rag-all-techniques and RAG-Arena
These are complements: one provides simplified implementations of multiple RAG techniques for practical application, while the other offers comparative evaluation and explanation of those same techniques, making them useful together for both learning and benchmarking RAG approaches.
About rag-all-techniques
liu673/rag-all-techniques
Implementation of all RAG techniques in a simpler way（以简单的方式实现所有 RAG 技术）
This project provides practical, framework-agnostic implementations of various advanced Retrieval Augmented Generation (RAG) techniques. It takes unstructured text data, applies different methods for breaking it down and enriching it, and then uses a large language model to generate improved, contextually relevant answers to user queries. This is for AI practitioners, researchers, or anyone building custom question-answering systems who wants to understand and experiment with core RAG components.
About RAG-Arena
ZehaoJia1024/RAG-Arena
讲解并评估多种RAG算法
This project helps AI developers and researchers understand and compare various Retrieval-Augmented Generation (RAG) techniques. It takes different RAG algorithms as input and provides a systematic evaluation of their performance, offering insights into their effectiveness. The output is a clear ranking and detailed breakdown of how each RAG method performs against specific criteria, guiding users to select the most suitable approach for their large language model applications.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work