GitHub radar
RAGFlow — Creating an AI Chatbot from Your Documents
RAGFlow is an open-source RAG engine developed by infiniflow. You can upload your PDFs, synchronize Notion / Google Drive, and have your own AI chatbot that answers questions based on your knowledge.
RAGFlow is an open source RAG engine provided by infiniflow. It was released at late 2023 with ~91,000 Stars. A complete end-to-end solution for building AI assistants to answer questions from your documents. Upload your PDFs, Word docs, connect your Confluence, S3, Notion, Discord, Google Drive. Process your documents(MinerU/Docling), chunk, embed, retrieve. Visual agentic workflow designer, agent templates. Answer your questions via its built-in chat UI or integrate to Telegram/Discord/Feishu/Line. Support all kinds of LLMs via APIs(e.g., OpenAI/DeepSeek/Gemini). Support MCP since mid-2025. Cloud deployment: https://cloud.ragflow.io/. Self hosted: CPU >= 4 cores, RAM >= 16G, Docker.
Why a vibe-coder should care
If you want a stable AI assistant to answer questions from your knowledge(product docs, notes, research etc.) without hallucination, RAGFlow is one of the most stable open source solutions. Try our cloud service first, and then deploy it locally.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Deploy RAGFlow from https://github.com/infiniflow/ragflow — follow the README (docker compose up), run it locally, open the browser UI, and show me the interface. Ask me if you need an LLM API key.
Self-hosting needs a machine with 16+ GB RAM and Docker. To try without installing, use cloud.ragflow.io.
Open on GitHub▌ More finds