Support structured responses from the ChatGPT API #735
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
…ocess_inference_result`
…o more closely align with OpenAI
…tion from the ChatGPT API
…und for textual stop sequence matches
This removes direct references the internals of BufferedOutput to allow for better abstraction
joshuacoles
force-pushed
the
structured-output
branch
from
f19add6 to
099507c
Compare
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Outdated suggestions cannot be applied.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.
This PR implements the
response_formatproperty from the OpenAI API Spec (link) to allow specifying. It is implemented using the Low Level Guidance project which allows token masking based on JSON schemas and a variant of BNF grammars.There is support for JSON decoding, both with and without a supplied schema (although only supports a subset of JSON schemas). This is done by incorporating the masking process into the BufferedOutput object introduced in #734.
As with my other PRs this builds on them incrementally the others (#734, #720, #716) should be reviewed prior to this, I will keep this branch up to date with any changes from the prior PRs.
Still todo