Great Resources for Learning and Implementing Retrieval-Augmented Generation (RAG)

In this post, we will explore several excellent resources for understanding Retrieval-Augmented Generation (RAG). The post is structured as a step-by-step learning journey. This is intended to be a regularly updated list.

101 - Basic introductions

a) Microsoft’s Generative AI for Beginners RAG chapter

b) AWS short article What is RAG

c) NVidia’s introduction blog

201 - Depth over introductions

a) NVidia’s Building RAG Agents with LLMs

b) Google’s Cloud Skills Boost course

c) LLamaIndex Understanding RAG

301 - In depth explorations

• Blogs

  • Systematically Improving Your RAG blog
  • LLMs and Graphs Part 1 blog
  • LLMs and Graphs Part 2 blog

• OpenRAG paper

• Output Evaluation paper

• Data to SQL paper

• ReACT paper

• ReWoo paper

• Tree retrievals

  • Raptor Tree retrieval paper
  • RAGFlow github repo

• Knowledge graphs

  • KG Retriever paper

  • GraphRAG Survey paper

  • Microsoft GraphRag

    • Intro - blog
    • Github repo

  • Fast GraphRAG github repo

  • LightRAG github repo

  • NanoGraph github repo

  • GraphDB backends

    • Neo4j NaLLM github repo

• HippoRAG (graph + pagerank)

  • HippoRAG github repo
  • HippoRAG paper

• Interleaving Retrieval with Chain-of-Thought Reasoning

  • IRCoT github repo
  • IRCoT paper

• Memory based RAG

  • Paper at arxiv
  • MemoRAG github repo

• File document processing

  • WDoc github repo
  • Paperless-NGX docs
  • Docling github repo

• ReRank

  • FlashRank github repo

• Code Search

  • Sourcegraph website

• Frameworks: UI/API

  • RAG to Riches
    • R2R github repo
    • R2R Docs website
  • Doc Chat with UI
    • Kotaemon github repo
  • Timescale PostGreSQL AI github repo

• Collections

  • Retrieval LM Papers github repo
  • Awesome RAG github repo
  • Rag Techniques github repo

Semantic search companies

• Glean
• Guru
• Quench/Ollo
• Coveo
• Yext
• BloomFire
• Qatalog