Skip to content

vchord Documentation

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

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.

Overview, installation packages, Docker images, and the Vchord retrieval suite.

Indexing with vchordrq and vchordg, MaxSim multi-vector retrieval, quantization types, range queries, and tuning.

End-to-end recipes for hybrid BM25 + dense search, ColBERT reranking, and multimodal OCR-free RAG.

Price, throughput, latency, and recall benchmarks against pgvector, pgvectorscale, and Elasticsearch.

Migrating from pgvecto.rs or pgvector, horizontal read scalability, and Kubernetes deployment.

Real-world production deployments of VectorChord at multi-billion vector scale.