What does RAG stand for?	Retrieval Augmented Generation
What fundamental problem does RAG aim to solve when using LLMs with large documents?	Getting specific information from a large document into the LLM so it can answer a user's question.
Describe the first, simplest method of using a large document with an LLM.	Placing the entire document text directly into the prompt.
What are two major limitations of putting an entire large document into an LLM prompt?	Reaching hard text limits (causing errors) and reduced LLM effectiveness due to prompt length.
How does RAG improve upon the simple prompt method?	By breaking the document into small chunks and retrieving only the most relevant chunks for the user's question.
Name two key advantages of using RAG.	Focus on relevant content, scalability to large or multiple documents, and smaller prompts (less time/cost).
What is the initial step required when implementing RAG?	A pre-processing step where the document is split into smaller chunks.
What is a major technical challenge associated with RAG implementation?	Increased complexity, requiring a searching mechanism to find relevant chunks.
What is the definition of a "chunk" in the context of RAG?	A small, defined piece of text extracted from a larger document.
Is there a guarantee that the chunks retrieved by RAG will contain all the context needed for the LLM to answer the question?	No.