zvec

Overview

Zvec is an in-process vector database designed for high-performance similarity search. It supports dense and sparse vectors, full-text search, and hybrid retrieval with multiple index types. Durable storage via WAL ensures data safety, and it provides official SDKs for Python, Node.js, Go, Rust, and Dart.

README Preview

\n  English | 中文\n\n\n\n  \n    \n    \n  \n\n\n\n  \n  \n  \n  \n  \n  \n\n\n\n  \n\n\n\n  🚀 Quickstart  |\n  🏠 Home  |\n  📚 Docs  |\n  📊 Benchmarks  |\n  🔎 DeepWiki  |\n  🎮 Discord  |\n  🐦 X (Twitter) \n\n\n**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.\n\n> [!Important]\n> 🚀 **v0.5.0 (June 12, 2026)**\n>\n> - **Full-Text Search (FTS)**: Native full-text search — attach an FTS index to any string field and query it with natural-language or structured expressions, no external search engine required.\n> - **Hybrid Retrieval**: Combine full-text and vector search in a single `MultiQuery` across dense vectors, sparse vectors, scalar filters, and text.\n> - **DiskANN Index**: New on-disk index that keeps the bulk of the index on disk, drastically cutting memory usage for large-scale datasets.\n> - **Ecosystem & Platforms**: New official [Go](https://github.com/zvec-ai/zvec-go) / [Rust](https://github.com/zvec-ai/zvec-rust) SDKs, the [Zvec Studio](https://github.com/zvec-ai/zvec-studio) visual tool, and RISC-V support.\n>\n> 👉 [Read the Release Notes](https://github.com/alibaba/zvec/releases/tag/v0.5.0) | [View Roadmap 📍](https://github.com/alibaba/zvec/issues/309)\n\n## 💫 Features\n\n- **Blazing Fast**: Searches billions of vectors in milliseconds.\n- **Simple, Just Works**: [Install](#-installation) and start searching in seconds. Pure local, no servers, no config, no fuss.\n- **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.\n- **Full-Text Search (FTS)**: Native keyword-based full-text search — query string fields with natural-language or structured expressions