Overview
[Product Introduction] Zvec is an open source, lightweight in-process vector database built on Alibaba's proven Proxima engine. Designed for embedded applications, it provides production-grade, low-latency scalable similarity search capabilities in any code execution environment, from servers to edge devices, without the need for separate server configuration. Zvec aims to help developers quickly build high-performance AI applications such as RAG, image search, and code search through a minimalist architecture. [Product Features] Ultimate performance: Supports millisecond-level retrieval of billions of vectors, and has excellent QPS performance on tens of millions of data sets. Lightweight and easy to use: It adopts the in-process (InProcess) operating mode and is ready to use without complex operation, maintenance and configuration. Hybrid search: supports dense vectors and sparse vectors, and provides hybrid search and group search functions combined with structured filters. Multi-terminal support: Compatible with Python and Node.js, supports Linux and macOS (including ARM64) platforms. Project open source address: https://github.com/alibaba/zvec
Connected profiles
More Coding assistants products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
【产品介绍】Zvec 是一款基于阿里巴巴实战检验的 Proxima 引擎构建的开源、轻量级进程内向量数据库。它专为嵌入应用程序设计，无需独立的服务器配置，即可在任何代码运行环境（从服务器到边缘设备）中提供生产级、低延迟的可扩展相似性搜索能力。Zvec 旨在通过极简的架构，帮助开发者快速构建 RAG、图像搜索和代码搜索等高性能 AI 应用。【产品功能】极致性能：支持十亿级向量规模的毫秒级检索，在千万级数据集上具备卓越的 QPS 表现。轻量易用：采用进程内（InProcess）运行模式，安装即用，无需复杂的运维与配置。混合检索：支持稠密向量与稀疏向量，并提供结合结构化过滤器的混合搜索及分组搜索功能。多端支持：兼容 Python 和 Node.js，支持 Linux 和 macOS（含 ARM64）平台。项目开源地址：https://github.com/alibaba/zvec