[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9753":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":37,"discoverSource":38},9753,"R2R","SciPhi-AI\u002FR2R","SciPhi-AI","SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.","",null,"Python",7884,636,43,105,0,2,10,70,8,39.41,"MIT License",false,"main",[26,27,28,29,30,31,32,33],"artificial-intelligence","large-language-models","python","question-answering","rag","retrieval-augmented-generation","retrieval-systems","search","2026-06-12 02:02:12","\u003Cimg width=\"1217\" alt=\"Screenshot 2025-03-27 at 6 35 02 AM\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F10b530a6-527f-4335-b2e4-ceaa9fc1219f\" \u002F>\n\n\u003Ch3 align=\"center\">\nThe most advanced AI retrieval system.\n\nAgentic Retrieval-Augmented Generation (RAG) with a RESTful API.\n\u003C\u002Fh3>\n\n\u003Cdiv align=\"center\">\n   \u003Cdiv>\n      \u003Ca href=\"https:\u002F\u002Fr2r-docs.sciphi.ai\u002F\">\u003Cstrong>Docs\u003C\u002Fstrong>\u003C\u002Fa> ·\n      \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=bug_report.md&title=\">\u003Cstrong>Report Bug\u003C\u002Fstrong>\u003C\u002Fa> ·\n      \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=feature_request.md&title=\">\u003Cstrong>Feature Request\u003C\u002Fstrong>\u003C\u002Fa> ·\n      \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fp6KqD2kjtB\">\u003Cstrong>Discord\u003C\u002Fstrong>\u003C\u002Fa>\n   \u003C\u002Fdiv>\n   \u003Cbr \u002F>\n   \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fr2r-docs.sciphi.ai\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs.sciphi.ai-3F16E4\" alt=\"Docs\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fp6KqD2kjtB\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1120774652915105934?style=social&logo=discord\" alt=\"Discord\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciPhi-AI\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FSciPhi-AI\u002FR2R\" alt=\"Github Stars\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fpulse\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fw\u002FSciPhi-AI\u002FR2R\" alt=\"Commits-per-week\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-purple.svg\" alt=\"License: MIT\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n# About\nR2R is an advanced AI retrieval system supporting Retrieval-Augmented Generation (RAG) with production-ready features. Built around a RESTful API, R2R offers multimodal content ingestion, hybrid search, knowledge graphs, and comprehensive document management.\n\nR2R also includes a **Deep Research API**, a multi-step reasoning system that fetches relevant data from your knowledgebase and\u002For the internet to deliver richer, context-aware answers for complex queries.\n\n# Usage\n\n```python\n# Basic search\nresults = client.retrieval.search(query=\"What is DeepSeek R1?\")\n\n# RAG with citations\nresponse = client.retrieval.rag(query=\"What is DeepSeek R1?\")\n\n# Deep Research RAG Agent\nresponse = client.retrieval.agent(\n  message={\"role\":\"user\", \"content\": \"What does deepseek r1 imply? Think about market, societal implications, and more.\"},\n  rag_generation_config={\n    \"model\": \"anthropic\u002Fclaude-3-7-sonnet-20250219\",\n    \"extended_thinking\": True,\n    \"thinking_budget\": 4096,\n    \"temperature\": 1,\n    \"top_p\": None,\n    \"max_tokens_to_sample\": 16000,\n  },\n)\n```\n\n\n\n## Getting Started\n```bash\n# Quick install and run in light mode\npip install r2r\nexport OPENAI_API_KEY=sk-...\npython -m r2r.serve\n\n# Or run in full mode with Docker\n# git clone git@github.com:SciPhi-AI\u002FR2R.git && cd R2R\n# export R2R_CONFIG_NAME=full OPENAI_API_KEY=sk-...\n# docker compose -f compose.full.yaml --profile postgres up -d\n```\n\nFor detailed self-hosting instructions, see the [self-hosting docs](https:\u002F\u002Fr2r-docs.sciphi.ai\u002Fself-hosting\u002Finstallation\u002Foverview).\n\n## Demo\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F173f7a1f-7c0b-4055-b667-e2cdcf70128b\n\n## Using the API\n\n### 1. Install SDK & Setup\n\n```bash\n# Install SDK\npip install r2r  # Python\n# or\nnpm i r2r-js    # JavaScript\n```\n\n### 2. Client Initialization\n\n```python\nfrom r2r import R2RClient\nclient = R2RClient(base_url=\"http:\u002F\u002Flocalhost:7272\")\n```\n\n```javascript\nconst { r2rClient } = require('r2r-js');\nconst client = new r2rClient(\"http:\u002F\u002Flocalhost:7272\");\n```\n\n### 3. Document Operations\n\n```python\n# Ingest sample or your own document\nclient.documents.create(file_path=\"\u002Fpath\u002Fto\u002Ffile\")\n\n# List documents\nclient.documents.list()\n```\n\n\n## Key Features\n\n- **📁 Multimodal Ingestion**: Parse `.txt`, `.pdf`, `.json`, `.png`, `.mp3`, and more\n- **🔍 Hybrid Search**: Semantic + keyword search with reciprocal rank fusion\n- **🔗 Knowledge Graphs**: Automatic entity & relationship extraction\n- **🤖 Agentic RAG**: Reasoning agent integrated with retrieval\n- **🔐 User & Access Management**: Complete authentication & collection system\n\n## Community & Contributing\n\n- [Join our Discord](https:\u002F\u002Fdiscord.gg\u002Fp6KqD2kjtB) for support and discussion\n- Submit [feature requests](https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=feature_request.md&title=) or [bug reports](https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fissues\u002Fnew?assignees=&labels=&projects=&template=bug_report.md&title=)\n- Open PRs for new features, improvements, or documentation\n\n### Our Contributors\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciPhi-AI\u002FR2R\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=SciPhi-AI\u002FR2R\" \u002F>\n\u003C\u002Fa>\n","R2R是一个先进的AI检索系统，支持检索增强生成（RAG）并提供生产就绪的特性。该项目基于RESTful API构建，具备多模态内容摄入、混合搜索、知识图谱以及全面的文档管理功能。其核心技术包括一个深度研究API，该API能够从知识库或互联网中获取相关数据，为复杂查询提供更丰富、上下文感知的答案。适用于需要高效信息检索和智能问答的应用场景，如企业内部知识管理、在线客服系统等。","2026-06-11 03:24:34","top_topic"]