Retrieval-augmented generation (RAG) quickly separated itself as one of the most popular ways to leverage large language models (LLMs). Why? Because RAG patches up a critical problem in using LLMs for our own use cases. LLMs are trained on vast amounts of data, but they don’t have access to the specialized data that we need for personal or business use cases, which makes them much more likely to hallucinate an answer. This is where RAG comes in. RAG uses embedding models and vector databases to store your data in a way that it can be used as context for LLMs. This course shows you what the different pieces of an RAG app are, how to use them, and how to build your own RAG app from scratch in Python. This course also leverages GitHub Models to enhance your learning.
Learn More