XRAG and rageval
About XRAG
DocAILab/XRAG
XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation
This project helps developers and researchers evaluate different components of Retrieval-Augmented Generation (RAG) systems. It takes various RAG configurations, such as different retrievers, embeddings, and Large Language Models, and outputs performance metrics and visualizations. The primary users are AI/ML engineers and researchers building or optimizing RAG applications.
About rageval
gomate-community/rageval
Evaluation tools for Retrieval-augmented Generation (RAG) methods.
This tool helps evaluate the performance of your Retrieval-Augmented Generation (RAG) systems. It takes the outputs from various stages of your RAG pipeline—like rewritten queries, retrieved documents, and generated answers—and provides comprehensive scores on how well your system is performing across aspects like answer correctness, factual consistency, and document relevance. It is designed for AI/ML engineers or researchers building and refining RAG-based applications.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work