rag-web-ui

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

What is rag-web-ui?

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Overview of rag-web-ui

What it is

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology. It helps build intelligent Q&A systems based on a user's own knowledge base by combining document retrieval and large language models. The system supports multiple LLM deployment options, including cloud services like OpenAI, DeepSeek, and MiniMax, as well as local model deployment through Ollama. It also provides OpenAPI interfaces for knowledge base access via API calls.

Key features

  • 📚 Intelligent Document Management: Supports multiple document formats (PDF, DOCX, Markdown, Text), automatic document chunking and vectorization, and async document processing with incremental updates.- 🤖 Advanced Dialogue Engine: Precise retrieval and generation based on RAG, support for multi-turn contextual dialogue, and support for reference citations in conversations.- 🎯 Robust Architecture: Frontend-backend separation design, distributed file storage, and high-performance vector database support for ChromaDB and Qdrant with easy switching through a Factory pattern.

Use cases

Building intelligent Q&A systems based on a user's own knowledge base. Suitable for scenarios requiring accurate and reliable knowledge-based question answering, with options for cloud or local LLM deployment to meet privacy and cost requirements.

Getting started

Prerequisites: Docker & Docker Compose v2.0+, Node.js 18+, Python 3.9+, 8GB+ RAM.bashgit clone https://github.com/rag-web-ui/rag-web-ui.gitcd rag-web-uicp .env.example .envdocker compose up -d --buildAfter startup, access the frontend UI at http://127.0.0.1.nip.io and API documentation at http://127.0.0.1.nip.io/redoc.

License and pricing

Licensed under Apache-2.0. Open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/rag-web-uirag-web-ui.svg)](https://yunodb.com/tools/rag-web-uirag-web-ui?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/rag-web-uirag-web-ui?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/rag-web-uirag-web-ui.svg" alt="Featured on YunoDB" height="20"></a>