AIAnytime/rag-evaluator

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

52
/ 100
Established

This tool helps you check the quality of answers generated by AI systems, especially those that combine information retrieval with text generation (RAG systems). You provide an AI's answer, the original question, and a perfect reference answer, and it tells you how good the AI's answer is. This is ideal for AI developers, researchers, and anyone building or testing conversational AI applications.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing or managing AI systems that generate text and need to quantitatively assess the accuracy, coherence, and fairness of their outputs against known good answers.

Not ideal if you're looking for a tool to generate text, fix grammar, or analyze human-written content for sentiment, as it specifically evaluates AI-generated responses.

AI-development NLP-evaluation conversational-AI-testing content-generation-quality
Stale 6m
Maintenance 0 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

42

Forks

18

Language

Python

License

MIT

Last pushed

Aug 10, 2024

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/AIAnytime/rag-evaluator"

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