Bugfix/aoai row mismatch #42466
Open
Bugfix/aoai row mismatch #42466
+183
−39
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
Add pyrit and not remove the other one
…row misalignment; add missing-rows unit test
github-actions
bot
added
the
Evaluation
There was a problem hiding this comment.
Pull Request Overview
This pull request fixes a critical bug in the Azure AI evaluation system where evaluation results were not properly aligned with input data, leading to incorrect metrics being reported. The issue occurred because AOAI (Azure OpenAI) evaluation runs could return results in a different order than the original dataset or drop some rows entirely.
Key changes:
- Added row alignment validation by tracking expected row count
- Enhanced result processing to handle missing rows with proper padding
- Updated test cases to validate ordering preservation and missing row handling
Reviewed Changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
test_aoai_evaluation_pagination.py |
Updated test cases to include expected_rows parameter and fixed test data to properly validate row ordering |
test_aoai_alignment_missing_rows.py |
New test file to validate proper handling of unordered AOAI results and missing row detection |
_evaluate_aoai.py |
Core fix implementing row alignment validation, missing row padding, and proper result ordering |
CHANGELOG.md |
Documentation of the bug fix |
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_evaluate_aoai.py
Outdated
Show resolved
Hide resolved
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_evaluate_aoai.py
Outdated
Show resolved
Hide resolved
…te/_evaluate_aoai.py Co-authored-by: Copilot <[email protected]>
…te/_evaluate_aoai.py Co-authored-by: Copilot <[email protected]>
singankit
reviewed
Aug 13, 2025
| if expected is not None: | ||
| pre_len = len(output_df) | ||
| # Assumes original datasource_item_id space is 0..expected-1 | ||
| output_df = output_df.reindex(range(expected)) |
There was a problem hiding this comment.
How do we know for which row we did not get result ?
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.
Description
Please add an informative description that covers that changes made by the pull request and link all relevant issues.
If an SDK is being regenerated based on a new API spec, a link to the pull request containing these API spec changes should be included above.
All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines