03 classification api test #304
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
✅ Deploy Preview for vllm-semantic-router ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Add e2e test for standalone Classification API service that validates the /api/v1/classify/intent endpoint correctly classifies different types of queries. Test validates: - Math queries are classified as 'math' - Computer science queries are classified as 'computer science' - Business queries are classified as 'business' - History queries are classified as 'history' - Batch classification endpoint processes multiple texts correctly The Classification API (port 8080) is a standalone service separate from the ExtProc router, providing direct classification capabilities for applications that need text classification without LLM routing. Test requirements: - Classification API must be running on port 8080 - Start with: make run-router-e2e Signed-off-by: Yossi Ovadia <[email protected]>
Add 03-classification-api-test.py to the test suite documentation: - Add to test flow list as test vllm-project#4 - Update numbering for remaining tests - Add to Available Tests section with usage example Signed-off-by: Yossi Ovadia <[email protected]>
- Apply black formatter: remove unnecessary parentheses - Fix end of file: remove extra blank line Signed-off-by: Yossi Ovadia <[email protected]>
yossiovadia
force-pushed
the
03-classification-api-test
branch
from
9b73db7 to
f01b771
Compare
👥 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 1, 2025
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* test: add Classification API intent classification test Add e2e test for standalone Classification API service that validates the /api/v1/classify/intent endpoint correctly classifies different types of queries. Test validates: - Math queries are classified as 'math' - Computer science queries are classified as 'computer science' - Business queries are classified as 'business' - History queries are classified as 'history' - Batch classification endpoint processes multiple texts correctly The Classification API (port 8080) is a standalone service separate from the ExtProc router, providing direct classification capabilities for applications that need text classification without LLM routing. Test requirements: - Classification API must be running on port 8080 - Start with: make run-router-e2e Signed-off-by: Yossi Ovadia <[email protected]> * docs: update README with 03-classification-api-test Add 03-classification-api-test.py to the test suite documentation: - Add to test flow list as test vllm-project#4 - Update numbering for remaining tests - Add to Available Tests section with usage example Signed-off-by: Yossi Ovadia <[email protected]> * style: apply pre-commit fixes to 03-classification-api-test.py - Apply black formatter: remove unnecessary parentheses - Fix end of file: remove extra blank line Signed-off-by: Yossi Ovadia <[email protected]> --------- Signed-off-by: Yossi Ovadia <[email protected]> Signed-off-by: liuhy <[email protected]>
Aias00
pushed a commit
to Aias00/semantic-router
that referenced
this pull request
Oct 4, 2025
* test: add Classification API intent classification test Add e2e test for standalone Classification API service that validates the /api/v1/classify/intent endpoint correctly classifies different types of queries. Test validates: - Math queries are classified as 'math' - Computer science queries are classified as 'computer science' - Business queries are classified as 'business' - History queries are classified as 'history' - Batch classification endpoint processes multiple texts correctly The Classification API (port 8080) is a standalone service separate from the ExtProc router, providing direct classification capabilities for applications that need text classification without LLM routing. Test requirements: - Classification API must be running on port 8080 - Start with: make run-router-e2e Signed-off-by: Yossi Ovadia <[email protected]> * docs: update README with 03-classification-api-test Add 03-classification-api-test.py to the test suite documentation: - Add to test flow list as test vllm-project#4 - Update numbering for remaining tests - Add to Available Tests section with usage example Signed-off-by: Yossi Ovadia <[email protected]> * style: apply pre-commit fixes to 03-classification-api-test.py - Apply black formatter: remove unnecessary parentheses - Fix end of file: remove extra blank line Signed-off-by: Yossi Ovadia <[email protected]> --------- Signed-off-by: Yossi Ovadia <[email protected]> Signed-off-by: liuhy <[email protected]>
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.
The 03-classification-api-test validates the standalone Classification API service
Key Differences between this test and the 02-classificatoin test:
Architecture: ExtProc is integrated with Envoy for transparent routing; Classification API is a standalone HTTP service
Use Case: ExtProc is for LLM routing; Classification API is for direct text categorization
Response: ExtProc returns LLM completions; Classification API returns category labels
Integration: ExtProc uses classifier directly; Classification API uses service wrapper layer
NOTE: this test exposes a bug in the server.go functionality. related to #303
Release Notes: Yes/No