openai: fix get_text_response reading wrong role and truncating output#1609
Open
joaquinhuigomez wants to merge 1 commit into0xPlaygrounds:mainfrom
Open
openai: fix get_text_response reading wrong role and truncating output#1609joaquinhuigomez wants to merge 1 commit into0xPlaygrounds:mainfrom
joaquinhuigomez wants to merge 1 commit into0xPlaygrounds:mainfrom
Conversation
ProviderResponseExt::get_text_response() for the OpenAI chat completions provider matched on Message::User on the response message and returned only the first text content item. OpenAI chat completions return the assistant reply as Message::Assistant, so this always returned None for real provider responses, and even if the match were corrected, returning only the first content item would truncate multi-part assistant replies. Match on Message::Assistant and concatenate all Text content items into the returned string. Fixes 0xPlaygrounds#1602
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ProviderResponseExt::get_text_response()for the OpenAI chat completions provider matchedMessage::Useron the response message and returned only the first text content item. OpenAI chat completions return the assistant reply asMessage::Assistant, so this always returnedNonefor real provider responses, and even if the match were corrected, returning only the first item would truncate multi-part assistant replies.This patch matches
Message::Assistantand concatenates allTextcontent items into the returned string.Fixes #1602