# vchord Documentation

> Scalable, fast, and disk-friendly vector similarity search in PostgreSQL powered by RaBitQ quantization.

---

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

---

Welcome to the **`vchord`** documentation. Select a topic below to get started with installation, indexing (`vchordrq` and `vchordg`), multi-vector retrieval, hybrid search, benchmarks, and production operations.

---

Section pages:

- [Getting Started](/docs/getting-started/): Overview, installation packages, Docker images, and the Vchord retrieval suite.
- [Usage](/docs/usage/): Indexing with vchordrq and vchordg, MaxSim multi-vector retrieval, quantization types, range queries, and tuning.
- [Use Cases](/docs/use-case/): End-to-end recipes for hybrid BM25 + dense search, ColBERT reranking, and multimodal OCR-free RAG.
- [Benchmarks](/docs/benchmark/): Price, throughput, latency, and recall benchmarks against pgvector, pgvectorscale, and Elasticsearch.
- [Administration](/docs/admin/): Migrating from pgvecto.rs or pgvector, horizontal read scalability, and Kubernetes deployment.
- [Customer Stories](/docs/customer-stories/): Real-world production deployments of VectorChord at multi-billion vector scale.

---

Backlinks:

- [Page Not Found](/404/)
- [About](/about/)
- [VectorChord 0.4: Faster PostgreSQL Vector Search with Advanced I/O and Prefiltering](/blog/release/vectorchord-04-faster-postgresql-vector-search-with-advanced-io-and-prefiltering/)
- [BM25](/bm25/)
- [Hybrid Search (BM25 + VectorChord)](/bm25/usage/hybrid-search/)
- [pgvecto.rs](/pgvecto-rs/)