feat(retrievers): Add BM25Plus variant support to BM25Retriever #488
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
1 task
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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
This PR adds optional support for the BM25Plus variant to
BM25Retriever.The default behavior remains unchanged and continues to use BM25Okapi
BM25Plus can be enabled explicitly via a new
bm25_variant="plus"optionAll scoring logic and parameter defaults are delegated to the underlying
rank_bm25implementationNo new retriever classes are introduced, and the change is fully backward compatible
BM25Plus is particularly useful for passage-level retrieval and chunked documents, where standard BM25 can under-rank short texts.
Issue
N/A
Dependencies
No new dependencies added
Continues to rely on the existing
rank_bm25packageLint and test
✅ make format
✅ make lint
✅ make test
All checks pass locally.