RAG (Retrieval Augmented Generation)

Retrieval Augmented Generation (RAG) is the technique that makes AI actually know things it was not trained on. The recipe: (1) take the user's question, (2) search a database of documents for relevant chunks, (3) feed those chunks into the model as context, (4) the model answers using both its training AND the retrieved info. Every "chat with your documents" product is RAG. Every enterprise AI assistant answering questions about company data is RAG. Critical for grounded, citeable answers — the model is reading real sources, not hallucinating from training data. RAG is what makes Perplexity, NotebookLM, Glean, and most enterprise chatbots work.