fix: trimAndLoadJson failure for llm outputs with <think> tags#2410
Open
abhijitmamarde wants to merge 2 commits intoconfident-ai:mainfrom
Open
fix: trimAndLoadJson failure for llm outputs with <think> tags#2410abhijitmamarde wants to merge 2 commits intoconfident-ai:mainfrom
abhijitmamarde wants to merge 2 commits intoconfident-ai:mainfrom
Conversation
Contributor
|
Skipped: This PR was not opened by one of your configured authors: ( |
|
@abhijitmamarde is attempting to deploy a commit to the Confident AI Team on Vercel. A member of the Team first needs to authorize it. |
Author
|
admins, Any feedback you can give in order to merge this PR? @tanayvaswani @trevor-cai @kritinv could you please have a look? Thanks in advance! |
Author
|
Gentle nudge to core members!!! Thanks! |
Author
|
authors need your action pls! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Some evaluation models (ex: llama-3_3-nemotron-super-49b-v1_5) emit reasoning wrapped in
<think>...</think>tags, which caused JSON parsing to fail. This change strips those blocks before running the existing JSON trimming and parsing logic.