Databricks Certified Generative AI Engineer Associate · Free Practice Question Medium
Question 7
A Generative AI Engineer is tasked with building a Vector Search index to handle document queries for a knowledge base. What steps are required to create and query this index?
- A Use embeddings to encode queries but not documents.
- B Preprocess documents, embed them using an embedding model, store the embeddings in a vector store, and use a retriever for queries.
- C Skip preprocessing and store raw document text in a vector store for querying.
- D Use a retrieval model directly on raw documents without embeddings.
Reveal correct answer
Correct answer: B
Explanation
Creating a Vector Search index requires preprocessing, embedding, storing in a vector store, and using retrievers for query handling.A. Incorrect: Both documents and queries must be embedded for semantic alignment during search.
B. Correct: Preprocessing, embedding, and retrieval are essential for building and querying an effective Vector Search index.
C. Incorrect: Without preprocessing, documents may include noise, degrading retrieval quality.
D. Incorrect: Retrievers require embeddings to semantically represent document content for effective search.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
You must be logged in to post a comment.
