# VectorChord

> Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

- **URL**: https://www.freshcrate.ai/projects/VectorChord
- **Author**: tensorchord
- **Category**: Databases
- **Latest version**: `1.1.1` (2026-02-28)
- **License**: NOASSERTION
- **Source**: https://github.com/tensorchord/VectorChord
- **Homepage**: https://docs.vectorchord.ai/vectorchord/getting-started/overview.html
- **Language**: Rust
- **GitHub**: 1,646 stars, 57 forks
- **Registry**: github
- **Tags**: `artificial-intelligence`, `llmops`, `postgresql`, `rust`, `vector-database`, `vector-search`

## Description

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `1.1.1` | 2026-02-28 | Low | **VectorChord 1.1.1 Release Notes**  ## Features  Added 4 new functions:  * `dequantize_to_vector(rabitq8)` * `dequantize_to_halfvec(rabitq8)` * `dequantize_to_vector(rabitq4)` * `dequantize_to_halfvec(rabitq4)`  These functions convert quantized vectors back into floating-point vectors.  See [Quantization Types](https://docs.vectorchord.ai/vectorchord/usage/quantization-types.html) for docs.  ## What's Changed  Replaced the quantization algorithm used by:  * `quantize_to_rabi |
| `1.1.0` | 2026-02-11 | Low | **VectorChord 1.1.0 Release Notes**  ## Features  VectorChord now provides `rabitq8` and `rabitq4` types. They are RaBitQ-quantized vectors, internally stored as `uint8[]` or `uint4[]` instead of `float32[]` or `float16[]`, costing less storage. Like other vector types, you can create indexes for them.  ```sql CREATE TABLE items (id bigserial PRIMARY KEY, embedding rabitq8(3)); CREATE INDEX ON items USING vchordrq (embedding rabitq8_l2_ops); INSERT INTO items (embedding) VALUES (quantiz |
| `1.0.0` | 2025-11-12 | Low | # VectorChord 1.0 Release Notes  VectorChord 1.0 is here. This release delivers much faster PostgreSQL index builds with IVF + RaBitQ, quicker updates, broader architecture support, and a stack of new features since our first release. It’s a major milestone—production-ready and thoroughly tested.  ## Highlights  We have dramatically optimized index build speed, now capable of building a 100M-vector dataset in 20 minutes on a 16-vCPU machine while sharply cutting memory usage, making index |
| `0.5.3` | 2025-09-26 | Low | **VectorChord 0.5.3 Release Notes**  * Fix `build.pin` if parallel build is not enabled. https://github.com/tensorchord/VectorChord/pull/346 * Run tests on x86_64 MacOS. https://github.com/tensorchord/VectorChord/pull/348 * Build prebuilt packages for PostgreSQL 18. https://github.com/tensorchord/VectorChord/pull/349 |
| `0.5.2` | 2025-09-15 | Low | **VectorChord 0.5.2 Release Notes**  * Add built-in query simpling, for recall evaluation with online queries, see also [Query sampling](https://docs.vectorchord.ai/vectorchord/usage/measure-recall.html#query-sampling). (https://github.com/tensorchord/VectorChord/pull/321, https://github.com/tensorchord/VectorChord/pull/334, https://github.com/tensorchord/VectorChord/pull/337, https://github.com/tensorchord/VectorChord/pull/338) * Fix MVCC violation if either `build.rerank_in_table` or `vchor |
| `0.5.1` | 2025-09-02 | Low | **VectorChord 0.5.1 Release Notes**  * A little performance improvement. (#314) * Fix compilation on x86_64 nix with `gcc.arch` set. (#316) * Fix compilation and tests, and add initial simd support, on s390x and powerpc64le, see also [s390x](https://docs.vectorchord.ai/vectorchord/getting-started/installation.html#s390x). (#318, #323, #324, #326, #325, #327, #328, #329, #330)  **Full Changelog**: https://github.com/tensorchord/VectorChord/compare/0.5.0...0.5.1 |
| `0.5.0` | 2025-08-15 | Low | # VectorChord v0.5.0  Two big upgrades, focused and pragmatic.  ## 1) Experimental DiskANN (with RaBitQ) — `vchordg` *(preview)* A new **disk-backed graph index** that keeps memory low while giving you a DiskANN-style option inside VectorChord.  - **When it shines:** can be **faster** than IVF+RaBitQ (`vchordrq`) on some embeddings (e.g., OpenAI/Cohere) — **but not always**. - **Caveats:** **slow build**, and **insert/delete are weaker** than IVF. Dataset-dependent: benchmark before swit |
| `0.4.3` | 2025-06-20 | Low | **VectorChord 0.4.3 Release Notes**  * use mimalloc on aarch64-linux * fix compilation with gcc on x86_64 * fix compilation with clang on Windows * prompt the user to rebuild the index after the upgrade  **Full Changelog**: https://github.com/tensorchord/VectorChord/compare/0.4.2...0.4.3 |
| `0.4.2` | 2025-05-29 | Low | **VectorChord 0.4.2 Release Notes**  * fix compilation on aarch64 macos * add support for `pgxnclient`: you can install VectorChord with `pgxnclient install vchord==0.4.2` now  **Full Changelog**: https://github.com/tensorchord/VectorChord/compare/0.4.1...0.4.2 |
| `0.4.1` | 2025-05-24 | Low | **VectorChord 0.4.1 Release Notes**  * Fix potential precision issue if the dimension of vectors is `1`, `2`, `4`, `8`, `16`, `32`, `64`, `128`, `256`, `512`, `1024`, `2048`, `4096`, `8192`, `16384`, `32768`.  **Full Changelog**: https://github.com/tensorchord/VectorChord/compare/0.4.0...0.4.1 |

## Dependency audit

- **Score**: 90/100
- **Total deps**: 7
- **Resolved**: 7
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 5
- **Scanned**: 2026-05-11

## Citation

- HTML: https://www.freshcrate.ai/projects/VectorChord
- Markdown: https://www.freshcrate.ai/projects/VectorChord.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/VectorChord/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._