Add hybrid search (BM25+RRF) and cross-encoder reranking#1
Open
Add hybrid search (BM25+RRF) and cross-encoder reranking#1
Conversation
Extends the search tool with two config-gated improvements: 1. Hybrid search: Runs BM25 (FTS5) alongside vector search and fuses results via Reciprocal Rank Fusion. Enabled with search.hybrid=true. 2. Reranking: Optional cross-encoder pass (sentence-transformers ONNX) that reranks candidates after retrieval. Enabled with reranker.enabled=true. Both default to false — existing deployments are unaffected. No schema changes required. Also adds tools/sync-forks.sh for fork propagation and source_subdir support in pipeline.py. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Surface the review-driven development process and test coverage for hiring managers who won't click into commit history. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
sentence-transformersONNX backend (cross-encoder/ms-marco-MiniLM-L6-v2), lazy-loaded on first usesearch.hybridandreranker.enabled, both defaultfalse) — zero impact on existing deploymentstools/sync-forks.shfor propagating changes to noz-rag/verse-rag, andsource_subdirsupport in pipeline.pyTest plan
hybrid=false(default)hybrid=truein verse-rag config, compare results for 5-10 queriesreranker.enabled=true, verify model downloads and reranking improves relevancetools/sync-forks.shto verify fork propagation workspip install -r requirements.txtto verify sentence-transformers installs on WindowsGenerated by Claude Code · Claude Opus 4.6