Eustema-S-p-A/SCARF

SCARF (System for Comprehensive Assessment of RAG Frameworks) is a modular evaluation framework for benchmarking deployed Retrieval Augmented Generation (RAG) applications. It offers end-to-end, black-box assessment across multiple configurations, supports automated testing with several vector databases and LLMs.

22
/ 100
Experimental

This tool helps AI engineers and machine learning practitioners systematically evaluate the performance of their Retrieval Augmented Generation (RAG) applications. It takes your deployed RAG systems, along with various configurations like different vector databases and large language models, and outputs detailed reports on their factual accuracy, contextual relevance, and response coherence. You'd use this to compare and fine-tune different versions of your RAG applications.

No commits in the last 6 months.

Use this if you need to objectively compare multiple versions of your RAG application or understand how changes to its components impact its real-world performance.

Not ideal if you are looking for a tool to build or deploy RAG applications, as this is solely for evaluation.

AI application development Natural Language Processing LLM evaluation machine learning operations RAG system testing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Python

License

AGPL-3.0

Last pushed

Apr 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Eustema-S-p-A/SCARF"

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