Add support for OpenAI structured outputs with json_schema #40
+36
−9
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
prithvikannan
approved these changes
Jan 7, 2025
|
@prithvikannan I fixed the linting error, should be good to go now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implements a "json_schema" mode in ChatDatabricks to allow passing a JSON schema to models. Enhances existing options (function calling, JSON mode). Includes updates to test cases to reflect currently-available models and to test the new functionality. (And passes all unit tests.)
This approach is slightly less sophisticated than what the OpenAI integration uses (see https://github.com/langchain-ai/langchain/blob/ff675c11f6814e88aa338dc3668aa84d1ade3d19/libs/partners/openai/langchain_openai/chat_models/base.py#L1142). I personally don't think that the complexity makes sense right now (i.e., when enforced json schemas are not utilized by other Databricks models) but would be willing to implement it if desired by the project maintainers.
@prithvikannan happy to take feedback or comments