Keeping Answers Grounded

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.

• Large language model (LLM): A model trained on a very large amount of text that writes text, such as an answer to a question.
• Retrieval-augmented generation (RAG): A design in which the system first finds relevant passages in its documents. It then gives them to the LLM with the question.
• Context: All the text the LLM receives with one request: the instructions, the retrieved chunks, and the question.