zvec

<p align="right">
  English | <a href="./README_CN.md">中文</a>
</p>

<div align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset="https://zvec.oss-cn-hongkong.aliyuncs.com/logo/github_log_2.svg" />
    <img src="https://zvec.oss-cn-hongkong.aliyuncs.com/logo/github_logo_1.svg" width="400" alt="zvec logo" />
  </picture>
</div>

<p align="center">
  <a href="https://codecov.io/github/alibaba/zvec"><img src="https://codecov.io/github/alibaba/zvec/graph/badge.svg?token=O81CT45B66" alt="Code Coverage"/></a>
  <a href="https://github.com/alibaba/zvec/actions/workflows/01-ci-pipeline.yml"><img src="https://github.com/alibaba/zvec/actions/workflows/01-ci-pipeline.yml/badge.svg?branch=main" alt="Main"/></a>
  <a href="https://github.com/alibaba/zvec/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License"/></a>
  <a href="https://github.com/alibaba/zvec/releases/latest"><img src="https://img.shields.io/github/v/release/alibaba/zvec?label=release" alt="Latest Release"/></a>
</p>

<p align="center">
  <a href="https://trendshift.io/repositories/20830" target="_blank"><img src="https://trendshift.io/api/badge/repositories/20830" alt="alibaba%2Fzvec | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
</p>

<p align="center">
  <a href="https://zvec.org/en/docs/db/quickstart/">🚀 <strong>Quickstart</strong> </a> |
  <a href="https://zvec.org/en/">🏠 <strong>Home</strong> </a> |
  <a href="https://zvec.org/en/docs/db/">📚 <strong>Docs</strong> </a> |
  <a href="https://zvec.org/en/docs/db/benchmarks/">📊 <strong>Benchmarks</strong> </a> |
  <a href="https://deepwiki.com/alibaba/zvec">🔎 <strong>DeepWiki</strong> </a> |
  <a href="https://discord.gg/rKddFBBu9z">🎮 <strong>Discord</strong> </a> |
  <a href="https://x.com/ZvecAI">🐦 <strong>X (Twitter)</strong> </a>
</p>

**Zvec** is an open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Battle-tested within Alibaba Group, it delivers production-grade, low-latency and scalable similarity search with minimal setup.

> [!Important]
> 🚀 **v0.8.0**
>
> - **Broader platform support**: Added **Intel Mac** and **Windows ARM64** builds, wheels, and SDKs; extended **DiskANN to Windows, Android, and iOS**, and **RaBitQ to Windows x86_64**.
> - **Chinese FTS ready to use**: Embedded the default **Jieba dictionary and HMM model**, so Chinese tokenization needs no separate dictionary files or path configuration.
> - **Lower index build costs**: Reduced peak memory during **IVF / DiskANN** builds and merges, and accelerated **HNSW RaBitQ** construction through vector reuse and batched lookups. Build and nested training tasks now enforce configured thread limits more strictly.
> - **Faster distance computation**: Extensively refactored quantizers and distance calculations to benefit multiple
    quantization types and metrics, with major improvements to **INT4 kernel