Add support for LeanVec-OOD #16
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
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for LeanVec-OOD (Out-of-Distribution) functionality to the SVS benchmark tool. LeanVec-OOD allows for improved vector quantization by training matrices on query data that may be out-of-distribution relative to the base vectors.
- Introduces a new module
generate_leanvec_matrices.pyfor computing and saving LeanVec transformation matrices - Extends the build functionality to support training query files and pre-computed matrices
- Updates the loader interface to accept optional data and query matrices for LeanVec operations
Reviewed Changes
Copilot reviewed 9 out of 10 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
src/svsbench/generate_leanvec_matrices.py |
New module implementing LeanVec matrix generation and saving functionality |
src/svsbench/build.py |
Extended to support LeanVec-OOD training with query files and matrix parameters |
src/svsbench/loader.py |
Updated loader creation to accept optional data and query matrices |
src/svsbench/merge.py |
Added max_vectors parameter to read_vecs function for limiting vectors read |
src/svsbench/consts.py |
Added default constants for LeanVec dimensions and training vector limits |
tests/test_build.py |
Added comprehensive tests for new LeanVec-OOD functionality |
tests/test_generate_leanvec_matrices.py |
New test file for matrix generation functionality |
pyproject.toml |
Added typer-slim dependency for CLI functionality |
README.md |
Added documentation for building LeanVec-OOD indexes |
aguerreb
reviewed
Jul 25, 2025
Yes. I resolved the Copilot conversations; I don't think changes were necessary. (A previous suggestion did uncover a bug that I fixed.) |
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.
No description provided.