Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation, or RAG, is a way of making an AI model answer from trusted information rather than from memory alone. Before the model writes a reply, a retrieval step searches a collection of documents or records for the passages most relevant to the question and passes them to the model with it.

The model then writes its answer from those passages, and can point to where each fact came from. RAG reduces made-up answers and lets an assistant use private or recent information it was never trained on. Its quality depends on finding the right passages, so the search step matters as much as the model.

For example, an HR assistant asked how many days of leave carry over retrieves the relevant section of the leave policy first, and answers from that text.