MRAG and RAGLAB
About MRAG
spcl/MRAG
Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"
This project helps developers working with large language models (LLMs) to improve information retrieval for complex queries. It takes queries that require diverse information and a collection of documents, then retrieves more relevant documents by understanding different facets of the query and documents. LLM developers, AI researchers, or data scientists building retrieval-augmented generation (RAG) systems would use this.
About RAGLAB
fate-ubw/RAGLAB
[EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
This project helps researchers and developers evaluate and compare different Retrieval-Augmented Generation (RAG) algorithms for large language models. It takes in various RAG algorithms and benchmark datasets, then outputs comprehensive evaluation results. It is ideal for AI researchers, NLP scientists, and machine learning engineers who need to understand, reproduce, and extend state-of-the-art RAG techniques.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work