Lesson 121 Quiz: Retrieval-Augmented Generation (RAG)

Question 1

What does RAG primarily combine?

Generative AI with random data generation Information retrieval with generative AI Database administration with image generation Traditional programming with network monitoring

Question 2

Why is document chunking useful in a RAG system?

To make every document identical To remove all metadata from documents To divide documents into useful sections for more precise retrieval To convert documents into database passwords

Question 3

What happens after relevant information is retrieved in a typical RAG workflow?

The application deletes the source documents The retrieved information is supplied to the AI model as context The embedding model is permanently retrained The user is automatically granted access to all documents

Question 4

Which statement about RAG and hallucinations is correct?

RAG completely eliminates hallucinations RAG removes the need for source documents RAG guarantees that every retrieved document is correct RAG can improve grounding but does not guarantee factual accuracy

Question 5

Why are access controls important in a RAG system?

Relevant documents are always safe for every user Vector similarity automatically determines user permissions Access controls ensure users only receive information they are authorized to access Access controls are unnecessary when using embeddings