Fix/improve batch classification test #319
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
Previously, the batch classification test only validated HTTP status and result count, but never checked if the classifications were correct. The expected_categories variable was created but never used for validation. Changes: - Extract actual categories from batch classification results - Compare against expected categories and calculate accuracy percentage - Add detailed output showing each classification result - Assert that accuracy meets 75% threshold - Maintain backward compatibility with existing HTTP/count checks This improved test now properly catches classification accuracy issues and will fail when the classification system returns incorrect results, exposing problems that were previously hidden. Related to issue vllm-project#318: Batch Classification API Returns Incorrect Categories Signed-off-by: Yossi Ovadia <yovadia@redhat.com>
Automatic formatting applied by black pre-commit hook. Signed-off-by: Yossi Ovadia <yovadia@redhat.com>
✅ Deploy Preview for vllm-semantic-router ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
👥 vLLM Semantic Team NotificationThe following members have been identified for the changed files in this PR and have been automatically assigned: 📁
|
rootfs
approved these changes
Oct 2, 2025
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* feat: improve batch classification test to validate accuracy Previously, the batch classification test only validated HTTP status and result count, but never checked if the classifications were correct. The expected_categories variable was created but never used for validation. Changes: - Extract actual categories from batch classification results - Compare against expected categories and calculate accuracy percentage - Add detailed output showing each classification result - Assert that accuracy meets 75% threshold - Maintain backward compatibility with existing HTTP/count checks This improved test now properly catches classification accuracy issues and will fail when the classification system returns incorrect results, exposing problems that were previously hidden. Related to issue vllm-project#318: Batch Classification API Returns Incorrect Categories Signed-off-by: Yossi Ovadia <yovadia@redhat.com> * style: apply black formatting to classification test Automatic formatting applied by black pre-commit hook. Signed-off-by: Yossi Ovadia <yovadia@redhat.com> --------- Signed-off-by: Yossi Ovadia <yovadia@redhat.com> Signed-off-by: liuhy <liuhongyu@apache.org>
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* feat: improve batch classification test to validate accuracy Previously, the batch classification test only validated HTTP status and result count, but never checked if the classifications were correct. The expected_categories variable was created but never used for validation. Changes: - Extract actual categories from batch classification results - Compare against expected categories and calculate accuracy percentage - Add detailed output showing each classification result - Assert that accuracy meets 75% threshold - Maintain backward compatibility with existing HTTP/count checks This improved test now properly catches classification accuracy issues and will fail when the classification system returns incorrect results, exposing problems that were previously hidden. Related to issue vllm-project#318: Batch Classification API Returns Incorrect Categories Signed-off-by: Yossi Ovadia <yovadia@redhat.com> * style: apply black formatting to classification test Automatic formatting applied by black pre-commit hook. Signed-off-by: Yossi Ovadia <yovadia@redhat.com> --------- Signed-off-by: Yossi Ovadia <yovadia@redhat.com> Signed-off-by: liuhy <liuhongyu@apache.org>
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* feat: improve batch classification test to validate accuracy Previously, the batch classification test only validated HTTP status and result count, but never checked if the classifications were correct. The expected_categories variable was created but never used for validation. Changes: - Extract actual categories from batch classification results - Compare against expected categories and calculate accuracy percentage - Add detailed output showing each classification result - Assert that accuracy meets 75% threshold - Maintain backward compatibility with existing HTTP/count checks This improved test now properly catches classification accuracy issues and will fail when the classification system returns incorrect results, exposing problems that were previously hidden. Related to issue vllm-project#318: Batch Classification API Returns Incorrect Categories Signed-off-by: Yossi Ovadia <yovadia@redhat.com> * style: apply black formatting to classification test Automatic formatting applied by black pre-commit hook. Signed-off-by: Yossi Ovadia <yovadia@redhat.com> --------- Signed-off-by: Yossi Ovadia <yovadia@redhat.com> Signed-off-by: liuhy <liuhongyu@apache.org>
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* feat: improve batch classification test to validate accuracy Previously, the batch classification test only validated HTTP status and result count, but never checked if the classifications were correct. The expected_categories variable was created but never used for validation. Changes: - Extract actual categories from batch classification results - Compare against expected categories and calculate accuracy percentage - Add detailed output showing each classification result - Assert that accuracy meets 75% threshold - Maintain backward compatibility with existing HTTP/count checks This improved test now properly catches classification accuracy issues and will fail when the classification system returns incorrect results, exposing problems that were previously hidden. Related to issue vllm-project#318: Batch Classification API Returns Incorrect Categories Signed-off-by: Yossi Ovadia <yovadia@redhat.com> * style: apply black formatting to classification test Automatic formatting applied by black pre-commit hook. Signed-off-by: Yossi Ovadia <yovadia@redhat.com> --------- Signed-off-by: Yossi Ovadia <yovadia@redhat.com> Signed-off-by: liuhy <liuhongyu@apache.org>
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.
Problem Fixed:
The original test_batch_classification method had a critical flaw - it only validated HTTP status (200) and result count, but never checked if the classifications were actually correct. The
expected_categories variable was created but never used for validation.
What We Added:
- Extract actual categories from each classification result
- Compare against expected categories: ["math", "computer science", "business", "history"]
- Calculate accuracy percentage and assert ≥75% threshold