-
Notifications
You must be signed in to change notification settings - Fork 16.2k
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.
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
mistralai: support method="json_schema" in structured output #29461
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
method: Literal["function_calling", "json_mode"] = "function_calling", | ||
method: Literal[ | ||
"function_calling", "json_mode", "json_schema" | ||
] = "function_calling", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should we update default as well here or wait and see how people use it
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
separate release IMO
|
||
|
||
@pytest.mark.parametrize("schema", [Book, BookDict, Book.model_json_schema()]) | ||
def test_structured_output_json_schema(schema: Any) -> None: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
is this not a part of standard tests?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can merge into standard tests-- need to add ability to test multiple methods + more coverage of TypedDict.
https://docs.mistral.ai/capabilities/structured-output/custom_structured_output/