What is the primary purpose of a vector index in Mosaic AI Vector Search?

To store embeddings and metadata for efficient similarity search

To provide a user interface for managing vector data

To train machine learning models on vector data

To generate embeddings from raw text

A team is deploying a RAG application and needs to log an input example for the MLflow model. The model takes a user query as a string and returns a response. What is the purpose of providing an input example?

It is required to create the Vector Search index schema.

It defines the embedding model's input format.

It is used to train the retriever on the query distribution.

It validates the model signature and provides a sample for testing the served model.

A data science team has deployed a RAG application using Mosaic AI Vector Search. The retriever is returning results, but the relevance of the top documents is poor. The embedding model and index schema are confirmed correct. Which adjustment should the team make first to improve retrieval quality?

Disable the delta-sync on the index to prevent stale embeddings from being used.

Switch to a different Vector Search endpoint type to get faster query responses.

Reduce the number of embedding dimensions in the index schema.

Increase the number of results returned by the query and apply a re-ranking step.

For a vector search solution that requires near-real-time updates to the index, which configuration choice is most appropriate?

Use manual sync to control update timing

Reduce the number of embeddings to speed up updates

Enable Delta Sync for automatic incremental updates

Disable automatic updates to reduce cost

DatabricksCertified Generative AI Engineer Associate

Domain 4Objective 1

Build and Configure RAG Applications GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 2)

Part of the Section 4: Assembling and Deploying Applications domain, which makes up ~11% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~4–7 in this domain), expect 1–2 from this objective — we provide 13 practice questions to prepare you well beyond it. (estimate)

13questions here

3free pages

5concepts

Questions 6–10

6foundation · easy
What is the primary purpose of a vector index in Mosaic AI Vector Search?
Select an answer first
7application · medium
A team is deploying a RAG application and needs to log an input example for the MLflow model. The model takes a user query as a string and returns a response. What is the purpose of providing an input example?
Select an answer first
8foundation · easy
When creating a Vector Search index in Databricks, which of the following must be specified to define the structure of the data that will be indexed?
Select an answer first
9application · medium
A data science team has deployed a RAG application using Mosaic AI Vector Search. The retriever is returning results, but the relevance of the top documents is poor. The embedding model and index schema are confirmed correct. Which adjustment should the team make first to improve retrieval quality?
Select an answer first
10foundation · easy
For a vector search solution that requires near-real-time updates to the index, which configuration choice is most appropriate?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to GENERATIVE-AI-ENGINEER-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “GENERATIVE-AI-ENGINEER-ASSOCIATE” is a trademark of its owner, used for identification only.