Introduction: RAG & Retrieval

Look It Up First, Then Answer

Retrieval-augmented generation (RAG) is a simple idea.

Before the model answers, the system searches your documents. It finds the most relevant passages. It hands those passages to the model. The model answers from them.

Look it up first. Then write the answer.

RAG is a common design for products that need information beyond the model's training data. It is useful practice for questions about document assistants and knowledge search.

Here is why.