RAGFlow
RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine and orchestration platform developed by the InfiniFlow team. It provides developers with end-to-end RAG pipeline management capabilities based on document parsing, knowledge base construction, and large language model integration. The platform supports deep document understanding across multiple file formats and offers a visual workflow orchestration interface. It is widely used in enterprise knowledge base question answering, intelligent customer service, and document retrieval applications.
Core Facts
Timeline (last 90 days)
RAGFlow depends on components such as redis, es, and minio, and the first startup takes approximately 10 to 20 minutes.
Because RAGFlow runs inside a Docker container and cannot directly access the host machine, when configuring the Ollama URL, host.docker.internal plus port 11434 should be used instead of the IPv4 address from ipconfig.
RAGFlow's .env configuration file uses port 80 by default, which can be changed to other ports such as 8888 to avoid conflicts with software like Dify.
The .env configuration file in RAGFlow defaults to the lightweight version (without an Embedding model), while the full version comes with an Embedding model ready for direct use.
RAGFlow requires a large number of dependencies such as databases, and deploying via Docker can automatically pull images and complete dependency configuration and network interconnection.
After uploading a file in RAGFlow, you must click parse; otherwise, the large model will be unable to understand the file content.
RAGFlow currently has no official web version and must be deployed and run by the user themselves.
The RAGFlow full-version image is approximately 9 GB in size, and the initial pull may take more than half an hour on a slow network connection.
Around line 84 in the RAGFlow environment file, the lightweight version is distinguished from the full version: the lightweight version does not include an Embedding model, while the full version comes with an Embedding model.
When adding a local DeepSeek in RAGFlow, the model type must be selected as chat, and no API key is required for local deployment.
2 more timeline events
All Facts (20)
RAGFlow is an open-source RAG engine that provides complete knowledge base management and intelligent question-answering functionality.
80%UnverifiedRAGFlow基于Docker容器化部署，启动后运行五个容器：Redis、MinIO、MySQL、Elasticsearch和RAGFlow Server
95%Unverified53AI Hub支持与Coze、Dify、FastGPT、RAGFlow等主流AI开发平台无缝集成
90%UnverifiedRAGFlow集成了AI Agent功能，提供可视化画布和预置模板，支持客服、数据分析等典型场景
90%UnverifiedRAGFlow的聊天助理提供可溯源的回答机制，用户可以查看AI回答具体引用了哪些知识库原文
90%UnverifiedRAGFlow依赖Elasticsearch（全文检索）、Redis（缓存）、MySQL（元数据存储）等多个服务
85%UnverifiedRAGFlow由Infiniflow团队开发，专注于RAG流程的深度优化，采用了DeepDoc等自研文档理解技术
85%Unverified在RAG框架市场中，LangChain和LlamaIndex作为编排层框架，Dify、FastGPT、RAGFlow是面向业务用户的完整平台产品
85%UnverifiedOllama的OLLAMA_HOST环境变量需设置为0.0.0.0:11434，以便Docker容器中的RAGFlow能访问本机的Ollama服务
85%UnverifiedOllama listens only on localhost by default; the environment variable OLLAMA_HOST must be configured to 0.0.0.0:11434 to listen on all IPs, making it accessible to RAGFlow inside a virtual machine.
60%UnverifiedWhen adding a local DeepSeek in RAGFlow, the model type must be selected as chat, and no API key is required for local deployment.
60%UnverifiedRAGFlow supports a parent-child chunking strategy — using small chunks for retrieval matching while returning parent chunks containing more context to the LLM
60%UnverifiedRAGFlow integrates the OCR capabilities of the DeepDoc project, enabling it to recognize text content in scanned PDFs
60%UnverifiedRAGFlow支持多种文档格式，包括PDF、Word、Excel等
60%UnverifiedRAGFlow employs Deep Document Understanding technology, which can recognize layout information such as heading hierarchy, table structure, and headers and footers within documents.
60%UnverifiedBecause RAGFlow runs inside a Docker container and cannot directly access the host machine, when configuring the Ollama URL, host.docker.internal plus port 11434 should be used instead of the IPv4 address from ipconfig.
50%UnverifiedRAGFlow depends on components such as redis, es, and minio, and the first startup takes approximately 10 to 20 minutes.
50%UnverifiedRAGFlow's .env configuration file uses port 80 by default, which can be changed to other ports such as 8888 to avoid conflicts with software like Dify.
50%UnverifiedThe .env configuration file in RAGFlow defaults to the lightweight version (without an Embedding model), while the full version comes with an Embedding model ready for direct use.
50%UnverifiedAfter uploading a file in RAGFlow, you must click parse; otherwise, the large model will be unable to understand the file content.
50%