# Usage & Hybrid Search

> Index management, Top-K querying, prefiltering, hybrid search with vchord, and Block-WeakAnd internals.

---

LLMS index: [llms.txt](/llms.txt)

---

Learn how to build, tune, and query `vchord_bm25` indexes in production:


  - [Indexing \& Maintenance](/bm25/usage/indexing/) — Create bm25 indexes, tune segment sizes and BM25 parameters (k1, b), monitor parallel builds, and inspect pages.
  - [Querying \& Scoring](/bm25/usage/querying/) — Run Top-K Block-WeakAnd queries, understand negative BM25 scores, and tune bm25_limit.
  - [Filtered Search \& Prefiltering](/bm25/usage/filtering/) — Combine WHERE predicates with BM25 ranking using post-filtering, pre-filtering, and partial indexes.
  - [Hybrid Search \(BM25 \+ VectorChord\)](/bm25/usage/hybrid-search/) — Fuse sparse BM25 lexical search with VectorChord dense vector search via Reciprocal Rank Fusion (RRF) and ColBERT.
  - [BM25 \& Block\-WeakAnd Internals](/bm25/usage/algorithms/) — Deep dive into the Okapi BM25 formula, 1-byte fieldnorm quantization, delta-bitpacking, and Block-Max WAND.

---

Section pages:

- [Indexing & Maintenance](/bm25/usage/indexing/): Create, configure, maintain, and inspect bm25 indexes in PostgreSQL.
- [Querying & Scoring](/bm25/usage/querying/): Execute Top-K BM25 queries, interpret negative BM25 scores, and tune search limits.
- [Filtered Search & Prefiltering](/bm25/usage/filtering/): Combine SQL WHERE clauses with BM25 Top-K ranking using post-filtering, pre-filtering, and partial indexes.
- [Hybrid Search (BM25 + VectorChord)](/bm25/usage/hybrid-search/): Combine sparse lexical BM25 search (vchord_bm25) and dense vector search (vchord) with Reciprocal Rank Fusion (RRF) and ColBERT reranking.
- [BM25 & Block-WeakAnd Internals](/bm25/usage/algorithms/): Mathematical formulation and index architecture of Okapi BM25, 1-byte fieldnorm quantization, delta-bitpacking, and Block-WeakAnd in vchord_bm25.