{"id":13405520,"url":"https://github.com/infiniflow/ragflow","last_synced_at":"2025-05-12T20:46:21.285Z","repository":{"id":230850787,"uuid":"730534580","full_name":"infiniflow/ragflow","owner":"infiniflow","description":"RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.","archived":false,"fork":false,"pushed_at":"2025-05-03T13:09:58.000Z","size":76265,"stargazers_count":51196,"open_issues_count":2011,"forks_count":4852,"subscribers_count":231,"default_branch":"main","last_synced_at":"2025-05-05T16:06:28.434Z","etag":null,"topics":["agent","agents","ai-search","chatbot","chatgpt","deep-learning","deepseek","deepseek-r1","document-parser","document-understanding","genai","graphrag","llm","nlp","ollama","pdf-to-text","rag","retrieval-augmented-generation","table-structure-recognition","text2sql"],"latest_commit_sha":null,"homepage":"https://ragflow.io","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/infiniflow.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-12-12T06:13:13.000Z","updated_at":"2025-05-05T16:04:23.000Z","dependencies_parsed_at":"2024-06-21T20:57:43.186Z","dependency_job_id":"2d608629-0cdf-4ab8-aabf-804c9ca42f82","html_url":"https://github.com/infiniflow/ragflow","commit_stats":null,"previous_names":["infiniflow/ragflow"],"tags_count":26,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/infiniflow%2Fragflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/infiniflow%2Fragflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/infiniflow%2Fragflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/infiniflow%2Fragflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/infiniflow","download_url":"https://codeload.github.com/infiniflow/ragflow/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253818840,"owners_count":21969232,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","agents","ai-search","chatbot","chatgpt","deep-learning","deepseek","deepseek-r1","document-parser","document-understanding","genai","graphrag","llm","nlp","ollama","pdf-to-text","rag","retrieval-augmented-generation","table-structure-recognition","text2sql"],"created_at":"2024-07-30T19:02:04.497Z","updated_at":"2025-05-12T20:46:21.278Z","avatar_url":"https://github.com/infiniflow.png","language":"TypeScript","readme":"\u003cdiv align=\"center\"\u003e\n\u003ca href=\"https://demo.ragflow.io/\"\u003e\n\u003cimg src=\"web/src/assets/logo-with-text.png\" width=\"520\" alt=\"ragflow logo\"\u003e\n\u003c/a\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"./README.md\"\u003eEnglish\u003c/a\u003e |\n  \u003ca href=\"./README_zh.md\"\u003e简体中文\u003c/a\u003e |\n  \u003ca href=\"./README_tzh.md\"\u003e繁体中文\u003c/a\u003e |\n  \u003ca href=\"./README_ja.md\"\u003e日本語\u003c/a\u003e |\n  \u003ca href=\"./README_ko.md\"\u003e한국어\u003c/a\u003e |\n  \u003ca href=\"./README_id.md\"\u003eBahasa Indonesia\u003c/a\u003e |\n  \u003ca href=\"/README_pt_br.md\"\u003ePortuguês (Brasil)\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://x.com/intent/follow?screen_name=infiniflowai\" target=\"_blank\"\u003e\n        \u003cimg src=\"https://img.shields.io/twitter/follow/infiniflow?logo=X\u0026color=%20%23f5f5f5\" alt=\"follow on X(Twitter)\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://demo.ragflow.io\" target=\"_blank\"\u003e\n        \u003cimg alt=\"Static Badge\" src=\"https://img.shields.io/badge/Online-Demo-4e6b99\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://hub.docker.com/r/infiniflow/ragflow\" target=\"_blank\"\u003e\n        \u003cimg src=\"https://img.shields.io/badge/docker_pull-ragflow:v0.18.0-brightgreen\" alt=\"docker pull infiniflow/ragflow:v0.18.0\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/infiniflow/ragflow/releases/latest\"\u003e\n        \u003cimg src=\"https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue\u0026label=Latest%20Release\" alt=\"Latest Release\"\u003e\n    \u003c/a\u003e\n    \u003ca href=\"https://github.com/infiniflow/ragflow/blob/main/LICENSE\"\u003e\n        \u003cimg height=\"21\" src=\"https://img.shields.io/badge/License-Apache--2.0-ffffff?labelColor=d4eaf7\u0026color=2e6cc4\" alt=\"license\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch4 align=\"center\"\u003e\n  \u003ca href=\"https://ragflow.io/docs/dev/\"\u003eDocument\u003c/a\u003e |\n  \u003ca href=\"https://github.com/infiniflow/ragflow/issues/4214\"\u003eRoadmap\u003c/a\u003e |\n  \u003ca href=\"https://twitter.com/infiniflowai\"\u003eTwitter\u003c/a\u003e |\n  \u003ca href=\"https://discord.gg/NjYzJD3GM3\"\u003eDiscord\u003c/a\u003e |\n  \u003ca href=\"https://demo.ragflow.io\"\u003eDemo\u003c/a\u003e\n\u003c/h4\u003e\n\n\u003cdetails open\u003e\n\u003csummary\u003e\u003cb\u003e📕 Table of Contents\u003c/b\u003e\u003c/summary\u003e\n\n- 💡 [What is RAGFlow?](#-what-is-ragflow)\n- 🎮 [Demo](#-demo)\n- 📌 [Latest Updates](#-latest-updates)\n- 🌟 [Key Features](#-key-features)\n- 🔎 [System Architecture](#-system-architecture)\n- 🎬 [Get Started](#-get-started)\n- 🔧 [Configurations](#-configurations)\n- 🔧 [Build a docker image without embedding models](#-build-a-docker-image-without-embedding-models)\n- 🔧 [Build a docker image including embedding models](#-build-a-docker-image-including-embedding-models)\n- 🔨 [Launch service from source for development](#-launch-service-from-source-for-development)\n- 📚 [Documentation](#-documentation)\n- 📜 [Roadmap](#-roadmap)\n- 🏄 [Community](#-community)\n- 🙌 [Contributing](#-contributing)\n\n\u003c/details\u003e\n\n## 💡 What is RAGFlow?\n\n[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document\nunderstanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models)\nto provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted\ndata.\n\n## 🎮 Demo\n\nTry our demo at [https://demo.ragflow.io](https://demo.ragflow.io).\n\n\u003cdiv align=\"center\" style=\"margin-top:20px;margin-bottom:20px;\"\u003e\n\u003cimg src=\"https://github.com/infiniflow/ragflow/assets/7248/2f6baa3e-1092-4f11-866d-36f6a9d075e5\" width=\"1200\"/\u003e\n\u003cimg src=\"https://github.com/user-attachments/assets/504bbbf1-c9f7-4d83-8cc5-e9cb63c26db6\" width=\"1200\"/\u003e\n\u003c/div\u003e\n\n## 🔥 Latest Updates\n\n- 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.\n- 2025-02-28 Combined with Internet search (Tavily), supports reasoning like Deep Research for any LLMs.\n- 2025-01-26 Optimizes knowledge graph extraction and application, offering various configuration options.\n- 2024-12-18 Upgrades Document Layout Analysis model in DeepDoc.\n- 2024-11-01 Adds keyword extraction and related question generation to the parsed chunks to improve the accuracy of retrieval.\n- 2024-08-22 Support text to SQL statements through RAG.\n\n## 🎉 Stay Tuned\n\n⭐️ Star our repository to stay up-to-date with exciting new features and improvements! Get instant notifications for new\nreleases! 🌟\n\n\u003cdiv align=\"center\" style=\"margin-top:20px;margin-bottom:20px;\"\u003e\n\u003cimg src=\"https://github.com/user-attachments/assets/18c9707e-b8aa-4caf-a154-037089c105ba\" width=\"1200\"/\u003e\n\u003c/div\u003e\n\n## 🌟 Key Features\n\n### 🍭 **\"Quality in, quality out\"**\n\n- [Deep document understanding](./deepdoc/README.md)-based knowledge extraction from unstructured data with complicated\n  formats.\n- Finds \"needle in a data haystack\" of literally unlimited tokens.\n\n### 🍱 **Template-based chunking**\n\n- Intelligent and explainable.\n- Plenty of template options to choose from.\n\n### 🌱 **Grounded citations with reduced hallucinations**\n\n- Visualization of text chunking to allow human intervention.\n- Quick view of the key references and traceable citations to support grounded answers.\n\n### 🍔 **Compatibility with heterogeneous data sources**\n\n- Supports Word, slides, excel, txt, images, scanned copies, structured data, web pages, and more.\n\n### 🛀 **Automated and effortless RAG workflow**\n\n- Streamlined RAG orchestration catered to both personal and large businesses.\n- Configurable LLMs as well as embedding models.\n- Multiple recall paired with fused re-ranking.\n- Intuitive APIs for seamless integration with business.\n\n## 🔎 System Architecture\n\n\u003cdiv align=\"center\" style=\"margin-top:20px;margin-bottom:20px;\"\u003e\n\u003cimg src=\"https://github.com/infiniflow/ragflow/assets/12318111/d6ac5664-c237-4200-a7c2-a4a00691b485\" width=\"1000\"/\u003e\n\u003c/div\u003e\n\n## 🎬 Get Started\n\n### 📝 Prerequisites\n\n- CPU \u003e= 4 cores\n- RAM \u003e= 16 GB\n- Disk \u003e= 50 GB\n- Docker \u003e= 24.0.0 \u0026 Docker Compose \u003e= v2.26.1\n  \u003e If you have not installed Docker on your local machine (Windows, Mac, or Linux),\n  \u003e see [Install Docker Engine](https://docs.docker.com/engine/install/).\n\n### 🚀 Start up the server\n\n1. Ensure `vm.max_map_count` \u003e= 262144:\n\n   \u003e To check the value of `vm.max_map_count`:\n   \u003e\n   \u003e ```bash\n   \u003e $ sysctl vm.max_map_count\n   \u003e ```\n   \u003e\n   \u003e Reset `vm.max_map_count` to a value at least 262144 if it is not.\n   \u003e\n   \u003e ```bash\n   \u003e # In this case, we set it to 262144:\n   \u003e $ sudo sysctl -w vm.max_map_count=262144\n   \u003e ```\n   \u003e\n   \u003e This change will be reset after a system reboot. To ensure your change remains permanent, add or update the\n   \u003e `vm.max_map_count` value in **/etc/sysctl.conf** accordingly:\n   \u003e\n   \u003e ```bash\n   \u003e vm.max_map_count=262144\n   \u003e ```\n\n2. Clone the repo:\n\n   ```bash\n   $ git clone https://github.com/infiniflow/ragflow.git\n   ```\n\n3. Start up the server using the pre-built Docker images:\n\n\u003e [!CAUTION]\n\u003e All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.\n\u003e If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.\n\n   \u003e The command below downloads the `v0.18.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.18.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.18.0` for the full edition `v0.18.0`.\n\n   ```bash\n   $ cd ragflow/docker\n   # Use CPU for embedding and DeepDoc tasks:\n   $ docker compose -f docker-compose.yml up -d\n\n   # To use GPU to accelerate embedding and DeepDoc tasks:\n   # docker compose -f docker-compose-gpu.yml up -d\n   ```\n\n   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |\n   |-------------------|-----------------|-----------------------|--------------------------|\n   | v0.18.0           | \u0026approx;9       | :heavy_check_mark:    | Stable release           |\n   | v0.18.0-slim      | \u0026approx;2       | ❌                   | Stable release            |\n   | nightly           | \u0026approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |\n   | nightly-slim      | \u0026approx;2       | ❌                   | _Unstable_ nightly build  |\n\n4. Check the server status after having the server up and running:\n\n   ```bash\n   $ docker logs -f ragflow-server\n   ```\n\n   _The following output confirms a successful launch of the system:_\n\n   ```bash\n\n         ____   ___    ______ ______ __\n        / __ \\ /   |  / ____// ____// /____  _      __\n       / /_/ // /| | / / __ / /_   / // __ \\| | /| / /\n      / _, _// ___ |/ /_/ // __/  / // /_/ /| |/ |/ /\n     /_/ |_|/_/  |_|\\____//_/    /_/ \\____/ |__/|__/\n\n    * Running on all addresses (0.0.0.0)\n   ```\n\n   \u003e If you skip this confirmation step and directly log in to RAGFlow, your browser may prompt a `network anormal`\n   \u003e error because, at that moment, your RAGFlow may not be fully initialized.\n\n5. In your web browser, enter the IP address of your server and log in to RAGFlow.\n   \u003e With the default settings, you only need to enter `http://IP_OF_YOUR_MACHINE` (**sans** port number) as the default\n   \u003e HTTP serving port `80` can be omitted when using the default configurations.\n6. In [service_conf.yaml.template](./docker/service_conf.yaml.template), select the desired LLM factory in `user_default_llm` and update\n   the `API_KEY` field with the corresponding API key.\n\n   \u003e See [llm_api_key_setup](https://ragflow.io/docs/dev/llm_api_key_setup) for more information.\n\n   _The show is on!_\n\n## 🔧 Configurations\n\nWhen it comes to system configurations, you will need to manage the following files:\n\n- [.env](./docker/.env): Keeps the fundamental setups for the system, such as `SVR_HTTP_PORT`, `MYSQL_PASSWORD`, and\n  `MINIO_PASSWORD`.\n- [service_conf.yaml.template](./docker/service_conf.yaml.template): Configures the back-end services. The environment variables in this file will be automatically populated when the Docker container starts. Any environment variables set within the Docker container will be available for use, allowing you to customize service behavior based on the deployment environment.\n- [docker-compose.yml](./docker/docker-compose.yml): The system relies on [docker-compose.yml](./docker/docker-compose.yml) to start up.\n\n\u003e The [./docker/README](./docker/README.md) file provides a detailed description of the environment settings and service\n\u003e configurations which can be used as `${ENV_VARS}` in the [service_conf.yaml.template](./docker/service_conf.yaml.template) file.\n\nTo update the default HTTP serving port (80), go to [docker-compose.yml](./docker/docker-compose.yml) and change `80:80`\nto `\u003cYOUR_SERVING_PORT\u003e:80`.\n\nUpdates to the above configurations require a reboot of all containers to take effect:\n\n\u003e ```bash\n\u003e $ docker compose -f docker-compose.yml up -d\n\u003e ```\n\n### Switch doc engine from Elasticsearch to Infinity\n\nRAGFlow uses Elasticsearch by default for storing full text and vectors. To switch to [Infinity](https://github.com/infiniflow/infinity/), follow these steps:\n\n1. Stop all running containers:\n\n   ```bash\n   $ docker compose -f docker/docker-compose.yml down -v\n   ```\n\n\u003e [!WARNING]\n\u003e `-v` will delete the docker container volumes, and the existing data will be cleared.\n\n2. Set `DOC_ENGINE` in **docker/.env** to `infinity`.\n\n3. Start the containers:\n\n   ```bash\n   $ docker compose -f docker-compose.yml up -d\n   ```\n\n\u003e [!WARNING]\n\u003e Switching to Infinity on a Linux/arm64 machine is not yet officially supported.\n\n## 🔧 Build a Docker image without embedding models\n\nThis image is approximately 2 GB in size and relies on external LLM and embedding services.\n\n```bash\ngit clone https://github.com/infiniflow/ragflow.git\ncd ragflow/\ndocker build --platform linux/amd64 --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .\n```\n\n## 🔧 Build a Docker image including embedding models\n\nThis image is approximately 9 GB in size. As it includes embedding models, it relies on external LLM services only.\n\n```bash\ngit clone https://github.com/infiniflow/ragflow.git\ncd ragflow/\ndocker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly .\n```\n\n## 🔨 Launch service from source for development\n\n1. Install uv, or skip this step if it is already installed:\n\n   ```bash\n   pipx install uv pre-commit\n   ```\n\n2. Clone the source code and install Python dependencies:\n\n   ```bash\n   git clone https://github.com/infiniflow/ragflow.git\n   cd ragflow/\n   uv sync --python 3.10 --all-extras # install RAGFlow dependent python modules\n   uv run download_deps.py\n   pre-commit install\n   ```\n\n3. Launch the dependent services (MinIO, Elasticsearch, Redis, and MySQL) using Docker Compose:\n\n   ```bash\n   docker compose -f docker/docker-compose-base.yml up -d\n   ```\n\n   Add the following line to `/etc/hosts` to resolve all hosts specified in **docker/.env** to `127.0.0.1`:\n\n   ```\n   127.0.0.1       es01 infinity mysql minio redis\n   ```\n\n4. If you cannot access HuggingFace, set the `HF_ENDPOINT` environment variable to use a mirror site:\n\n   ```bash\n   export HF_ENDPOINT=https://hf-mirror.com\n   ```\n\n5. Launch backend service:\n\n   ```bash\n   source .venv/bin/activate\n   export PYTHONPATH=$(pwd)\n   bash docker/launch_backend_service.sh\n   ```\n\n6. Install frontend dependencies:\n   ```bash\n   cd web\n   npm install\n   ```\n7. Launch frontend service:\n\n   ```bash\n   npm run dev\n   ```\n\n   _The following output confirms a successful launch of the system:_\n\n   ![](https://github.com/user-attachments/assets/0daf462c-a24d-4496-a66f-92533534e187)\n\n## 📚 Documentation\n\n- [Quickstart](https://ragflow.io/docs/dev/)\n- [Configuration](https://ragflow.io/docs/dev/configurations)\n- [Release notes](https://ragflow.io/docs/dev/release_notes)\n- [User guides](https://ragflow.io/docs/dev/category/guides)\n- [Developer guides](https://ragflow.io/docs/dev/category/developers)\n- [References](https://ragflow.io/docs/dev/category/references)\n- [FAQs](https://ragflow.io/docs/dev/faq)\n\n## 📜 Roadmap\n\nSee the [RAGFlow Roadmap 2025](https://github.com/infiniflow/ragflow/issues/4214)\n\n## 🏄 Community\n\n- [Discord](https://discord.gg/NjYzJD3GM3)\n- [Twitter](https://twitter.com/infiniflowai)\n- [GitHub Discussions](https://github.com/orgs/infiniflow/discussions)\n\n## 🙌 Contributing\n\nRAGFlow flourishes via open-source collaboration. In this spirit, we embrace diverse contributions from the community.\nIf you would like to be a part, review our [Contribution Guidelines](./CONTRIBUTING.md) first.\n","funding_links":[],"categories":["Python","TypeScript","**Section 1: RAG, LlamaIndex, and Vector Storage**","🏗️ Frameworks \u0026 Orchestration","A01_文本生成_文本对话","Table of Contents","Web \u0026 Desktop UIs","Chatbots","Azure Cognitive Search \u0026 OpenAI","2024.08","开源工具","📚 Projects (1974 total)","知识库 RAG","nlp","RAG","HarmonyOS","Industry Strength Information Retrieval","Repos","📊 Data and Research Agents","Orchestration","开发者工具 \u0026 AI Infra","Data Processing \u0026 ETL Agents","SDK, Libraries, Frameworks","Machine Learning","🧠 AI Applications \u0026 Platforms","Libraries/Frameworks","Frameworks and Libraries","LLM Application / RAG","Open Source Tools","Open Source and Commercial Projects"],"sub_categories":["**RAG Solution Design \u0026 Application**","3. The Enterprise / High-Scale Stack (The 1%)","大语言对话模型及数据","RAG","RAGFlow-GraphRAG【导航员】","RAG框架","MCP Servers","Windows Manager","RAG and Knowledge Bases","RAG 框架","NL AI Frameworks","Python library, sdk or frameworks","Tools","Evaluation","RAG and Knowledge Systems"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finfiniflow%2Fragflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finfiniflow%2Fragflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finfiniflow%2Fragflow/lists"}