Awesome-GraphRAG and RAG-Survey
These are complementary resources that together provide comprehensive coverage of retrieval-augmented generation: one specializes in graph-based RAG approaches and implementations while the other surveys the broader RAG landscape across foundations, enhancements, and applications.
About Awesome-GraphRAG
DEEP-PolyU/Awesome-GraphRAG
Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.
This project compiles a comprehensive list of research and open-source tools related to Graph-based Retrieval-Augmented Generation (GraphRAG). It helps researchers, PhD students, and AI practitioners explore advanced methods for building more accurate and context-aware customized Large Language Models (LLMs). The project categorizes and explains various techniques for organizing knowledge, retrieving information, and integrating it with LLMs, moving beyond traditional text-chunking approaches.
About RAG-Survey
hymie122/RAG-Survey
Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".
This project offers a curated collection of research papers focused on Retrieval-Augmented Generation (RAG) for AI-Generated Content (AIGC). It organizes these papers into a clear taxonomy covering foundations, enhancements, and applications, providing a comprehensive overview of the field. Anyone conducting research or developing AIGC solutions using RAG will find this useful for understanding current advancements.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work