RAG (Retrieval Augmented Generation)

RAG combines a language model with a retrieval system. Instead of relying only on what the model learned during training, it searches a database of documents at query time and adds the most relevant results to the prompt as context. The model then generates a response grounded in that retrieved information. This significantly reduces hallucination for factual questions and keeps answers up to date.

Videos explaining this concept

E020

Notes on AI

Why Long Chats Get Confused

The LLM inside a chatbot has no memory. Every response is generated fresh from the same frozen trained model -- it doesn't retain anything between responses and doesn't become smarter as you chat. ...