The RAG Pipeline

Know the Vocabulary

This lesson uses the terms below many times. Read them once now, and come back here when a later section needs one.

• RAG (retrieval-augmented generation): A design that first finds relevant passages in your own documents, then asks a large language model (LLM) to answer from them.
• Corpus: The full set of documents the system can search, stored as chunks.
• Chunk: A focused passage cut from a document, usually a few hundred words or fewer. It is the unit that retrieval works with.