[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72206":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":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},72206,"openrag","langflow-ai\u002Fopenrag","langflow-ai","OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch. ","https:\u002F\u002Fwww.openr.ag",null,"Python",4152,417,23,149,0,18,52,174,54,29.86,"Apache License 2.0",false,"main",true,[],"2026-06-12 02:03:00","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fopenrag-logo-dog.svg\" alt=\"\" width=\"120\"\u002F>\n\n# OpenRAG\n\n\u003Ch3>\n  \u003Cem>Intelligent Agent-powered document search\u003C\u002Fem>\n\u003C\u002Fh3>\n\n\u003C!-- Badges -->\n\n[![Langflow](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLangflow-1C1C1E?style=for-the-badge&logo=langflow)](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Flangflow)\n[![OpenSearch](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOpenSearch-005EB8?style=for-the-badge&logo=opensearch&logoColor=white)](https:\u002F\u002Fgithub.com\u002Fopensearch-project\u002FOpenSearch)\n[![Docling](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocling-000000?style=for-the-badge)](https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling)\n\n[![YouTube Channel](https:\u002F\u002Fimg.shields.io\u002Fyoutube\u002Fchannel\u002Fsubscribers\u002FUCn2bInQrjdDYKEEmbpwblLQ?label=Subscribe&style=social)](https:\u002F\u002Fwww.youtube.com\u002F@OpenRAG\u002F)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Flangflow-ai\u002Fopenrag?style=social)](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Fopenrag\u002Fstargazers)\n[![GitHub forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Flangflow-ai\u002Fopenrag?style=social)](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Fopenrag\u002Fnetwork\u002Fmembers)\n\n[![Documentation](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocumentation-773eff)](https:\u002F\u002Fdocs.openr.ag) [![Ask DeepWiki](https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg)](https:\u002F\u002Fdeepwiki.com\u002Flangflow-ai\u002Fopenrag)\n\n\u003C\u002Fdiv>\n\n---\n\nOpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.\n\nUsers can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience.\n\nCheck out the [documentation](https:\u002F\u002Fdocs.openr.ag\u002F) or get started with the [quickstart](https:\u002F\u002Fdocs.openr.ag\u002Fquickstart).\n\nBuilt with [FastAPI](https:\u002F\u002Ffastapi.tiangolo.com\u002F) and [Next.js](https:\u002F\u002Fgithub.com\u002Fvercel\u002Fnext.js). \nPowered by [OpenSearch](https:\u002F\u002Fgithub.com\u002Fopensearch-project\u002FOpenSearch), [Langflow](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Flangflow), and [Docling](https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling).\n\n---\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fopenrag_readme_downsized.gif\" alt=\"OpenRAG Demo\" width=\"100%\"\u002F>\n\u003C\u002Fdiv>\n\n## ✨ Highlight Features\n\n- **Pre-packaged & ready to run** - All core tools are hooked up and ready to go, just install and run\n- **Agentic RAG workflows** - Advanced orchestration with re-ranking and multi-agent coordination\n- **Document ingestion** - Handles messy, real-world data with intelligent parsing\n- **Drag-and-drop workflow builder** - Visual interface powered by Langflow for rapid iteration\n- **Modular enterprise add-ons** - Extend functionality when you need it\n- **Enterprise search at any scale** - Powered by OpenSearch for production-grade performance\n\n## 🔄 How OpenRAG Works\n\nOpenRAG follows a streamlined workflow to transform your documents into intelligent, searchable knowledge:\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fworkflow-diagram.svg\" alt=\"OpenRAG Workflow Diagram\" width=\"800\"\u002F>\n\u003C\u002Fdiv>\n\n## 🚀 Install OpenRAG\n\nTo get started with OpenRAG, see the installation guides in the OpenRAG documentation:\n\n* [Quickstart](https:\u002F\u002Fdocs.openr.ag\u002Fquickstart)\n* [Install the OpenRAG Python package](https:\u002F\u002Fdocs.openr.ag\u002Finstall-options)\n* [Deploy self-managed services with Docker or Podman](https:\u002F\u002Fdocs.openr.ag\u002Fdocker)\n\n## ✨ Quick Start Workflow\n\n\u003Cdiv align=\"center\">\n\n\u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fuv_run_openrag.png\" alt=\"Use uv run openrag to start\" width=\"300\"\u002F>\n\n**1. Launch OpenRAG**\n\n↓\n\n\u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fadd_knowledge_openrag.png\" alt=\"Add files or folders as knowledge\" width=\"300\"\u002F>\n\n**2. Add Knowledge**\n\n↓\n\n\u003Cimg src=\".\u002Fdocs\u002Fstatic\u002Fimg\u002Fchat_openrag.png\" alt=\"Start Chatting with your knowledge\" width=\"700\"\u002F>\n\n**3. Start Chatting**\n\n\u003C\u002Fdiv>\n\n## 📦 SDKs\n\nIntegrate OpenRAG into your applications with our official SDKs:\n\n### Python SDK\n```bash\npip install openrag-sdk\n```\n\n**Quick Example:**\n```python\nimport asyncio\nfrom openrag_sdk import OpenRAGClient\n\n\nasync def main():\n    async with OpenRAGClient() as client:\n        response = await client.chat.create(message=\"What is RAG?\")\n        print(response.response)\n\n\nif __name__ == \"__main__\":\n    asyncio.run(main())\n```\n\n📖 [Full Python SDK Documentation](https:\u002F\u002Fpypi.org\u002Fproject\u002Fopenrag-sdk\u002F)\n\n### TypeScript\u002FJavaScript SDK\n```bash\nnpm install openrag-sdk\n```\n\n**Quick Example:**\n```typescript\nimport { OpenRAGClient } from \"openrag-sdk\";\n\nconst client = new OpenRAGClient();\nconst response = await client.chat.create({ message: \"What is RAG?\" });\nconsole.log(response.response);\n```\n\n📖 [Full TypeScript\u002FJavaScript SDK Documentation](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fopenrag-sdk)\n\n## 🔌 Model Context Protocol (MCP)\n\nConnect AI assistants like Cursor and Claude Desktop to your OpenRAG knowledge base:\n\n```bash\npip install openrag-mcp\n```\n\n**Quick Example (Cursor\u002FClaude Desktop config):**\n```json\n{\n  \"mcpServers\": {\n    \"openrag\": {\n      \"command\": \"uvx\",\n      \"args\": [\"openrag-mcp\"],\n      \"env\": {\n        \"OPENRAG_URL\": \"http:\u002F\u002Flocalhost:3000\",\n        \"OPENRAG_API_KEY\": \"your_api_key_here\"\n      }\n    }\n  }\n}\n```\n\nThe MCP server provides tools for RAG-enhanced chat, semantic search, and settings management.\n\n📖 [Full MCP Documentation](https:\u002F\u002Fpypi.org\u002Fproject\u002Fopenrag-mcp\u002F)\n\n## 🛠️ Development\n\nFor developers who want to [contribute to OpenRAG](https:\u002F\u002Fdocs.openr.ag\u002Fsupport\u002Fcontribute) or set up a development environment, see [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## 🛟 Troubleshooting\n\nFor assistance with OpenRAG, see [Troubleshoot OpenRAG](https:\u002F\u002Fdocs.openr.ag\u002Fsupport\u002Ftroubleshoot) and visit the [Discussions page](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Fopenrag\u002Fdiscussions).\n\nTo report a bug or submit a feature request, visit the [Issues page](https:\u002F\u002Fgithub.com\u002Flangflow-ai\u002Fopenrag\u002Fissues).","OpenRAG 是一个基于Langflow、Docling和OpenSearch构建的综合性检索增强生成平台，旨在提供智能文档搜索与AI驱动的对话功能。其核心功能包括预打包即用工具、代理型RAG工作流、文档摄入处理、拖放式工作流构建器以及模块化企业插件等，能够有效应对复杂的真实世界数据，并通过语义搜索技术提升信息检索效率。该平台特别适合需要在大规模文档集合中进行高效准确查询的企业级应用场景，如知识管理、客户服务支持及内部信息共享等领域。",2,"2026-06-11 03:40:51","high_star"]