Exams / AIF-C01 / RAG, knowledge bases and vector stores / Question 2
AIF-C01 practice question: RAG, knowledge bases and vector stores (2 of 4)
Applications of Foundation Models A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.
An airline wants its customer assistant to answer questions using its baggage and refund policies, which change most weeks. It wants answers based on the current documents, with citations, and does not want to retrain a model each time. Which approach fits BEST?
Choose one answer.
- AA. Pre-train a new foundation model on the policies every week
- BB. Use RAG with Amazon Bedrock Knowledge Bases over the policies
- CC. Raise the model's temperature so it explores more possible policies
- DD. Fine-tune the model once on last year's policy documents
Show the answer and explanation
Answer: B
- A. Wrong: Pre-training is the most expensive way to add knowledge, and it would still be out of date between runs.
- B. Right: Correct. RAG retrieves the latest documents at query time, adds them to the prompt and can include citations.
- C. Wrong: Temperature changes randomness. It cannot give the model knowledge of documents it has never seen.
- D. Wrong: A one-off fine-tune would quickly go out of date as the policies change weekly.
Explanation
Retrieval Augmented Generation grounds a model's answer in data retrieved at query time. Amazon Bedrock Knowledge Bases manages ingestion, retrieval and prompt augmentation, and can return citations. Updating the documents updates the answers, with no retraining.
Study
Keep practising
Answer questions with a score at the end, or practise just this topic with the explanation after each one. No sign-up needed.