A company wants to serve a generative AI application that uses a Foundation Model API. They need to ensure that the endpoint is secure and only accessible within their VNet. Which deployment option should they choose?

Deploy the model as a Databricks job that runs on a schedule.

Use a Databricks notebook as a webhook.

Deploy the model using Databricks Model Serving with VNet injection.

Use a Databricks SQL warehouse to serve the model.

In a pyfunc model used for a chain, where should the code that converts the model's raw output into a user-friendly format be placed?

In the predict() method, after calling the underlying model

DatabricksCertified Generative AI Engineer Associate

Domain 4Objective 2

Develop and Deploy LLM 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 14 practice questions to prepare you well beyond it. (estimate)

14questions here

3free pages

4concepts

Questions 6–10

6foundation · easy
A team wants to serve an LLM application that calls a Foundation Model API on Databricks. Which Databricks feature is designed to expose the application as a REST API endpoint for real-time inference?
Select an answer first
7foundation · easy
A data engineer needs to run an LLM inference on a large dataset stored in a Delta table, where each row contains a text prompt. Which Databricks SQL function is designed to call a Foundation Model API for each row in a batch?
Select an answer first
8application · medium
A company wants to serve a generative AI application that uses a Foundation Model API. They need to ensure that the endpoint is secure and only accessible within their VNet. Which deployment option should they choose?
Select an answer first
9foundation · easy
A data scientist is building a custom MLflow model to serve as a chain that first normalizes raw text input, then passes it to a language model, and finally formats the output as JSON. Which MLflow model flavor should they use to define this chain with pre-processing and post-processing logic?
Select an answer first
10foundation · easy
In a pyfunc model used for a chain, where should the code that converts the model's raw output into a user-friendly format be placed?
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.

Develop and Deploy LLM Applications GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 2)

Questions 6–10

A team wants to serve an LLM application that calls a Foundation Model API on Databricks. Which Databricks feature is designed to expose the application as a REST API endpoint for real-time inference?

A data engineer needs to run an LLM inference on a large dataset stored in a Delta table, where each row contains a text prompt. Which Databricks SQL function is designed to call a Foundation Model API for each row in a batch?

A company wants to serve a generative AI application that uses a Foundation Model API. They need to ensure that the endpoint is secure and only accessible within their VNet. Which deployment option should they choose?

A data scientist is building a custom MLflow model to serve as a chain that first normalizes raw text input, then passes it to a language model, and finally formats the output as JSON. Which MLflow model flavor should they use to define this chain with pre-processing and post-processing logic?

In a pyfunc model used for a chain, where should the code that converts the model's raw output into a user-friendly format be placed?

Keep studying — Section 4: Assembling and Deploying Applications