, body=None, memoryId=None, x__xgafv=None)Create a Memory. Args: @@ -166,6 +166,7 @@Method Details
"updateTime": "A String", # Output only. Timestamp when this Memory was most recently updated. } + memoryId: string, Optional. The user defined ID to use for memory, which will become the final component of the memory resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format @@ -246,11 +247,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. A single piece of content from which to generate memories. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -259,12 +260,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -277,9 +278,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.html new file mode 100644 index 0000000000..2d404847da --- /dev/null +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.html @@ -0,0 +1,91 @@ + + + +Vertex AI API . reasoningEngines . runtimeRevisions
+Instance Methods
++
+operations()+Returns the operations Resource.
+ ++
+close()Close httplib2 connections.
+Method Details
+++ + \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.operations.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.operations.html new file mode 100644 index 0000000000..b1c93b3255 --- /dev/null +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.runtimeRevisions.operations.html @@ -0,0 +1,272 @@ + + + +close()+Close httplib2 connections.+Vertex AI API . reasoningEngines . runtimeRevisions . operations
+Instance Methods
+ +Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`.
++
+close()Close httplib2 connections.
+ +Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.
+ +Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
++
+list(name, filter=None, pageSize=None, pageToken=None, returnPartialSuccess=None, x__xgafv=None)Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.
+ +Retrieves the next page of results.
++
+wait(name, timeout=None, x__xgafv=None)Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done.
+Method Details
+++ +cancel(name, x__xgafv=None)+Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of `1`, corresponding to `Code.CANCELLED`. + +Args: + name: string, The name of the operation resource to be cancelled. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } +}+++ +close()+Close httplib2 connections.+++ +delete(name, x__xgafv=None)+Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. + +Args: + name: string, The name of the operation resource to be deleted. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); } +}+++ +get(name, x__xgafv=None)+Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service. + +Args: + name: string, The name of the operation resource. (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, +}+++ +list(name, filter=None, pageSize=None, pageToken=None, returnPartialSuccess=None, x__xgafv=None)+Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. + +Args: + name: string, The name of the operation's parent resource. (required) + filter: string, The standard list filter. + pageSize: integer, The standard list page size. + pageToken: string, The standard list page token. + returnPartialSuccess: boolean, When set to `true`, operations that are reachable are returned as normal, and those that are unreachable are returned in the ListOperationsResponse.unreachable field. This can only be `true` when reading across collections. For example, when `parent` is set to `"projects/example/locations/-"`. This field is not supported by default and will result in an `UNIMPLEMENTED` error if set unless explicitly documented otherwise in service or product specific documentation. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # The response message for Operations.ListOperations. + "nextPageToken": "A String", # The standard List next-page token. + "operations": [ # A list of operations that matches the specified filter in the request. + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + }, + ], + "unreachable": [ # Unordered list. Unreachable resources. Populated when the request sets `ListOperationsRequest.return_partial_success` and reads across collections. For example, when attempting to list all resources across all supported locations. + "A String", + ], +}+++ +list_next()+Retrieves the next page of results. + + Args: + previous_request: The request for the previous page. (required) + previous_response: The response from the request for the previous page. (required) + + Returns: + A request object that you can call 'execute()' on to request the next + page. Returns None if there are no more items in the collection. ++++ + \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.events.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.events.html index 2189cfd24c..7dfa3d180f 100644 --- a/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.events.html +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.events.html @@ -129,11 +129,11 @@wait(name, timeout=None, x__xgafv=None)+Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done. + +Args: + name: string, The name of the operation resource to wait on. (required) + timeout: string, The maximum duration to wait before timing out. If left blank, the wait will be at most the time permitted by the underlying HTTP/RPC protocol. If RPC context deadline is also specified, the shorter one will be used. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, +}+Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -142,12 +142,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -160,9 +160,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -318,6 +318,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. }, ], diff --git a/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.html b/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.html index 1a6dc87639..e19afaf08a 100644 --- a/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.html +++ b/docs/dyn/aiplatform_v1beta1.reasoningEngines.sessions.html @@ -91,7 +91,7 @@Instance Methods
close()Close httplib2 connections.
-
+create(parent, body=None, x__xgafv=None)create(parent, body=None, sessionId=None, x__xgafv=None)Creates a new Session.
@@ -137,11 +137,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Optional. Content of the event provided by the author. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -150,12 +150,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -168,9 +168,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -326,6 +326,9 @@Method Details
}, "invocationId": "A String", # Required. The invocation id of the event, multiple events can have the same invocation id. "name": "A String", # Identifier. The resource name of the event. Format:`projects/{project}/locations/{location}/reasoningEngines/{reasoning_engine}/sessions/{session}/events/{event}`. + "rawEvent": { # Optional. Weakly typed raw event data in proto struct format. + "a_key": "", # Properties of the object. + }, "timestamp": "A String", # Required. Timestamp when the event was created on client side. } @@ -347,7 +350,7 @@Method Details
-create(parent, body=None, x__xgafv=None)+create(parent, body=None, sessionId=None, x__xgafv=None)Creates a new Session. Args: @@ -371,6 +374,7 @@Method Details
"userId": "A String", # Required. Immutable. String id provided by the user } + sessionId: string, Optional. The user defined ID to use for session, which will become the final component of the session resource name. If not provided, Vertex AI will generate a value for this ID. This value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The first character must be a letter, and the last character must be a letter or number. x__xgafv: string, V1 error format. Allowed values 1 - v1 error format diff --git a/docs/dyn/aiplatform_v1beta1.v1beta1.html b/docs/dyn/aiplatform_v1beta1.v1beta1.html index eb61fee5bf..65a9795d39 100644 --- a/docs/dyn/aiplatform_v1beta1.v1beta1.html +++ b/docs/dyn/aiplatform_v1beta1.v1beta1.html @@ -789,11 +789,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -802,12 +802,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -820,9 +820,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -872,7 +872,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1107,11 +1107,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1120,12 +1120,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1138,9 +1138,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1190,7 +1190,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1421,11 +1421,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1434,12 +1434,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1452,9 +1452,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1503,11 +1503,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -1516,12 +1516,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -1534,9 +1534,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -1581,7 +1581,7 @@Method Details
"tools": { # Deprecated: Use `agent_eval_data` instead. Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -1810,7 +1810,7 @@Method Details
{ # A single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2035,11 +2035,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2048,12 +2048,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2066,9 +2066,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2131,7 +2131,7 @@Method Details
], "tools": [ # Optional. The list of tools available to this agent. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2360,7 +2360,7 @@Method Details
{ # Represents a single event in the execution trace. "activeTools": [ # Optional. The list of tools that were active/available to the agent at the time of this event. This overrides the `AgentConfig.tools` if set. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -2585,11 +2585,11 @@Method Details
"content": { # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. # Required. The content of the event (e.g., text response, tool call, tool response). "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2598,12 +2598,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2616,9 +2616,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2669,7 +2669,7 @@Method Details
}, ], }, - "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. + "otherData": { # Instance data specified as a map. # Optional. Other data used to populate placeholders based on their key. If a key conflicts with a field in the EvaluationInstance (e.g. `prompt`), the value of the field will take precedence over the value in other_data. "mapInstance": { # Optional. Map of instance data. "a_key": { # Instance data used to populate placeholders in a metric prompt template. "contents": { # List of standard Content messages from Gemini API. # List of Gemini content data. @@ -2677,11 +2677,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2690,12 +2690,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2708,9 +2708,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2762,11 +2762,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2775,12 +2775,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2793,9 +2793,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2845,11 +2845,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2858,12 +2858,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2876,9 +2876,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -2928,11 +2928,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -2941,12 +2941,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -2959,9 +2959,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3357,11 +3357,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3370,12 +3370,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3388,9 +3388,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -3481,11 +3481,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -3494,12 +3494,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -3512,9 +3512,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4120,11 +4120,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4133,12 +4133,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4151,9 +4151,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. @@ -4203,7 +4203,7 @@Method Details
"tools": { # Represents a list of tools for an agent. # List of tools. "tool": [ # Optional. List of tools: each tool can have multiple function declarations. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). - "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also [ExecutableCode]and [CodeExecutionResult] which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. + "codeExecution": { # Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. # Optional. CodeExecution tool type. Enables the model to execute code as part of generation. }, "computerUse": { # Tool to support computer use. # Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. "environment": "A String", # Required. The environment being operated. @@ -4431,11 +4431,11 @@Method Details
{ # The structured data content of a message. A Content message contains a `role` field, which indicates the producer of the content, and a `parts` field, which contains the multi-part data of the message. "parts": [ # Required. A list of Part objects that make up a single message. Parts of a message can have different MIME types. A Content message must have at least one Part. { # A datatype containing media that is part of a multi-part Content message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. For media types that are not text, `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes. - "codeExecutionResult": { # Result of executing the [ExecutableCode]. Only generated when using the [CodeExecution] tool, and always follows a `part` containing the [ExecutableCode]. # Optional. The result of executing the ExecutableCode. + "codeExecutionResult": { # Result of executing the ExecutableCode. Generated only when the `CodeExecution` tool is used. # Optional. The result of executing the ExecutableCode. "outcome": "A String", # Required. Outcome of the code execution. "output": "A String", # Optional. Contains stdout when code execution is successful, stderr or other description otherwise. }, - "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the [CodeExecution] tool, in which the code will be automatically executed, and a corresponding [CodeExecutionResult] will also be generated. # Optional. Code generated by the model that is intended to be executed. + "executableCode": { # Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the `CodeExecution` tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated. # Optional. Code generated by the model that is intended to be executed. "code": "A String", # Required. The code to be executed. "language": "A String", # Required. Programming language of the `code`. }, @@ -4444,12 +4444,12 @@Method Details
"fileUri": "A String", # Required. The URI of the file in Google Cloud Storage. "mimeType": "A String", # Required. The IANA standard MIME type of the source data. }, - "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. - "args": { # Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. + "functionCall": { # A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values. # Optional. A predicted function call returned from the model. This contains the name of the function to call and the arguments to pass to the function. + "args": { # Optional. The function parameters and values in JSON object format. See FunctionDeclaration.parameters for parameter details. "a_key": "", # Properties of the object. }, "id": "A String", # Optional. The unique id of the function call. If populated, the client to execute the `function_call` and return the response with the matching `id`. - "name": "A String", # Optional. The name of the function to call. Matches [FunctionDeclaration.name]. + "name": "A String", # Optional. The name of the function to call. Matches FunctionDeclaration.name. "partialArgs": [ # Optional. The partial argument value of the function call. If provided, represents the arguments/fields that are streamed incrementally. { # Partial argument value of the function call. "boolValue": True or False, # Optional. Represents a boolean value. @@ -4462,9 +4462,9 @@Method Details
], "willContinue": True or False, # Optional. Whether this is the last part of the FunctionCall. If true, another partial message for the current FunctionCall is expected to follow. }, - "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. + "functionResponse": { # The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a `FunctionCall` made based on model prediction. # Optional. The result of a function call. This is used to provide the model with the result of a function call that it predicted. "id": "A String", # Optional. The id of the function call this response is for. Populated by the client to match the corresponding function call `id`. - "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name]. + "name": "A String", # Required. The name of the function to call. Matches FunctionDeclaration.name and FunctionCall.name. "parts": [ # Optional. Ordered `Parts` that constitute a function response. Parts may have different IANA MIME types. { # A datatype containing media that is part of a `FunctionResponse` message. A `FunctionResponsePart` consists of data which has an associated datatype. A `FunctionResponsePart` can only contain one of the accepted types in `FunctionResponsePart.data`. A `FunctionResponsePart` must have a fixed IANA MIME type identifying the type and subtype of the media if the `inline_data` field is filled with raw bytes. "fileData": { # URI based data for function response. # URI based data. diff --git a/docs/dyn/analyticshub_v1.projects.locations.dataExchanges.listings.html b/docs/dyn/analyticshub_v1.projects.locations.dataExchanges.listings.html index ac5626746e..6e6633e91e 100644 --- a/docs/dyn/analyticshub_v1.projects.locations.dataExchanges.listings.html +++ b/docs/dyn/analyticshub_v1.projects.locations.dataExchanges.listings.html @@ -927,6 +927,12 @@Method Details
"useTopicSchema": True or False, # Optional. When true, use the topic's schema as the columns to write to in BigQuery, if it exists. `use_topic_schema` and `use_table_schema` cannot be enabled at the same time. "writeMetadata": True or False, # Optional. When true, write the subscription name, message_id, publish_time, attributes, and ordering_key to additional columns in the table. The subscription name, message_id, and publish_time fields are put in their own columns while all other message properties (other than data) are written to a JSON object in the attributes column. }, + "bigtableConfig": { # Configuration for a Bigtable subscription. The Pub/Sub message will be written to a Bigtable row as follows: - row key: subscription name and message ID delimited by #. - columns: message bytes written to a single column family "data" with an empty-string column qualifier. - cell timestamp: the message publish timestamp. # Optional. If delivery to Bigtable is used with this subscription, this field is used to configure it. + "appProfileId": "A String", # Optional. The app profile to use for the Bigtable writes. If not specified, the "default" application profile will be used. The app profile must use single-cluster routing. + "serviceAccountEmail": "A String", # Optional. The service account to use to write to Bigtable. The subscription creator or updater that specifies this field must have `iam.serviceAccounts.actAs` permission on the service account. If not specified, the Pub/Sub [service agent]({$universe.dns_names.final_documentation_domain}/iam/docs/service-agents), service-{project_number}@gcp-sa-pubsub.iam.gserviceaccount.com, is used. + "table": "A String", # Optional. The unique name of the table to write messages to. Values are of the form `projects//instances//tables/`. + "writeMetadata": True or False, # Optional. When true, write the subscription name, message_id, publish_time, attributes, and ordering_key to additional columns in the table under the pubsub_metadata column family. The subscription name, message_id, and publish_time fields are put in their own columns while all other message properties (other than data) are written to a JSON object in the attributes column. + }, "cloudStorageConfig": { # Configuration for a Cloud Storage subscription. # Optional. If delivery to Google Cloud Storage is used with this subscription, this field is used to configure it. "avroConfig": { # Configuration for writing message data in Avro format. Message payloads and metadata will be written to files as an Avro binary. # Optional. If set, message data will be written to Cloud Storage in Avro format. "useTopicSchema": True or False, # Optional. When true, the output Cloud Storage file will be serialized using the topic schema, if it exists. diff --git a/docs/dyn/androidmanagement_v1.enterprises.policies.html b/docs/dyn/androidmanagement_v1.enterprises.policies.html index 5af5524096..9f7460aed3 100644 --- a/docs/dyn/androidmanagement_v1.enterprises.policies.html +++ b/docs/dyn/androidmanagement_v1.enterprises.policies.html @@ -422,7 +422,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. @@ -949,7 +949,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. @@ -1562,7 +1562,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. @@ -2080,7 +2080,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. @@ -2596,7 +2596,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. @@ -3128,7 +3128,7 @@Method Details
"mountPhysicalMediaDisabled": True or False, # Whether the user mounting physical external media is disabled. "name": "A String", # The name of the policy in the form enterprises/{enterpriseId}/policies/{policyId}. "networkEscapeHatchEnabled": True or False, # Whether the network escape hatch is enabled. If a network connection can't be made at boot time, the escape hatch prompts the user to temporarily connect to a network in order to refresh the device policy. After applying policy, the temporary network will be forgotten and the device will continue booting. This prevents being unable to connect to a network if there is no suitable network in the last policy and the device boots into an app in lock task mode, or the user is otherwise unable to reach device settings.Note: Setting wifiConfigDisabled to true will override this setting under specific circumstances. Please see wifiConfigDisabled for further details. Setting configureWifi to DISALLOW_CONFIGURING_WIFI will override this setting under specific circumstances. Please see DISALLOW_CONFIGURING_WIFI for further details. - "networkResetDisabled": True or False, # Whether resetting network settings is disabled. + "networkResetDisabled": True or False, # Whether resetting network settings is disabled. This applies only on fully managed devices. A NonComplianceDetail with MANAGEMENT_MODE is reported for other management modes. "oncCertificateProviders": [ # This feature is not generally available. { # This feature is not generally available. "certificateReferences": [ # This feature is not generally available. diff --git a/docs/dyn/androidpublisher_v3.applications.html b/docs/dyn/androidpublisher_v3.applications.html index e92f80aec9..c5cde32ec2 100644 --- a/docs/dyn/androidpublisher_v3.applications.html +++ b/docs/dyn/androidpublisher_v3.applications.html @@ -79,6 +79,11 @@Instance Methods
Returns the deviceTierConfigs Resource.
++
+tracks()+Returns the tracks Resource.
+Close httplib2 connections.
diff --git a/docs/dyn/androidpublisher_v3.applications.tracks.html b/docs/dyn/androidpublisher_v3.applications.tracks.html new file mode 100644 index 0000000000..b44d06c02f --- /dev/null +++ b/docs/dyn/androidpublisher_v3.applications.tracks.html @@ -0,0 +1,91 @@ + + + +Google Play Android Developer API . applications . tracks
+Instance Methods
++
+releases()+Returns the releases Resource.
+ ++
+close()Close httplib2 connections.
+Method Details
+++ + \ No newline at end of file diff --git a/docs/dyn/androidpublisher_v3.applications.tracks.releases.html b/docs/dyn/androidpublisher_v3.applications.tracks.releases.html new file mode 100644 index 0000000000..28f1f01cd0 --- /dev/null +++ b/docs/dyn/androidpublisher_v3.applications.tracks.releases.html @@ -0,0 +1,119 @@ + + + +close()+Close httplib2 connections.+Google Play Android Developer API . applications . tracks . releases
+Instance Methods
++
+close()Close httplib2 connections.
+ +Returns the list of all releases for a given track. This excludes any releases that are obsolete.
+Method Details
+++ +close()+Close httplib2 connections.+++ + \ No newline at end of file diff --git a/docs/dyn/androidpublisher_v3.edits.html b/docs/dyn/androidpublisher_v3.edits.html index 4938779d16..8abbaf4c1b 100644 --- a/docs/dyn/androidpublisher_v3.edits.html +++ b/docs/dyn/androidpublisher_v3.edits.html @@ -128,7 +128,7 @@list(parent, x__xgafv=None)+Returns the list of all releases for a given track. This excludes any releases that are obsolete. + +Args: + parent: string, Required. The parent track, which owns this collection of releases. Format: applications/{package_name}/tracks/{track} (required) + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # Response listing all releases for a given track that are either ready to be sent for review, in review, approved, not approved or available. + "releases": [ # List of releases for this track. There will be a maximum of 20 releases returned. + { # Summary of a release. + "activeArtifacts": [ # List of active artifacts on this release. + { # Summary of an artifact. + "versionCode": 42, # The version code of the artifact. + }, + ], + "releaseLifecycleState": "A String", # The lifecycle state of a release. + "releaseName": "A String", # Name of the release. + "track": "A String", # Identifier of the track. More on [track name](https://developers.google.com/android-publisher/tracks). + }, + ], +}+Instance Methods
close()Close httplib2 connections.
-
+commit(packageName, editId, changesNotSentForReview=None, x__xgafv=None)commit(packageName, editId, changesInReviewBehavior=None, changesNotSentForReview=None, x__xgafv=None)Commits an app edit.
@@ -149,12 +149,17 @@
delete(packageName, editId, x__xgafv=None)Method Details
-commit(packageName, editId, changesNotSentForReview=None, x__xgafv=None)+commit(packageName, editId, changesInReviewBehavior=None, changesNotSentForReview=None, x__xgafv=None)Commits an app edit. Args: packageName: string, Package name of the app. (required) editId: string, Identifier of the edit. (required) + changesInReviewBehavior: string, Optional. Specify how the API should behave if there are changes currently in review. If this value is not set, it will default to "CANCEL_IN_REVIEW_AND_SUBMIT", which will cancel the changes in review and then send all the changes for publishing. + Allowed values + CHANGES_IN_REVIEW_BEHAVIOR_TYPE_UNSPECIFIED - Defaults to CANCEL_IN_REVIEW_AND_SUBMIT. + CANCEL_IN_REVIEW_AND_SUBMIT - If there are changes already in review, then this will cancel that review first and then send all the changes for publishing. + ERROR_IF_IN_REVIEW - If there are changes in review, then this will return an error. Please refer to the error message sample that is returned when this happens. Note that this won't invalidate the edit. If there aren't any changes in review, then this will continue and send the new changes for publishing. changesNotSentForReview: boolean, When a rejection happens, the parameter will make sure that the changes in this edit won't be reviewed until they are explicitly sent for review from within the Google Play Console UI. These changes will be added to any other changes that are not yet sent for review. x__xgafv: string, V1 error format. Allowed values diff --git a/docs/dyn/apihub_v1.projects.locations.apiHubInstances.html b/docs/dyn/apihub_v1.projects.locations.apiHubInstances.html index 316bc9cd0b..e605717694 100644 --- a/docs/dyn/apihub_v1.projects.locations.apiHubInstances.html +++ b/docs/dyn/apihub_v1.projects.locations.apiHubInstances.html @@ -89,6 +89,9 @@Instance Methods
Looks up an Api Hub instance in a given Google Cloud project. There will always be only one Api Hub instance for a Google Cloud project across all locations.
++
+patch(name, body=None, updateMask=None, x__xgafv=None)Update an Api Hub instance. The following fields in the ApiHubInstance can be updated: * disable_search * vertex_location * agent_registry_sync_config The update_mask should be used to specify the fields being updated.
Method Details
+close()@@ -106,6 +109,9 @@Method Details
{ # An ApiHubInstance represents the instance resources of the API Hub. Currently, only one ApiHub instance is allowed for each project. "config": { # Available configurations to provision an ApiHub Instance. # Required. Config of the ApiHub instance. + "agentRegistrySyncConfig": { # The configuration for Agent Registry sync. # Optional. The configuration for syncing MCP data in the API Hub instance to the Agent Registry. + "disabled": True or False, # Optional. If true, the MCP data sync to the Agent Registry will be disabled. The default value is false. + }, "cmekKeyName": "A String", # Optional. The Customer Managed Encryption Key (CMEK) used for data encryption. The CMEK name should follow the format of `projects/([^/]+)/locations/([^/]+)/keyRings/([^/]+)/cryptoKeys/([^/]+)`, where the location must match the instance location. If the CMEK is not provided, a GMEK will be created for the instance. "disableSearch": True or False, # Optional. If true, the search will be disabled for the instance. The default value is false. "encryptionType": "A String", # Optional. Encryption type for the region. If the encryption type is CMEK, the cmek_key_name must be provided. If no encryption type is provided, GMEK will be used. @@ -203,6 +209,9 @@Method Details
{ # An ApiHubInstance represents the instance resources of the API Hub. Currently, only one ApiHub instance is allowed for each project. "config": { # Available configurations to provision an ApiHub Instance. # Required. Config of the ApiHub instance. + "agentRegistrySyncConfig": { # The configuration for Agent Registry sync. # Optional. The configuration for syncing MCP data in the API Hub instance to the Agent Registry. + "disabled": True or False, # Optional. If true, the MCP data sync to the Agent Registry will be disabled. The default value is false. + }, "cmekKeyName": "A String", # Optional. The Customer Managed Encryption Key (CMEK) used for data encryption. The CMEK name should follow the format of `projects/([^/]+)/locations/([^/]+)/keyRings/([^/]+)/cryptoKeys/([^/]+)`, where the location must match the instance location. If the CMEK is not provided, a GMEK will be created for the instance. "disableSearch": True or False, # Optional. If true, the search will be disabled for the instance. The default value is false. "encryptionType": "A String", # Optional. Encryption type for the region. If the encryption type is CMEK, the cmek_key_name must be provided. If no encryption type is provided, GMEK will be used. @@ -237,6 +246,9 @@Method Details
{ # The LookupApiHubInstance method's response.` "apiHubInstance": { # An ApiHubInstance represents the instance resources of the API Hub. Currently, only one ApiHub instance is allowed for each project. # API Hub instance for a project if it exists, empty otherwise. "config": { # Available configurations to provision an ApiHub Instance. # Required. Config of the ApiHub instance. + "agentRegistrySyncConfig": { # The configuration for Agent Registry sync. # Optional. The configuration for syncing MCP data in the API Hub instance to the Agent Registry. + "disabled": True or False, # Optional. If true, the MCP data sync to the Agent Registry will be disabled. The default value is false. + }, "cmekKeyName": "A String", # Optional. The Customer Managed Encryption Key (CMEK) used for data encryption. The CMEK name should follow the format of `projects/([^/]+)/locations/([^/]+)/keyRings/([^/]+)/cryptoKeys/([^/]+)`, where the location must match the instance location. If the CMEK is not provided, a GMEK will be created for the instance. "disableSearch": True or False, # Optional. If true, the search will be disabled for the instance. The default value is false. "encryptionType": "A String", # Optional. Encryption type for the region. If the encryption type is CMEK, the cmek_key_name must be provided. If no encryption type is provided, GMEK will be used. @@ -255,4 +267,64 @@Method Details
}++patch(name, body=None, updateMask=None, x__xgafv=None)+Update an Api Hub instance. The following fields in the ApiHubInstance can be updated: * disable_search * vertex_location * agent_registry_sync_config The update_mask should be used to specify the fields being updated. + +Args: + name: string, Identifier. Format: `projects/{project}/locations/{location}/apiHubInstances/{apiHubInstance}`. (required) + body: object, The request body. + The object takes the form of: + +{ # An ApiHubInstance represents the instance resources of the API Hub. Currently, only one ApiHub instance is allowed for each project. + "config": { # Available configurations to provision an ApiHub Instance. # Required. Config of the ApiHub instance. + "agentRegistrySyncConfig": { # The configuration for Agent Registry sync. # Optional. The configuration for syncing MCP data in the API Hub instance to the Agent Registry. + "disabled": True or False, # Optional. If true, the MCP data sync to the Agent Registry will be disabled. The default value is false. + }, + "cmekKeyName": "A String", # Optional. The Customer Managed Encryption Key (CMEK) used for data encryption. The CMEK name should follow the format of `projects/([^/]+)/locations/([^/]+)/keyRings/([^/]+)/cryptoKeys/([^/]+)`, where the location must match the instance location. If the CMEK is not provided, a GMEK will be created for the instance. + "disableSearch": True or False, # Optional. If true, the search will be disabled for the instance. The default value is false. + "encryptionType": "A String", # Optional. Encryption type for the region. If the encryption type is CMEK, the cmek_key_name must be provided. If no encryption type is provided, GMEK will be used. + "vertexLocation": "A String", # Optional. The name of the Vertex AI location where the data store is stored. + }, + "createTime": "A String", # Output only. Creation timestamp. + "description": "A String", # Optional. Description of the ApiHub instance. + "labels": { # Optional. Instance labels to represent user-provided metadata. Refer to cloud documentation on labels for more details. https://cloud.google.com/compute/docs/labeling-resources + "a_key": "A String", + }, + "name": "A String", # Identifier. Format: `projects/{project}/locations/{location}/apiHubInstances/{apiHubInstance}`. + "state": "A String", # Output only. The current state of the ApiHub instance. + "stateMessage": "A String", # Output only. Extra information about ApiHub instance state. Currently the message would be populated when state is `FAILED`. + "updateTime": "A String", # Output only. Last update timestamp. +} + + updateMask: string, Optional. The list of fields to update. + x__xgafv: string, V1 error format. + Allowed values + 1 - v1 error format + 2 - v2 error format + +Returns: + An object of the form: + + { # This resource represents a long-running operation that is the result of a network API call. + "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available. + "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation. + "code": 42, # The status code, which should be an enum value of google.rpc.Code. + "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use. + { + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + ], + "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client. + }, + "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, + "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. + "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`. + "a_key": "", # Properties of the object. Contains field @type with type URL. + }, +}+