A data scientist has logged a custom PyFunc model with a preprocessing artifact and wants to register it in Unity Catalog. Which MLflow API is used to register the model to a specific catalog and schema?

mlflow.models.register(model_uri="runs:/ /model", name="catalog.schema.model_name")

mlflow.client.register_model(model_uri="runs:/ /model", name="catalog.schema.model_name")

mlflow.register_model(model_uri="runs:/ /model", name="catalog.schema.model_name")

mlflow.pyfunc.register_model(model_uri="runs:/ /model", name="catalog.schema.model_name")

A team has a custom PyFunc model that requires a large vocabulary file for text preprocessing. They have logged the model with the vocabulary as an artifact. When they deploy the model to Model Serving, how does the serving environment access this artifact?

The artifact is automatically loaded from the model's artifact store when the model is loaded.

The artifact is embedded in the model's code and does not need separate loading.

The artifact must be downloaded at runtime from an external URL.

The artifact must be manually uploaded to the serving endpoint's storage.

A custom PyFunc model has been deployed to a Databricks Model Serving endpoint. A developer needs to query the endpoint programmatically from a Python script. Which MLflow Deployments SDK method is used to send an inference request?

client.request(endpoint="my_endpoint", body={"data": [[1, 2, 3]]})

client.invoke(endpoint="my_endpoint", payload={"data": [[1, 2, 3]]})

client.query(endpoint="my_endpoint", data={"data": [[1, 2, 3]]})

client.predict(endpoint="my_endpoint", inputs={"data": [[1, 2, 3]]})

A data scientist has deployed a custom PyFunc model that returns a dictionary with multiple outputs. They want to call it from a notebook using the MLflow Deployments SDK. What format should the input data be in?

A list of strings representing the feature names.

A pandas DataFrame or a JSON-serializable object that matches the model's expected input.

A developer needs to query a custom model deployed on Databricks Model Serving from a Python application. They have installed the MLflow Deployments SDK. What is the correct way to create a client and call the model?

Use mlflow.pyfunc.load_model to load the model from the endpoint.

Use mlflow.client.MlflowClient to call the endpoint.

Use mlflow.deployments.get_deploy_client with the Databricks workspace URL, then call predict on the client.

Use mlflow.models.predict to call the endpoint.

DatabricksCertified Machine Learning Professional

Domain 3Objective 2

Custom Model Serving MACHINE-LEARNING-PROFESSIONAL Practice Questions (Page 3)

Part of the Model Deployment domain, which accounts for 12% of the MACHINE-LEARNING-PROFESSIONAL exam. Databricks does not publish an official question count, but from its 120-minute exam (~50–80 total, ~6–10 in this domain), expect 3–5 from this objective — we provide 17 practice questions to prepare you well beyond it. (estimate)

17questions here

4free pages

3concepts

12%of the exam

Questions 11–15

11foundation · easy
A data scientist has logged a custom PyFunc model with a preprocessing artifact and wants to register it in Unity Catalog. Which MLflow API is used to register the model to a specific catalog and schema?
Select an answer first
12application · medium
A team has a custom PyFunc model that requires a large vocabulary file for text preprocessing. They have logged the model with the vocabulary as an artifact. When they deploy the model to Model Serving, how does the serving environment access this artifact?
Select an answer first
13foundation · easy
A custom PyFunc model has been deployed to a Databricks Model Serving endpoint. A developer needs to query the endpoint programmatically from a Python script. Which MLflow Deployments SDK method is used to send an inference request?
Select an answer first
14application · medium
A data scientist has deployed a custom PyFunc model that returns a dictionary with multiple outputs. They want to call it from a notebook using the MLflow Deployments SDK. What format should the input data be in?
Select an answer first
15application · medium
A developer needs to query a custom model deployed on Databricks Model Serving from a Python application. They have installed the MLflow Deployments SDK. What is the correct way to create a client and call the model?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MACHINE-LEARNING-PROFESSIONAL

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-PROFESSIONAL” is a trademark of its owner, used for identification only.