infiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
What it solves
Infinity 是一个 AI 原生的数据库,旨在处理 LLM 应用的复杂数据检索需求。它解决了需要多个独立系统分别处理不同搜索类型(如语义向量搜索和关键词全文搜索)的难题,将它们合并为单一高性能引擎。
How it works
Infinity 提供统一的混合搜索系统,允许用户将密集嵌入、稀疏嵌入、张量和全文搜索结合,并支持过滤。它采用单二进制文件架构,无外部依赖,简化部署。对于 AI 开发者,可直接作为 Python 模块嵌入,或通过 Docker 以独立服务器方式运行。
Who it’s for
本项目面向构建 RAG(检索增强生成)应用的 AI 开发者,典型场景包括对话式 AI、协作助理、推荐系统以及问答系统。
Highlights
- Hybrid Search Capabilities: Supports dense and sparse embeddings, tensors, and full-text search in one place.
- High Performance: Achieves sub-millisecond query latency on million-scale vector datasets and high QPS for full-text search.
- Advanced Reranking: Includes support for various rerankers, including ColBERT, RRF, and weighted sum.
- Easy Deployment: Offered as a single-binary architecture or a Docker image for rapid setup.