-
Notifications
You must be signed in to change notification settings - Fork 236
Tokenize endpoint for rerank calculator #3876
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull request overview
This PR adds a tokenize endpoint for rerank models and updates documentation to reference models from the OpenVINO organization instead of other sources.
Changes:
- Adds tokenize endpoint support to the rerank calculator with configurable padding and truncation parameters
- Removes old demo configuration files (graph.pbtxt and config.json) from the rerank demo
- Updates documentation to reference OpenVINO organization models
Reviewed changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| src/test/reranknode_test.cpp | Adds comprehensive test coverage for the new tokenize endpoint including positive and negative test cases |
| src/rerank/rerank_calculator_ov.cc | Implements tokenize endpoint logic in the rerank calculator |
| src/rerank/BUILD | Adds dependency on tokenize_parser library |
| demos/rerank/models/graph.pbtxt | Removes old graph configuration file |
| demos/rerank/config.json | Removes old config file |
| demos/rerank/compare_results.py | Updates default model name in help text to match actual default value |
| demos/rerank/README.md | Updates model references to OpenVINO organization and adds tokenize endpoint documentation |
| demos/embeddings/README.md | Removes release version information from tokenize endpoint header |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
🛠 Summary
CVS-178256
Tokenize endpoint for rerank models. Changes in README to change models to models from OV organization.
Docs: https://openvino-doc.iotg.sclab.intel.com/rerank_tokenize/model-server/ovms_demos_rerank.html
🧪 Checklist
``