Fix timeout and output parsing issues for local models #2045
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
This commit addresses issue #2044 by: 1. Adding a new is_local_model flag to RunConfig with increased timeout for local models 2. Improving the JSON extraction logic in extract_json to handle common issues with local model outputs 3. Enhancing the RagasOutputParser to be more robust with malformed JSON 4. Adding tests to verify the fixes
dosubot
bot
added
the
size:L
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Outdated suggestions cannot be applied.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 addresses issue #2044 by improving the handling of local models in Ragas.
Changes
is_local_modelflag toRunConfigwith increased timeout (10 minutes) for local modelsextract_jsonto handle common issues with local model outputs:RagasOutputParserto be more robust with malformed JSONThese changes should help users who are using local models like Ollama to get better results with metrics like
context_recall,faithfulness, andcontext_precisionby reducing timeouts and improving output parsing.Fixes #2044
@jjmachan can click here to continue refining the PR