Skip to content

Update samplingMode preset documentation and WebIDL enum #210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
isaacahouma wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −1
Open

Update samplingMode preset documentation and WebIDL enum #210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -465,7 +465,9 @@ Developers can specify a high-level `samplingMode` during session creation to co
The allowed values for `samplingMode` are:
* `"most-predictable"`: For tasks requiring strict consistency and reproducibility (e.g. testing, code generation, or content extraction).
* `"predictable"`: For focused outputs with minimal variation.
* `"slightly-predictable"`: For focused outputs with a bit more variation than `"predictable"`.
* `"balanced"` (default): The standard preset for most conversational interactions.
* `"slightly-creative"`: For creative outputs that are slightly more focused than `"creative"`.
* `"creative"`: For tasks where variety and creativity are preferred over strict reproducibility.
* `"most-creative"`: For maximum diversity of output and creative brainstorming.

Expand Down
2 changes: 1 addition & 1 deletion index.bs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,7 +176,7 @@ dictionary LanguageModelMessageContent {
required LanguageModelMessageValue value;
};

enum LanguageModelSamplingMode { "most-predictable", "predictable", "balanced", "creative", "most-creative" };
enum LanguageModelSamplingMode { "most-predictable", "predictable", "slightly-predictable", "balanced", "slightly-creative", "creative", "most-creative" };

enum LanguageModelMessageRole { "system", "user", "assistant" };

Expand Down
Loading