Retrieval Augmented Generation (RAG) has become a popular application of LLMs recently, with significant progress made in just a few months. Its popularity stems from its lightweight nature and the ease with which it can be integrated with any LLM. To help you get acquainted with RAG, we have put together a 3-day learning plan.

This guide will introduce you to the fundamentals, show you how to develop applications, delve into advanced functionalities, and teach you how to assess RAG applications. Plan to spend about 2-3 hours each day on the provided materials.

Happy Learning!

Watch these videos:

1. Explanation of RAG by DeepLearning.AI ( link )

Read these resources:

1. What is RAG by DataStax ( link )
2. Retrieval-Augmented Generation (RAG) from basics to advanced by Tejpal Kumawat ( link )

Watch these videos:

1. Advanced RAG series (6 videos) by Sam Witteveen ( link )
2. LangChain101: Question A 300 Page Book (w/ OpenAI + Pinecone) by Greg Kamradt ( link )

Read these resources:

1. Blog on advanced RAG techniques by Akash ( link )
2. RAG hands-on tutorials on GitHub( link )

Watch these videos:

1. LlamaIndex Sessions: 12 RAG Pain Points and Solutions ( link )
2. Building and Evaluating Advanced RAG Applications by DeepLearning.AI ( link )
3. Challenges with Naive RAG & How to Evaluate RAG Applications? by ActiveLoop ( link )

Read these resources:

1. 12 RAG Pain Points and Solutions article( link )
2. RAGas core concepts for evaluating RAG( link )

1. Week 4 content from Applied LLMs mastery course on RAG ( link )
2. “Seven Failure Points When Engineering a Retrieval Augmented Generation System” paper( link )
3. “Retrieval-Augmented Generation for Large Language Models: A Survey” paper( link )
4. RAG description and available tools on Huggingface( link )
5. Original RAG paper "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks” ( link )