Introduction: RAG & Retrieval

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 that writes text, such as an answer to a question. It learned from a very large amount of text.
• Token: The unit of text an LLM reads and writes. In English, one token is about three-quarters of a word on average.
• Context window: The largest number of tokens an LLM can handle in one request. The instructions, the question, any added evidence, and the answer must all fit inside it.