R2R
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
7.7k
Stars
+-8
Stars/month
0
Releases (6m)
Star Growth
+1 (0.0%)
Overview
R2R 是一个先进的生产级 AI 检索系统，专为检索增强生成（RAG）设计，具备完整的 RESTful API。该系统支持多模态内容摄取、混合搜索、知识图谱和全面的文档管理功能。其独特的深度研究 API 提供多步骤推理能力，能够从知识库和互联网获取相关数据，为复杂查询提供更丰富、上下文感知的答案。R2R 在 GitHub 上拥有 7,748 颗星，证明了其在企业级 RAG 解决方案中的重要地位。该工具提供轻量模式和完整模式两种部署选项，支持 Docker 容器化部署和 PostgreSQL 数据库集成，确保可扩展性和生产环境的稳定性。
Deep Analysis
Key Differentiator
vs LlamaIndex / LangChain RAG: production-ready REST API with built-in knowledge graphs, Deep Research agent, and user access management — the most feature-complete open-source RAG platform
⚡ Capabilities
- • Advanced agentic RAG with RESTful API
- • Multimodal content ingestion (PDF, JSON, PNG, MP3, etc.)
- • Hybrid search (semantic + keyword) with reciprocal rank fusion
- • Automatic knowledge graph extraction (entities and relationships)
- • Deep Research API for multi-step reasoning
- • User authentication and access management
- • Python and JavaScript SDKs
🔗 Integrations
OpenAIAnthropic ClaudePostgreSQLDocker
✓ Best For
- ✓ Production RAG systems needing hybrid search + knowledge graphs
- ✓ Teams building multi-step research agents over their documents
- ✓ Applications requiring user-level access control for document retrieval
✗ Not Ideal For
- ✗ Simple Q&A prototypes (over-engineered for basic use)
- ✗ Fully offline/private setups (default requires OpenAI)
- ✗ Edge or mobile deployments
Languages
PythonJavaScript/TypeScript
Deployment
pip install r2rDocker Composeself-hosted
⚠ Known Limitations
- ⚠ Full mode requires Docker Compose with multiple services
- ⚠ Knowledge graph features require significant compute
- ⚠ OpenAI API key required for default configuration
- ⚠ Deep Research API uses extended thinking (higher cost)
Pros
- + 生产就绪的 RESTful API 架构，支持企业级部署和集成
- + 深度研究 API 具备多步骤推理和扩展思考能力，支持复杂查询分析
- + 全面的功能集：多模态内容摄取、混合搜索、知识图谱和文档管理
Cons
- - 基础设置需要 OpenAI API 密钥，增加了外部依赖
- - 完整功能需要 Docker 和 PostgreSQL，部署复杂度较高
Use Cases
- • 需要生产级部署的企业 RAG 系统，要求高可靠性和 API 集成
- • 复杂研究查询场景，需要多步骤推理和深度分析能力
- • 大规模知识管理系统，需要混合搜索和知识图谱功能
Getting Started
1. 安装：pip install r2r；2. 配置：export OPENAI_API_KEY=sk-...；3. 启动：python -m r2r.serve（轻量模式）或使用 Docker compose 启动完整模式