rag-web-ui and rag-arena
These are complements: the web UI provides an interface for RAG dialogue systems while the evaluation arena assesses RAG quality through user feedback, addressing different stages of the RAG development lifecycle.
About rag-web-ui
rag-web-ui/rag-web-ui
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
Supports multiple document formats (PDF, DOCX, Markdown, Text) with async processing and automatic chunking, while offering flexible LLM integration via OpenAI, DeepSeek, or local Ollama deployment. Built on Python FastAPI backend with ChromaDB/Qdrant vector databases, MinIO distributed storage, and Langchain framework; provides OpenAPI interfaces for programmatic knowledge base access alongside a frontend-backend separated architecture enabling multi-turn contextual dialogue with citation tracking.
About rag-arena
firecrawl/rag-arena
Open-source RAG evaluation through users' feedback
Implements a competitive RAG evaluation framework where multiple retrieval strategies (vector store, graph-based, multi-query, contextual compression) compete to answer the same queries, with user votes updating Elo ratings stored in Supabase. The Next.js frontend interfaces with a Flask Python service that runs LangChain retrievers, while a dynamic routing layer selects which RAG method to use per query. Real-time leaderboards track retriever performance across voting metrics, enabling systematic comparison of different embedding and document chunking approaches.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work