From the course: Developing RAG Apps with LlamaIndex and Next.js

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

RAG crash course

RAG crash course

From the course: Developing RAG Apps with LlamaIndex and Next.js

Start my 1-month free trial Buy for my team

RAG crash course

“

All right, so I'm going to do a very quick crash course on RAG here so we have an understanding of what RAG is. Now, if you already know what RAG is, just look at this as some sort of recap. Okay, so let's go ahead and do this. So what is RAG? So let's go ahead and do a definition because that seems to always be the best way to get started. So RAG, here's a definition, it's a framework that combines the strengths of retrieval-based systems and generation-based models to produce more accurate and contextual relevant response. Well, that's a mouthful, but let's translate this. What does that mean? Well, that just means efficient way to customize our LLM. In this case, our large model model with your own data. So RAG, Retrieval Augmented Generation, presents a solution to the challenge of hallucination, because RAG addresses this by combining the generative power of large language models with an external knowledge retrieval step before generating an answer so I love diagrams and I hope…

Contents