RuoYi AI

RuoYi AI is a self-hosted AI assistant platform for teams building assistants that answer questions about their documents or perform tasks with external tools. It has separate user and admin interfaces.

• Model connections: Use local models through Ollama or connect OpenAI, DeepSeek, Qwen, Zhipu and custom OpenAI-compatible APIs, plus FastGPT, RAGFlow and Anthropic-compatible services.
• Document knowledge bases: Search PDF, Word and Excel content with local retrieval, hybrid search and reranking, using Milvus, Weaviate or Qdrant as the vector database.
• Visual workflows: Combine model calls and knowledge searches with conditional branches, HTTP requests, email, web search and image generation in a visual editor.
• Agents and tools: Coordinate agents for web search, SQL queries and chart creation through LangChain4j Supervisor orchestration, and connect tools through function calling or local and remote MCP servers.

The platform is open source under the MIT license and supports Docker deployment on Linux, macOS and Windows. Local document retrieval runs within your deployment. Ollama provides local model execution; cloud model connections send requests to the selected provider. A separate hosted commercial edition is available.

Image, voice and video interfaces are separate capabilities. Ordinary chat attachments aren't connected to those interfaces. Dify and Coze adapter code requires additional provider and credential support before those integrations can be used.