RAG system for building intelligent Q&A over a knowledge base
Top 18.8% on sourcepulse
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
docker compose up -d --build
.http://127.0.0.1.nip.io
, API Docs at http://127.0.0.1.nip.io/redoc
.Highlighted Details
Maintenance & Community
Licensing & Compatibility
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.
3 months ago
1 day