What does RAG stand for?	Retrieval Augmented Generation.
What is the primary limitation of feeding an entire large document into a single prompt?	It hits hard limits on text length, reduces the LLM's effectiveness, and increases processing time/cost.
What is the first step in the RAG process?	Breaking the large document into smaller chunks.
How does RAG improve upon simply pasting a document into a prompt?	It retrieves only the chunks of text most relevant to the user's question, focusing the LLM's attention.
Name two major upsides of using RAG.	It allows the system to scale to very large documents and leads to smaller, less costly prompts.
What is a significant downside or challenge associated with implementing RAG?	It requires a complex pre-processing step and a searching mechanism to find relevant chunks.
What is the risk when using RAG to retrieve chunks?	There is no guarantee that the retrieved chunks will contain all the context needed for a complete answer.
How can text be chunked in a document?	By dividing it into equal portions or by using document headers/structure.