research(nightly): hybrid-sparse-dense — BM25 + dense ANN with RRF and linear fusion#476
Draft
ruvnet wants to merge 1 commit into
Draft
research(nightly): hybrid-sparse-dense — BM25 + dense ANN with RRF and linear fusion#476ruvnet wants to merge 1 commit into
ruvnet wants to merge 1 commit into
Conversation
Introduces hybrid sparse-dense search as ruvector's first dual-channel retrieval engine. Implements BM25 inverted index + dense flat ANN fused via Reciprocal Rank Fusion and linear score interpolation. Research: docs/research/nightly/2026-05-20-hybrid-sparse-dense/ ADR: docs/adr/ADR-194-hybrid-sparse-dense.md
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds nightly RuVector research for
hybrid-sparse-dense— ruvector's first dual-channel retrieval engine combining a BM25 sparse inverted index with dense ANN search, fused via Reciprocal Rank Fusion (RRF) and linear score interpolation.crates/ruvector-hybrid— builds clean, 16 unit tests passing, 5 acceptance tests passingdocs/adr/ADR-194-hybrid-sparse-dense.mddocs/research/nightly/2026-05-20-hybrid-sparse-dense/README.mdcargo run --release -p ruvector-hybrid --bin benchmarkKey Benchmark Numbers (x86_64, rustc 1.94.1, N=5K, D=128, K=10)
Fusion overhead: 33–35µs per query. All 5 acceptance tests: PASS.
Research doc
docs/research/nightly/2026-05-20-hybrid-sparse-dense/README.mdADR
docs/adr/ADR-194-hybrid-sparse-dense.mdBuild / Test
cargo build --release -p ruvector-hybrid cargo test -p ruvector-hybrid cargo run --release -p ruvector-hybrid --bin benchmarkGenerated by Claude Code