feat: preserve logprobs from chat completions API in ModelResponse #2134
+12
−0
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
The SDK already accepts `top_logprobs` in ModelSettings and passes it to the API, but the logprobs returned in the response were discarded during conversion. This change: 1. Adds an optional `logprobs` field to ModelResponse dataclass 2. Extracts logprobs from `choice.logprobs.content` in the chat completions model and includes them in the ModelResponse This enables use cases like RLHF training, confidence scoring, and uncertainty estimation that require access to token-level log probabilities.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
The SDK already accepts
top_logprobsin ModelSettings and passes it to the API, but the logprobs returned in the response were discarded during conversion. This change:logprobsfield to ModelResponse dataclasschoice.logprobs.contentin the chat completions model and includes them in the ModelResponseThis enables use cases like RLHF training, confidence scoring, and uncertainty estimation that require access to token-level log probabilities.