A team has deployed a model endpoint and wants to monitor its health and performance over time. They need to see metrics such as request latency, error rates, and traffic volume. What should they use?

Enable verbose logging on the endpoint and parse the logs manually.

Use the MLflow tracking server to log metrics from the endpoint.

Databricks model serving endpoint metrics available in the Databricks UI and through the REST API.

Set up a separate Prometheus server and scrape the endpoint's metrics endpoint.

A team has a custom model that requires a specific Python package version that is not in the default Databricks runtime. They want to deploy it to a model endpoint. What should they do?

Log the model with MLflow, ensuring the conda environment includes the required package version, and then deploy that model version.

Modify the Databricks runtime to include the package globally.

Install the package on the cluster that runs the endpoint.

Use a custom Docker image for the endpoint that includes the package.

DatabricksCertified Machine Learning Associate

Domain 4Objective 2

Deploy a Custom Model to a Model Endpoint MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 6)

Part of the Section 4: Model Deployment domain, which makes up ~30% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~11–18 in this domain), expect 2–3 from this objective — we provide 27 practice questions to prepare you well beyond it. (estimate)

27questions here

6free pages

7concepts

Questions 26–27

26application · medium
A team has deployed a model endpoint and wants to monitor its health and performance over time. They need to see metrics such as request latency, error rates, and traffic volume. What should they use?
Select an answer first
27application · medium
A team has a custom model that requires a specific Python package version that is not in the default Databricks runtime. They want to deploy it to a model endpoint. What should they do?
Select an answer first

Finished these 2 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to MACHINE-LEARNING-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. “MACHINE-LEARNING-ASSOCIATE” is a trademark of its owner, used for identification only.

Deploy a Custom Model to a Model Endpoint MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 6)

Questions 26–27

A team has deployed a model endpoint and wants to monitor its health and performance over time. They need to see metrics such as request latency, error rates, and traffic volume. What should they use?

A team has a custom model that requires a specific Python package version that is not in the default Databricks runtime. They want to deploy it to a model endpoint. What should they do?

Keep studying — Section 4: Model Deployment