# VectorChord

> Self-hosted PostgreSQL extension for scalable vector search using RaBitQ quantization, compatible with pgvector syntax, enabling 100M+ vectors on modest hardware.

- **Category:** Vector Database
- **Licence:** Other
- **Latest version:** 1.1.1
- **Open source:** open_core
- **Languages:** Rust, PLpgSQL
- **Platforms:** Docker
- **Tags:** PostgreSQL, LLMOps, LLM, Rag, Vector Search, Docker, Vector Database, Quantization, Artificial intelligence, Rabittq, Pgvector Compatible, Pg Extension

## Description

VectorChord is a PostgreSQL extension built for scalable, high-performance vector search at billion-scale. It uses RaBitQ compression — offering native 4-bit and 8-bit vector types — to drastically cut storage costs while keeping recall loss under 1%. The extension works with the same data types and syntax as pgvector, so existing applications can migrate without code changes. Indexing 100 million vectors takes roughly 20 minutes thanks to hierarchical K-means and optimized disk I/O, and the system can scale to 1 billion vectors on machines with 128 GB of RAM. It ships as Docker images: a base Postgres image with the extension (ghcr.io/tensorchord/vchord-postgres) and an all-in-one suite image that also bundles VectorChord-bm25 and pg_tokenizer.rs. The project is dual-licensed under AGPLv3 and Elastic License v2.

## Links

- [Homepage](https://github.com/supervc-stack/vectorchord)
- [Website](https://docs.vectorchord.ai/vectorchord/getting-started/overview.html)
- [Docker](ghcr.io/tensorchord/vchord-postgres)
- [Documentation](https://docs.vectorchord.ai/vectorchord/)
- [Discord Community](https://discord.gg/KqswhpVgdU)
- [Twitter / X](https://x.com/TensorChord)
- [Blog](https://blog.vectorchord.ai/)

---
Source: https://selfhost.directory/project/vectorchord