Support response api#18
Open
FR-SON wants to merge 4 commits into
Open
Conversation
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 bumps up the openai version to the most current 1.99.0 and with that introduces the
ResponsesAPI in addition to theChatCompletionAPI. The older response type is supported without changes. The newer response structure is now also supported for theParsedResponse, created withresponses.parsed()calls to an OpenAI client.Using a single dispatch pattern the correct implementation is chosen for
add_logprobsdepending on the given response type. This way, new response types can be added more easily in the future.Limitations
ParsedResponse. For example the basic Response is not supported, because without defining the desired response format the logprobs can not be added and validated properly.add_logprobs_inlineis not supported for the Response API because its main feature, theoutput_parsedfield, can not be updated with the inline probabilities. This mismatch between fields of a model is not desirable.