Pass is_reasoning_model through QAEvaluator #44640
Merged
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
github-actions
bot
added
the
Evaluation
Contributor
There was a problem hiding this comment.
Pull request overview
This pull request addresses issue #43842 by enabling the QAEvaluator to forward the is_reasoning_model parameter to its LLM-based sub-evaluators. This prevents max_tokens from being sent to reasoning models (o1/o3) which don't support that parameter.
Changes:
- Modified QAEvaluator to extract
is_reasoning_modelfrom kwargs and pass it to all LLM-based sub-evaluators (Groundedness, Relevance, Coherence, Fluency, Similarity) - Added comprehensive unit tests to verify the parameter is correctly propagated to sub-evaluators
- Added an unrelated change to set a default value for
image_tagin AzureOpenAIPythonGrader
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_qa/_qa.py | Extracts is_reasoning_model from kwargs and forwards it to all LLM-based sub-evaluators |
| sdk/evaluation/azure-ai-evaluation/tests/unittests/test_qa_evaluator.py | Adds unit tests verifying is_reasoning_model propagation to sub-evaluators |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_aoai/python_grader.py | Unrelated change: adds default value "2025-05-08" for image_tag parameter |
| sdk/evaluation/azure-ai-evaluation/tests/unittests/test_aoai_python_grader.py | Unrelated change: adds test for image_tag default value |
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_aoai/python_grader.py
Outdated
Show resolved
Hide resolved
sdk/evaluation/azure-ai-evaluation/tests/unittests/test_aoai_python_grader.py
Outdated
Show resolved
Hide resolved
API Change CheckAPIView identified API level changes in this PR and created the following API reviews |
nagkumar91
force-pushed
the
qa-evaluator-reasoning-model-fix
branch
from
8b62a14 to
d3048ce
Compare
w-javed
approved these changes
Jan 20, 2026
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Fixes #43842
is_reasoning_modelto its LLM-based sub-evaluators (Groundedness/Relevance/Coherence/Fluency/Similarity), preventingmax_tokensfrom being sent to reasoning models.Tests:
python -m pytest sdk/evaluation/azure-ai-evaluation/tests/unittests/test_qa_evaluator.py -q