[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72643":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":36,"readmeContent":37,"aiSummary":38,"trendingCount":16,"starSnapshotCount":16,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},72643,"paperless-ai","clusterzx\u002Fpaperless-ai","clusterzx","An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.","https:\u002F\u002Fclusterzx.github.io\u002Fpaperless-ai\u002F",null,"JavaScript",5745,311,37,52,0,20,44,99,60,113.38,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35],"ai","automation","gemma","llama","mistral","ollama","paperless","paperless-ngx","phi","2026-06-12 04:01:06","# 📄 Paperless-AI\n\n[![GitHub commit activity](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Ft\u002Fclusterzx\u002Fpaperless-ai)](https:\u002F\u002Fgithub.com\u002Fclusterzx\u002Fpaperless-ai\u002Fcommits\u002Fmain)\n[![Docker Pulls](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Fclusterzx\u002Fpaperless-ai)](https:\u002F\u002Fhub.docker.com\u002Fr\u002Fclusterzx\u002Fpaperless-ai)\n[![GitHub Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fclusterzx)](https:\u002F\u002Fgithub.com\u002Fclusterzx)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fclusterzx\u002Fpaperless-ai?cacheSeconds=1)](LICENSE)\n\n# ⚠️ IMPORTANT NOTICE:\nThis repo is currently not maintained. I appreciate all the efforts from the community pushing PRs and creating issues.\nI'm currently rewriting the entire codebase with a more stable, up-to-date architecture. But I'm limited to evenings, and doing support here while also working on the rewrite just isn't feasible for me.\nWith the upcoming official AI integration in Paperless-ngx itself, I'm also not sure if I'll complete the rewrite or continue maintaining this repo at all.\n\n---\n\n**Paperless-AI** is an AI-powered extension for [Paperless-ngx](https:\u002F\u002Fgithub.com\u002Fpaperless-ngx\u002Fpaperless-ngx) that brings automatic document classification, smart tagging, and semantic search using OpenAI-compatible APIs and Ollama.\n\nIt enables **fully automated document workflows**, **contextual chat**, and **powerful customization** — all via an intuitive web interface.\n\n> 💡 Just ask:  \n> “When did I sign my rental agreement?”  \n> “What was the amount of the last electricity bill?”  \n> “Which documents mention my health insurance?”  \n\nPowered by **Retrieval-Augmented Generation (RAG)**, you can now search semantically across your full archive and get precise, natural language answers.\n\n---\n\n## ✨ Features\n\n### 🔄 Automated Document Processing\n- Detects new documents in Paperless-ngx automatically\n- Analyzes content using OpenAI API, Ollama, and other compatible backends\n- Assigns title, tags, document type, and correspondent\n- Built-in support for:\n  - Ollama (Mistral, Llama, Phi-3, Gemma-2)\n  - OpenAI\n  - DeepSeek.ai\n  - OpenRouter.ai\n  - Perplexity.ai\n  - Together.ai\n  - LiteLLM\n  - VLLM\n  - Fastchat\n  - Gemini (Google)\n  - ...and more!\n\n### 🧠 RAG-Based AI Chat\n- Natural language document search and Q&A\n- Understands full document context (not just keywords)\n- Semantic memory powered by your own data\n- Fast, intelligent, privacy-friendly document queries  \n![RAG_CHAT_DEMO](https:\u002F\u002Fraw.githubusercontent.com\u002Fclusterzx\u002Fpaperless-ai\u002Frefs\u002Fheads\u002Fmain\u002Fppairag.png)\n\n### ⚙️ Manual Processing\n- Web interface for manual AI tagging\n- Useful when reviewing sensitive documents\n- Accessible via `\u002Fmanual`\n\n### 🧩 Smart Tagging & Rules\n- Define rules to limit which documents are processed\n- Disable prompts and apply tags automatically\n- Set custom output tags for tracked classification  \n![PPAI_SHOWCASE3](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F1fc9f470-6e45-43e0-a212-b8fa6225e8dd)\n\n---\n\n## 🚀 Installation\n\n> ⚠️ **First-time install:** Restart the container **after completing setup** (API keys, preferences) to build RAG index.  \n> 🔁 Not required for updates.\n\n📘 [Installation Wiki](https:\u002F\u002Fgithub.com\u002Fclusterzx\u002Fpaperless-ai\u002Fwiki\u002F2.-Installation)\n\n---\n\n## 🐳 Docker Support\n\n- Health monitoring and auto-restart\n- Persistent volumes and graceful shutdown\n- Works out of the box with minimal setup\n\n---\n\n## 🔧 Local Development\n\n```bash\n# Install dependencies\nnpm install\n\n# Start development\u002Ftest mode\nnpm run test\n```\n\n---\n\n## 🧭 Roadmap Highlights\n\n- ✅ Multi-AI model support\n- ✅ Multilingual document analysis\n- ✅ Tag rules and filters\n- ✅ Integrated document chat with RAG\n- ✅ Responsive web interface\n\n---\n\n## 🤝 Contributing\n\nWe welcome PRs and contributions!\n\n```bash\n# Fork, clone, then:\ngit checkout -b feature\u002FYourFeature\n# After changes:\ngit commit -m \"Add YourFeature\"\ngit push origin feature\u002FYourFeature\n```\n\nThen open a Pull Request via GitHub.\n\n---\n\n## 🆘 Support & Community\n\n- [Issues](https:\u002F\u002Fgithub.com\u002Fclusterzx\u002Fpaperless-ai\u002Fissues)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FAvNekAfK38)\n\n---\n\n## 📄 License\n\nThis project is licensed under the MIT License. See [LICENSE](LICENSE) for details.\n\n---\n\n## 🙏 Support Development\n\n[![Patreon](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPatreon-F96854?style=for-the-badge&logo=patreon&logoColor=white)](https:\u002F\u002Fwww.patreon.com\u002Fc\u002Fclusterzx)\n[![PayPal](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPayPal-00457C?style=for-the-badge&logo=paypal&logoColor=white)](https:\u002F\u002Fwww.paypal.com\u002Fpaypalme\u002Fbech0r)\n[![BuyMeACoffee](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBuy%20Me%20a%20Coffee-ffdd00?style=for-the-badge&logo=buy-me-a-coffee&logoColor=black)](https:\u002F\u002Fwww.buymeacoffee.com\u002Fclusterzx)\n[![Ko-Fi](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FKo--fi-F16061?style=for-the-badge&logo=ko-fi&logoColor=white)](https:\u002F\u002Fko-fi.com\u002Fclusterzx)\n","Paperless-AI 是一个基于AI的文档分析工具，专为Paperless-ngx设计，利用OpenAI API、Ollama等兼容服务自动分析和标记文档。该项目通过Retrieval-Augmented Generation技术实现了文档内容的智能分类、语义搜索及自然语言问答，支持多种AI后端如Mistral、Llama等，并提供了一个直观的网页界面来管理自动化流程或手动处理敏感文件。特别适用于需要高效管理和检索大量文档的个人或企业场景中，如法律、医疗记录管理等领域。",2,"2026-06-11 03:42:55","high_star"]