OSS Alternative - Discover Top Open Source Alternatives to Popular Software

infiniflow/infinity

An AI-native database designed for LLM applications, offering incredibly fast hybrid search across dense vector, sparse vector, tensor, and full-text data.

Core Features

Incredibly fast hybrid search (dense, sparse, tensor, full-text)

Robust support for RAG applications (search, recommenders, Q&A)

Rich data types including strings, numerics, and vectors

Easy-to-use Python API and single-binary deployment

Quick Start

docker run -d --name infinity -v /var/infinity/:/var/infinity --ulimit nofile=500000:500000 --network=host infiniflow/infinity:nightly

Detailed Introduction

Infinity is an advanced AI-native database specifically engineered to power large language model (LLM) applications. It excels in providing incredibly fast hybrid search capabilities, combining dense and sparse vector embeddings, tensor data, and full-text search with filtering. This makes it an ideal backend for various Retrieval-augmented Generation (RAG) use cases, including conversational AI, question-answering, and content generation. Its high performance, flexible data type support, and ease of deployment via a single binary or Python API address critical challenges in developing next-generation AI applications.