Run This Ai
EN DE

Infinity

The AI-native database built for LLM applications — incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text for RAG pipelines

★ 4,596 GitHub Apache-2.0 vector-databaseraghybrid-searchembeddingsllm RAG & Knowledge

Overview

Infinity is an AI-native database purpose-built for LLM applications and RAG pipelines. Unlike traditional vector databases, Infinity supports four types of search in a single unified engine: dense vector (ANN), sparse vector, tensor (multi-vector), and full-text search (BM25). This hybrid search capability means you get the best of all worlds — semantic similarity from dense vectors, keyword precision from sparse vectors and BM25, and multi-vector matching for complex queries. Key features include: blazing-fast performance with C++20 modules and HNSW indexing, production-ready reliability with 130K+ Docker pulls, a built-in GUI for management, and seamless integration with Python and TypeScript SDKs. Infinity handles the full RAG pipeline — from embedding generation to hybrid retrieval — in a single database. With 4,500+ GitHub stars and active development, Infinity is ideal for developers building retrieval-augmented generation systems, semantic search applications, AI-powered documentation search, and any LLM application that needs fast, accurate information retrieval across multiple search paradigms.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  infinity:
    image: infiniflow/infinity:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/infinity:/data

Best VPS for Infinity →

Related tools

LangChain

Build context-aware reasoning applications powered by LLMs

Supabase

Open-source Postgres platform for AI apps with vector search, realtime subscriptions & built-in dashboard

RedisStack

Redis with integrated modules for vector search, JSON, and search capabilities

Meilisearch

Lightning-fast search engine with AI-powered hybrid and vector search

PrivateGPT

Chat with your documents privately using LLMs — 100% local, no data leaks

Milvus

High-performance cloud-native vector database for scalable ANN search

Guides & articles

Getting Started with Infinity: A Developer's Guide to Hybrid Search with Dense, Sparse, and Full-Text Queries

Step-by-step tutorial for setting up Infinity — from Docker deployment to hybrid search with dense vectors, sparse vectors, and full-text using Python SDK.

Jul 4, 2026

Infinity: The AI-Native Database Powering Next-Gen RAG with Hybrid Search in a Single Engine

Discover Infinity — the open-source AI-native database that combines dense vector, sparse vector, tensor (multi-vector), and full-text search in a single unified engine for production RAG pipelines.

Jul 4, 2026