firecrawl/rag-arena

Open-source RAG evaluation through users' feedback

45
/ 100
Emerging

This project helps evaluate and compare how different retrieval-augmented generation (RAG) methods perform for a chatbot. You input a question, and the system provides multiple answers, each generated by a different RAG approach. You then vote on the best response, which helps benchmark the effectiveness of various data retrieval strategies. This tool is designed for AI practitioners, data scientists, or product managers who are building or optimizing RAG-powered chatbots and need to understand which retrieval techniques work best for their specific data.

216 stars. No commits in the last 6 months.

Use this if you are developing a RAG chatbot and want to systematically test and gather feedback on multiple document retrieval methods to improve response quality.

Not ideal if you are looking for a pre-built, ready-to-deploy RAG chatbot without needing to compare or optimize different retrieval strategies.

AI-evaluation chatbot-development natural-language-processing machine-learning-operations data-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

216

Forks

33

Language

TypeScript

License

MIT

Last pushed

Apr 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/firecrawl/rag-arena"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.