rag-web-ui  by rag-web-ui

RAG system for building intelligent Q&A over a knowledge base

created 6 months ago
2,542 stars

Top 18.8% on sourcepulse

GitHubView on GitHub
Project Summary

RAG Web UI is an intelligent dialogue system designed to build Q&A systems using Retrieval-Augmented Generation (RAG) on custom knowledge bases. It targets developers and users needing to create accurate, reliable knowledge-based services, offering flexibility with multiple LLM and vector database integrations, and providing an API for programmatic access.

How It Works

The system employs a backend-frontend separation architecture. Document ingestion involves asynchronous processing: documents are extracted, chunked, embedded, and stored in a vector database (ChromaDB or Qdrant). Queries are embedded, used to retrieve relevant chunks from the vector database, re-ranked, and then passed to an LLM (OpenAI, DeepSeek, or local via Ollama) for response generation. The process includes multi-turn context support and reference citations.

Quick Start & Requirements

  • Install: Clone the repository and use docker compose up -d --build.
  • Prerequisites: Docker & Docker Compose v2.0+, Node.js 18+, Python 3.9+, 8GB+ RAM.
  • Access: Frontend UI at http://127.0.0.1.nip.io, API Docs at http://127.0.0.1.nip.io/redoc.
  • Docs: Quick Start, Architecture, Configuration.

Highlighted Details

  • Supports multiple document formats (PDF, DOCX, Markdown, Text).
  • Integrates with OpenAI, DeepSeek, and local LLMs via Ollama.
  • Supports ChromaDB and Qdrant vector databases.
  • Features a distributed object storage solution (MinIO).
  • Provides OpenAPI interfaces for API access.

Maintenance & Community

  • Active development with a roadmap including features like "Workflow By Natural Language" and "Multi-path Retrieval".
  • Contribution guidelines provided, encouraging community involvement.

Licensing & Compatibility

  • Licensed under Apache-2.0.
  • Note: Explicitly states "Please do not use it for commercial purposes. It is not ready for production use."

Limitations & Caveats

The project is explicitly stated as being for learning and sharing RAG knowledge only, not ready for production use, and still under active development. Commercial use is prohibited.

Health Check
Last commit

3 months ago

Responsiveness

1 day

Pull Requests (30d)
4
Issues (30d)
0
Star History
185 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems).

super-rag by superagent-ai

0.3%
380
RAG pipeline for AI apps
created 1 year ago
updated 1 year ago
Starred by Andrej Karpathy Andrej Karpathy(Founder of Eureka Labs; Formerly at Tesla, OpenAI; Author of CS 231n), Alex Cheema Alex Cheema(Cofounder of EXO Labs), and
3 more.

Perplexica by ItzCrazyKns

0.3%
23k
AI-powered search engine alternative
created 1 year ago
updated 1 day ago
Feedback? Help us improve.