Exams / AIF-C01 / RAG, knowledge bases and vector stores / Question 3
AIF-C01 practice question: RAG, knowledge bases and vector stores (3 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.
A software company already runs Amazon Aurora PostgreSQL-Compatible Edition for its product data, and its database team knows it well. It wants to store the embeddings for a new RAG application in a familiar service rather than adopt a new one. Which option meets this need?
Choose one answer.
- AA. Amazon Aurora PostgreSQL-Compatible Edition with the pgvector extension
- BB. Amazon Polly with a custom pronunciation lexicon for each document
- CC. AWS Artifact with a separate compliance report for each embedding
- DD. Amazon Translate with a custom terminology file for each document
Show the answer and explanation
Answer: A
- A. Right: Correct. Aurora PostgreSQL supports pgvector for storing embeddings and running similarity searches, and Bedrock Knowledge Bases can use Aurora as a vector store.
- B. Wrong: Polly turns text into speech. It cannot store or search vectors.
- C. Wrong: Artifact provides AWS compliance documents. It is not a database.
- D. Wrong: Translate converts text between languages. It has no vector storage or search.
Explanation
A vector store holds embeddings and finds the nearest ones to a query vector. On AWS this includes Amazon OpenSearch Service, Amazon Aurora PostgreSQL and Amazon RDS for PostgreSQL with pgvector, Amazon Neptune and others. Reusing a database the team already runs can lower the learning curve and operational effort.
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.