Free CERTIFIED-GENERATIVE-AI-ENGINEER-ASSOCIATE Databricks CERTIFIED-GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Test Question - Page 2

Question 4 (Topic 1)

A Generative AI Engineer is deciding between using LSH (Locality Sensitive Hashing) and HNSW (Hierarchical Navigable Small World) for indexing their vector database. Their top priority is semantic accuracy. Which approach should the Generative AI Engineer use to evaluate these two techniques?

Select an option, then click Submit answer.

○ Compare the cosine similarities of the embeddings of returned results against those of a representative sample of test inputs
○ Compare the Bilingual Evaluation Understudy (BLEU) scores of returned results for a representative sample of test inputs
○ Compare the Recall-Oriented-Understudy for Gisting Evaluation (ROUGE) scores of returned results for a representative sample of test inputs
○ Compare the Levenshtein distances of returned results against a representative sample of test inputs

Question 5 (Topic 1)

Generative AI Engineer is helping a cinema extend its website’s chat bot to be able to respond to questions about specific showtimes for movies currently playing at their local theater. They already have the location of the user provided by location services to their agent, and a Delta table which is continually updated with the latest showtime information by location. They want to implement this new capability in their RAG application. Which option will do this with the least effort and in the most performant way?

Select an option, then click Submit answer.

○ Create a Feature Serving Endpoint from a FeatureSpec that references an online store synced from the Delta table. Query the Feature Serving Endpoint as part of the agent logic / tool implementation.
○ Query the Delta table directly via a SQL query constructed from the user’s input using a text-to-SQL LLM in the agent logic / tool implementation.
○ Set up a task in Databricks Workflows to write the information in the Delta table periodically to an external database such as MySQL and query the information from there as part of the agent logic / tool implementation.
○ Write the Delta table contents to a text column, then embed those texts using an embedding model and store these in the vector index. Look up the information based on the embedding as part of the agent logic / tool implementation.

Reference / correct answer:

Query the Delta table directly via a SQL query constructed from the user’s input using a text-to-SQL LLM in the agent logic / tool implementation.

Most accepted answer: B. Query the Delta table directly via a SQL query constructed from the user’s input using a text-to-SQL LLM in the agent logic / tool implementation.

Community votes: A=2, B=2

Selected Answer: B The most efficient and effective path is to query the source of truth directly. upvoted 1 times

Selected Answer: A Online Feature Store syncs live from Delta table → always up-to-date upvoted 3 times

Selected Answer: B This scenario describes: A RAG (Retrieval-Augmented Generation) application. A Delta table that is continuously updated with showtimes by location. The agent already knows the user’s location. The engineer wants the simplest and most performant way to query fresh data. Why Option B is correct Querying the Delta table directly is: Low effort — the data already exists in Databricks. Real-time — Delta is always up to date. Performant — optimized storage and indexing under the hood. Easy integration. upvoted 2 times

Selected Answer: A Feature Serving Endpoint with Online Store: This approach is specifically designed for providing low-latency access to feature data in real-time. The cinema's continuously updated showtime data can be synced from the Delta table to an online store, such as the Databricks Feature Store's online store. upvoted 4 times

Question 6 (Topic 1)

Generative AI Engineer is building a RAG application that answers questions about technology-related news articles. The source documents may contain a significant amount of irrelevant content, such as advertisements, sports news, or entertainment news. Which approach is NOT advisable for building a RAG application focused on answering technology-only questions?

Select an option, then click Submit answer.

○ Include in the system prompt that the application is not supposed to answer any questions unrelated to technology.
○ Filter out irrelevant news articles in the retrieval process.
○ Keep all news articles because the RAG application needs to understand non-technological content to avoid answering questions about them.
○ Filter out irrelevant news articles in the upstream document database.

Free CERTIFIED-GENERATIVE-AI-ENGINEER-ASSOCIATE – Databricks CERTIFIED-GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Test Question