RAG Web UI - An open-source AI retrieval system based on Retrieval-Augmented Generation (RAG) technology.

## Overview of RAG Web UI RAG Web UI is an open-source AI retrieval system based on Retrieval-Augmented Generation (RAG) technology. It is designed to help developers build intelligent question-answering systems using their own knowledge bases. The system combines document retrieval with large language models (LLMs) to provide accurate and reliable knowledge-based responses. It supports multiple LLM deployment options, including cloud services like OpenAI and DeepSeek, as well as local model deployment via Ollama. RAG Web UI is suitable for scenarios such as customer service automation, enterprise knowledge management, and intelligent chatbots. ## Overview of RAG Web UI RAG Web UI offers several key features: - **LLM Deployment Support**: Supports multiple large language models, including OpenAI, DeepSeek, and local deployment via Ollama. - **API Interface**: Provides OpenAPI for easy integration with knowledge bases. - **Vector Database Support**: Supports high-performance vector databases like ChromaDB and Qdrant, which can be easily switched using a factory pattern. - **Multi-modal Data Processing**: Supports various document formats such as PDF, DOCX, Markdown, and Text, enabling multi-modal data processing. - **Hybrid Search**: Combines vector retrieval with re-ranking mechanisms for efficient search. - **Knowledge Graph Construction**: Facilitates knowledge graph building through document management and retrieval. - **User Management**: Implements user authentication via JWT and OAuth2. ## System Requirements for RAG Web UI The system requirements for RAG Web UI include: - **Docker** and **Docker Compose v2.0+** for containerization. - **Node.js 18+** and **Python 3.9+** for runtime environments. - A minimum of **8GB of RAM** to ensure smooth operation. ## Installation and Configuration of RAG Web UI To install and configure RAG Web UI: 1. **Clone the Repository**: Clone the RAG Web UI repository from GitHub. 2. **Configure Environment Variables**: Copy the `.env.example` file to `.env` and configure the necessary environment variables. 3. **Start the Service**: Use the command `docker compose up -d --build` to start the service. 4. **Verify Installation**: Access the relevant URL to verify that the service is running correctly. Additional configuration options include settings for MySQL, LLM providers, embedding services, vector databases, and object storage. ## Licensing Terms for RAG Web UI RAG Web UI is licensed under the **Apache-2.0 License**, which allows for customization and commercialization. However, it is currently intended for learning and sharing purposes and is not yet ready for production environments. Developers should review the license details available in the project's GitHub repository. ## Use Cases for RAG Web UI RAG Web UI is suitable for various use cases, including: - **Customer Service Automation**: Automating responses to customer inquiries using a knowledge base. - **Enterprise Knowledge Management**: Managing and retrieving enterprise knowledge efficiently. - **Intelligent Chatbots**: Building chatbots that can provide accurate and context-aware responses. ## User Authentication in RAG Web UI RAG Web UI handles user authentication through **JWT (JSON Web Tokens)** and **OAuth2** mechanisms. This provides a secure way to manage user access and ensures that only authorized users can interact with the system. The configuration includes settings for `SECRET_KEY` and `ACCESS_TOKEN_EXPIRE_MINUTES`. ## Development Status of RAG Web UI RAG Web UI is currently in active development and is intended for learning and sharing purposes. It is not yet ready for production environments. Developers should be aware of this status when considering its use in their projects. ### Citation sources: - [RAG Web UI](https://github.com/rag-web-ui/rag-web-ui) - Official URL Updated: 2025-03-31