Skip to content

vchord vchord_bm25 pg_tokenizer pgvector pgvecto.rs pg_bestmatch

Engineering & Deep Dives Release Notes

English
简体中文

Appearance

Style

Paper (Default) Slate Ink Terminal

Light

Light Dark System

Your browser is not saving settings, so this choice lasts only on this page.

Documentation Unified documentation hub for the PostgreSQL vector search, BM25 ranking, and tokenization extension suite: vchord, vchord_bm25, pg_tokenizer, pgvector, pgvecto.rs, and pg_bestmatch. vchord Scalable, fast, and disk-friendly vector similarity search in PostgreSQL powered by RaBitQ quantization. vchord_bm25 Native Okapi BM25 ranking index and Block-WeakAnd full-text search for PostgreSQL (`vchord_bm25`). pg_tokenizer Complete guide to pg_tokenizer: installation, text analyzers, character/token filters, pretrained and custom models, multilingual tokenization, and SQL reference. pgvector Open-source vector similarity search for PostgreSQL: vector, halfvec, bit, and sparsevec data types, exact and approximate KNN search, HNSW and IVFFlat indexing. pgvecto.rs Complete documentation archive for pgvecto.rs (vectors extension), predecessor to vchord. pg_bestmatch Generate Okapi BM25 sparse vectors inside PostgreSQL and run lexical similarity search over pgvector (sparsevec) or pgvecto.rs (svector).

Vchord: Scalable Vector Search for PostgreSQL
- Documentation
  About
  
  License
  
  Attribution
  
  Trademark
  
  vchord
  
  Getting Started
  
  Overview
  
  Installation
  
  Vchord Suite
  
  Usage
  
  Indexing
  
  Multi-Vector Retrieval
  
  Graph Index
  
  Quantization Types
  
  Similarity Filter
  
  PostgreSQL Tuning
  
  Monitoring
  
  Fallback Parameters
  
  Measure Recall
  
  Prewarm
  
  Prefilter
  
  Prefetch
  
  Rerank in Table
  
  Partitioning Tuning
  
  External Build
  
  Use Cases
  
  Hybrid Search
  
  ColBERT Rerank
  
  ColQwen2 & Modal
  
  Benchmarks
  
  Price
  
  Performance
  
  Benchmarks with pgvector
  
  Benchmarks with Elasticsearch
  
  Benchmarks with pgvectorscale
  
  Administration
  
  Migration
  
  Scalability
  
  Kubernetes
  
  Customer Stories
  
  Earth Genome
  
  vchord_bm25
  
  Getting Started
  
  Overview
  
  Installation
  
  Quick Start
  
  Usage & Hybrid Search
  
  Indexing & Maintenance
  
  Querying & Scoring
  
  Filtered Search & Prefiltering
  
  Hybrid Search (BM25 + VectorChord)
  
  BM25 & Block-WeakAnd Internals
  
  Reference & Benchmarks
  
  SQL Reference
  
  GUC & Index Parameters
  
  Benchmarks
  
  Migrating to 0.4.0
  
  Release History & API Evolution
  
  pg_tokenizer
  
  Installation
  
  Tokenizer Architecture & Usage
  
  Text Analyzers & Filters
  
  Tokenization Models
  
  Multilingual Recipes & Limitations
  
  SQL & TOML Reference
  
  pgvector
  
  Getting Started
  
  Querying & Filtering
  
  HNSW & IVFFlat Indexing
  
  Quantization & Sparse Vectors
  
  Reference, Tuning & FAQ
  
  pgvecto.rs
  
  Getting Started
  
  Overview
  
  Installation
  
  Usage
  
  Indexing
  
  Search
  
  Monitoring
  
  Quantization
  
  Compatibility
  
  Use Cases
  
  Hybrid Search
  
  Adaptive Retrieval
  
  Image Search
  
  Multi Tenancy
  
  Sparse Vector
  
  Generative Question-Answering
  
  Integration
  
  LangChain
  
  LlamaIndex
  
  Citus
  
  Administration
  
  Configuration
  
  Upgrading
  
  Logical Replication
  
  Foreign Data Wrapper (FDW)
  
  Kubernetes
  
  Migration
  
  FAQs
  
  General FAQ
  
  pgvecto.rs vs. pgvector
  
  pgvecto.rs vs. Specialized VectorDB
  
  Benchmarks
  
  Reference
  
  Schema
  
  Indexing Options
  
  Search Options
  
  Vector Types
  
  Half-Precision Vector
  
  8-Bit Integer Vector
  
  Sparse Vector
  
  Binary Vector
  
  Community
  
  Contributing to pgvecto.rs
  
  Roadmap
  
  Adopters
  
  Developers
  
  Development Tutorial
  
  pg_bestmatch
  
  Getting Started
  
  Usage Guide
  
  SQL Reference
- Blog
  Engineering
  
  Scaling Vector Search to 1 Billion on PostgreSQL
  
  How We Made 100M Vector Indexing in 20 Minutes Possible on PostgreSQL
  
  Bringing Search‑Engine Ranking to PostgreSQL with VectorChord‑BM25
  
  Optimize RAG with Contextual Retrieval in PostgreSQL
  
  VectorChord: Cost-Efficient Upload & Search of 400 Million Vectors on AWS
  
  All-in-one VectorChord Suite: Building Production-Ready RAG Solutions Directly in PostgreSQL
  
  Introducing Vechord: Turn PostgreSQL into your search engine in a Pythonic way.
  
  Beyond Text: Unlock OCR-Free RAG in PostgreSQL with Modal & VectorChord
  
  3 Billion Vectors in PostgreSQL to Protect the Earth
  
  Vector Search Over PostgreSQL: A Comparative Analysis of Memory and Disk Solutions
  
  PostgreSQL Full-Text Search: Fast When Done Right (Debunking the Slow Myth)
  
  VectorChord-BM25: Introducing pg_tokenizer—A Standalone, Multilingual Tokenizer for Advanced Search
  
  Hybrid search with Postgres Native BM25 and VectorChord
  
  Vector Search at 10,000 QPS in PostgreSQL with VectorChord
  
  VectorChord-BM25: Revolutionize PostgreSQL Search with BM25 Ranking — 3x Faster Than ElasticSearch
  
  Do we really need a specialized vector database? (2023)
  
  Supercharge vector search with ColBERT rerank in PostgreSQL
  
  ARM + VectorChord: Affordable, Fast Vector Search
  
  Why HNSW is Not the Answer
  
  Benefits and Steps of External Centroids Building in VectorChord
  
  VectorChord: Store 400k Vectors for $1 in PostgreSQL
  
  Introducing PGVecto.rs Cloud - Scalable Vector Search in PostgreSQL, Now in the Cloud
  
  Introducing Terraform Support for PGVecto.rs Cloud
  
  Unleash the power of sparse vector
  
  pg_bestmatch.rs: Elevate Your PostgreSQL Text Queries with BM25
  
  My binary vector search is better than your FP32 vectors
  
  pgvector vs. pgvecto.rs in 2024: A Comprehensive Comparison for Vector Search in PostgreSQL
  
  Building LLM Applications in LangChain using pgvecto.rs
  
  Building the RAG pipeline with LlamaIndex and pgvecto.rs
  
  Do we really need a specialized vector database?
  
  Release Notes
  
  VectorChord 1.1: Native 4/8 Bit Vector Types and Per-Index Query Defaults
  
  VectorChord 1.0: Developer-First Vector Search on Postgres, 100x Faster Indexing than pgvector
  
  VectorChord 0.5: New RaBitQ-empowered DiskANN Index and Continuous Recall Measurement
  
  VectorChord 0.4: Faster PostgreSQL Vector Search with Advanced I/O and Prefiltering
  
  VectorChord 0.3: Bringing Efficient Multi-Vector Contextual Late Interaction in PostgreSQL
  
  VectorChord 0.2: 60K-Dimensional Vectors, 50% Faster Indexing with ARM
  
  pgvecto.rs 0.2: Unifying Relational Queries and Vector Search in PostgreSQL

Authors

6

Jinjing Zhou 11 pages
Junyu Chen 10 pages
Ce Gao 9 pages
xieydd 6 pages
Keming 5 pages
Zoie Wang 1 page

Authors 6
Tags 14

vectorchord18 postgresql13 release7 vectorsearch5 vector-database4 ai3 bm251 colbert1 contextual-retrieval1 multivector1 ocr1 pgvector1 rag1 sparsevectors1

Vector & BM25 Search for PostgreSQL

Scalable, fast, and disk-friendly retrieval extensions for PostgreSQL.
Originally developed by TensorChord, now maintained by PGSTY.

Documentation

Overview & Quick Start
Installation
Indexing Guide
Multi-Vector & Hybrid
Benchmarks
Migration Guide

Extension Suite

vchord
vchord_bm25
pg_tokenizer
pgvector
pgvecto.rs
pg_bestmatch

Project & Blog

Engineering Blog
Release Notes
About & License
Attribution
GitHub
Create Issue

Ecosystem

Pigsty
PIG CLI
PGEXT.CLOUD
PGSQL.CC
PG Docs
PG Center

© 2023–2026 TensorChord & PGSTY · CC BY 4.0 All Rights Reserved

Powered by Oink

English
简体中文

Appearance

Style

Paper (Default) Slate Ink Terminal

Light

Light Dark System

Your browser is not saving settings, so this choice lasts only on this page.

Keyboard shortcuts

Section navigation

WS↑↓: Move through sidebar
AD←→: Collapse or expand section
EnterG: Open focused page
JK: Previous or next heading
QE: Previous or next page

Actions

/F: Search
\C: Command palette
H: Reading mode
LY: Switch language
T: Switch theme
R: Cycle top-level pages

Search in

All sections Authors

↑↓ Navigate ↵ Open esc Close