Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -249,6 +249,9 @@ Deployment(
url_attachments=False,
folder_attachments=False,
allow_resume=True,
chat_completion=True,
responses_api=False,
reasoning_efforts=["low", "medium", "high"],
),
defaults={},
)
Expand Down Expand Up @@ -806,6 +809,9 @@ As a result, you will receive a list of `Application` objects:
url_attachments=False,
folder_attachments=False,
allow_resume=True,
chat_completion=True,
responses_api=False,
reasoning_efforts=[],
),
input_attachment_types=["image/png", "text/txt", "image/jpeg"],
defaults={},
Expand Down Expand Up @@ -877,6 +883,8 @@ ModelInfo(
)
```

For embedding models, `ModelInfo` also includes `embedding_dimensions` — the size of the output vector (e.g. `embedding_dimensions=1536`). It is omitted for non-embedding models.

### User

#### Get Authenticated User Info
Expand Down
6 changes: 6 additions & 0 deletions aidial_client/types/deployment.py
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,12 @@ class Features(ExtraAllowModel):
auto_caching: bool | None = None
assistant_attachments_in_request: bool | None = None
mcp: bool | None = None
chat_completion: bool | None = None
responses_api: bool | None = None
max_tokens_supported: bool | None = None
max_completion_tokens_supported: bool | None = None
custom_temperature_supported: bool | None = None
reasoning_efforts: list[str] = []


class DeploymentBase(ExtraAllowModel):
Expand Down
1 change: 1 addition & 0 deletions aidial_client/types/model.py
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ class ModelInfo(ExtraAllowModel):
updated_at: int | None = None
lifecycle_status: str | None = None
tokenizer_model: str | None = None
embedding_dimensions: int | None = None
capabilities: ModelCapabilities | None = None
limits: ModelLimits | None = None
pricing: ModelPricing | None = None
Loading