alibaba

alibaba/zvec

A lightweight, lightning-fast, in-process vector database

View on GitHub Website / Demo Back to listing

16.2kstars 1kforks 40contributors C++

README.md

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

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

**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 kernels** and **Linux ARM64** performance.
> - **Faster search**: Added faster **Uniform quantizers** and optimized **Vamana** graph layout and prefetching. Uniform quantization avoids per-point score reconstruction, though a shared min/max range can increase quantization error and reduce recall.
> - **Bug fixes and improvements**: Added more flexible **UTF-8 document IDs** up to 1,024 bytes; fixed concurrent reads during segment switches, index rebuilding with deleted rows, and correctness issues in **LIKE** and floating-point range filters.
>
> 👉 [Read the Release Notes](https://github.com/alibaba/zvec/releases/tag/v0.8.0)

[^query-performance]: Measured on GIST 1M with L2 distance, INT8 quantization, and HNSW on a 16-core Linux ARM64 system.

## 💫 Features

- **Blazing Fast**: Searches billions of vectors in milliseconds.
- **Simple, Just Works**: [Install](#-installation) and start searching in seconds. Pure local, no servers, no config, no fuss.
- **Dense + Sparse Vectors**: Support dense and sparse embeddings, multi-vector queries, and a rich selection of [vector index types](https://zvec.org/en/docs/db/concepts/vector-index/#vector-index-types) that scale from memory to disk.
- **Full-Text Search (FTS)**: Native keyword-based full-text search — query string fields with natural-language or structured expressions.
- **Hybrid Search**: Fuse vector similarity, full-text search, and structured filters in a single query for precise results.
- **Durable Storage**: Write-ahead logging (WAL) guarantees persistence — data is never lost, even on process crash or power failure.
- **Concurrent Access**: Multiple processes can read the same collection simultaneously; writes are single-process exclusive.
- **Runs Anywhere**: As an in-process library, Zvec runs wherever your code runs — notebooks, servers, CLI tools, or even edge devices.

## 📦 Installation

Zvec offers official SDKs across multiple languages:

| SDK | Install / Dependency | Source |
| --- | --- | --- |
| [Python](https://pypi.org/project/zvec/) | `pip install zvec` | [Source](https://github.com/alibaba/zvec/tree/main/python/zvec) |
| [Node.js](https://www.npmjs.com/package/@zvec/zvec) | `npm install @zvec/zvec` | [Source](https://github.com/zvec-ai/zvec-node) |
| [Go](https://pkg.go.dev/github.com/zvec-ai/zvec-go) | [Installation guide](https://github.com/zvec-ai/zvec-go#installation) | [Source](https://github.com/zvec-ai/zvec-go) |
| [Rust](https://crates.io/crates/zvec-rust) | `cargo add zvec-rust` | [Source](https://github.com/zvec-ai/zvec-rust) |
| [Java](https://central.sonatype.com/artifact/org.zvec/zvec-java) | `org.zvec:zvec-java` (Maven) | [Source](https://github.com/zvec-ai/zvec-java) |
| [Dart / Flutter](https://pub.dev/packages/zvec) | `flutter pub add zvec` | [Source](https://github.com/zvec-ai/zvec-dart) |

Python requires 64-bit Python 3.10–3.14; Java requires Java 8+.

Searching code or documents? Try **[zvec-grep](https://github.com/zvec-ai/zvec-grep)** (`zg`) — a local-first search CLI that unifies ripgrep, BM25, and vector search, built for humans and AI agents.

Prefer a visual tool? Try **[Zvec Studio](https://github.com/zvec-ai/zvec-studio)** to browse data and debug queries — no code required.

### ✅ Cross-Platform Support

**Linux · macOS · Windows · Android · iOS**

Zvec supports all major platforms — from servers and desktops to mobile devices. 
For more details, please see the [platform support documentation](https://zvec.org/en/docs/db/platforms/).

### 🛠️ Building from Source

If you prefer to build Zvec from source, please check the [Building from Source](https://zvec.org/en/docs/db/build/) guide.

## ⚡ One-Minute Python Example

```python
import zvec

# Define collection schema
schema = zvec.CollectionSchema(
    name="example",
    vectors=zvec.VectorSchema("embedding", zvec.DataType.VECTOR_FP32, 4),
)

# Create collection
collection = zvec.create_and_open(path="./zvec_example", schema=schema)

# Insert documents
collection.insert([
    zvec.Doc(id="doc_1", vectors={"embedding": [0.1, 0.2, 0.3, 0.4]}),
    zvec.Doc(id="doc_2", vectors={"embedding": [0.2, 0.3, 0.4, 0.1]}),
])

# Search by vector similarity
results = collection.query(
    zvec.Query(field_name="embedding", vector=[0.4, 0.3, 0.3, 0.1]),
    topk=10
)

# Results: list of {'id': str, 'score': float, ...}, sorted by relevance
print(results)
```

## 📈 Performance at Scale

Zvec delivers exceptional speed and efficiency, making it ideal for demanding production workloads.

For detailed benchmark methodology, configurations, and complete results, please see our [Benchmarks documentation](https://zvec.org/en/docs/db/benchmarks/).

## 🤝 Join Our Community

</div>

## ❤️ Contributing

We welcome and appreciate contributions from the community! Whether you're fixing a bug, adding a feature, or improving documentation, your help makes Zvec better for everyone.

Check out our [Contributing Guide](./CONTRIBUTING.md) to get started!

Repository info

Default branch: main
Latest version: v0.8.1
Created: 05/12/2025
Last activity: 11/11/2026
License: Apache-2.0
Open issues: 101
Watchers: 69

Topics

agent-skills db embedded faiss fts fulltext-search hnsw llm-memory local rag search-engine semantic-search similarity-search vector-database vector-db

Contributors

egolearner

78 contributions

JalinWang

59 contributions

iaojnh

57 contributions

richyreachy

44 contributions

zhourrr

43 contributions