This repository is a curated list of resources for Retrieval-Augmented Generation (RAG) in large language models, aimed at researchers and developers exploring or implementing RAG systems. It provides a structured overview of papers, tools, and educational materials to facilitate understanding and development in this rapidly evolving field.

How It Works

The project functions as a comprehensive, community-driven index of RAG-related research and tooling. It categorizes resources such as seminal papers, recent surveys, practical tools, and educational content like lectures and workshops. This organization allows users to quickly navigate the landscape of RAG, from foundational concepts to implementation details and advanced techniques.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required. Users can directly browse the provided links to papers, code repositories, and tools.

Highlighted Details

• Extensive collection of papers, including surveys from 2023 and 2024, covering general RAG, architecture, and training methodologies.
• Links to key tools like LangChain, LlamaIndex, Verba, and NEUM, which are frameworks for building RAG applications.
• Includes educational resources such as lectures, talks, and tutorials from institutions like Stanford and Anyscale.
• Features a dedicated section for workshops, including upcoming events like MAGMaR at ACL 2025.

Maintenance & Community

The list is actively maintained and updated, with contributions encouraged via suggestions on a "Potential Additions" page. It links to related "Awesome" lists for broader LLM context.

Licensing & Compatibility

The repository itself is a list and does not have a software license. Individual linked resources (papers, code, tools) are subject to their respective licenses.

Limitations & Caveats

As a curated list, the content's depth and breadth are dependent on community contributions and the maintainers' curation efforts. It does not provide direct implementation or benchmarking of RAG systems.