From the course: GraphRAG Essential Training

Unlock this course with a free trial

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

Introduction to Retrieval-Augmented Generation (RAG)

Introduction to Retrieval-Augmented Generation (RAG) - Neo4j Tutorial

From the course: GraphRAG Essential Training

Start my 1-month free trial Buy for my team

Introduction to Retrieval-Augmented Generation (RAG)

“

- [Instructor] RAG is a two-step process. First, the AI searches for relevant information from a trusted source. Then, it crafts a response based on what it found, making the output both relevant and accurate. There's practically no limit to the data you can use for RAG. This data can come from PDFs, websites, structured databases, or even real-time APIs. Basically any source that holds the truth AI needs. For example, in this course, we're going to work with graphs as our RAG, and we'll be creating those graphs from unstructured data, like PDF documents. I hope you will see that RAG isn't just cool, it's practical. It makes AI more reliable for things like customer support, research, medical advice, and even coding help. Whenever you need facts plus AI-generated insights, RAG is the way to go. Now that you know what RAG is, we'll explore how to build it using Python, and of course, graphs.

Contents