Courseiva
← PMLE
Full test
hardMultiple ChoiceObjective-mapped

Vertex AI Model Upload: Invalid SavedModel Directory

Network Topology
container-image-uri=us-central1-docker.pkg.dev/my-project/my-repo/model:latest']artifact-uri=gs://my-bucket/artifacts'display-name=my-model'region=us-central1'args: ['ai'endpoint=my-endpoint'model=my-model'region=us-central1']steps:- name: 'gcr.io/cloud-builders/docker'args: ['build', '-t', 'us-central1-docker.pkg.dev/my-project/my-repo/model:latest', '.']args: ['push', 'us-central1-docker.pkg.dev/my-project/my-repo/model:latest']- name: 'gcr.io/cloud-builders/gcloud'entrypoint: 'gcloud'id: 'deploy-model'

Refer to the exhibit. A team uses this Cloud Build configuration to deploy a model to a Vertex AI endpoint. The build succeeds up to the 'upload' step, but the 'deploy-model' step fails with an error that the model 'my-model' does not exist. What is the most likely cause?

Quick Answer

The answer is that the model was not uploaded because the artifact URI points to a directory, not a valid SavedModel. Cloud Build’s upload step specifically requires a SavedModel artifact—a directory containing a saved_model.pb file and a variables subdirectory. If the URI leads to a generic folder or an incorrectly structured directory, the upload may complete without error but fails to register a usable model resource, causing the subsequent deploy step to fail with a “model does not exist” error. On the Google Professional Machine Learning Engineer exam, this scenario tests your understanding of Vertex AI’s model upload requirements and the distinction between a successful build step and a valid artifact. A common trap is assuming any directory will work, when in fact the SavedModel format is strictly enforced. Memory tip: think “pb + variables = valid SavedModel”; if either is missing, your model is missing.

⚠ Common exam trap

Google Cloud often tests the distinction between a successful upload step and a valid model registration, trapping candidates who assume any directory upload creates a usable model resource.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

The model was not uploaded because the artifact URI is a directory, not a valid SavedModel

The 'deploy-model' step fails because the model was not successfully uploaded. Cloud Build's 'upload' step expects a valid SavedModel artifact (a directory containing a saved_model.pb file and variables subdirectory). If the artifact URI points to a directory that is not a valid SavedModel, the upload may appear to succeed but does not register a usable model resource, causing the subsequent deploy step to fail with 'model does not exist'.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • ✗

    The deploy step uses the display name instead of the model resource ID

    Why it's wrong here

    While possible, Vertex AI can resolve display names to resource IDs in deploy-model commands.

  • ✓

    The model was not uploaded because the artifact URI is a directory, not a valid SavedModel

    Why this is correct

    The artifact URI must point to a specific model file or subdirectory, not a generic directory.

  • ✗

    The Vertex AI API was not enabled for the project

    Why it's wrong here

    If the API were disabled, the upload would have failed earlier.

  • ✗

    The region in the deploy step does not match the model's region

    Why it's wrong here

    Both steps use us-central1, so region is consistent.

About these practice questions

This PMLE question is part of Courseiva's 990-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

Same concept, more angles

1 more way this is tested on PMLE

These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.

Variation 1. Refer to the exhibit. A team runs this command to upload a model to Vertex AI. They want to create this model as a new version under an existing model named 'my_model'. What is missing from the command?

easy
  • A.--description='Second version'
  • B.--version=v2
  • C.--labels=team=ml
  • D.--service-account=sa@project.iam.gserviceaccount.com
  • ✓ E.--parent-model=my_model

Why E: The `--parent-model` flag is required when uploading a new model version to an existing model in Vertex AI. Without specifying the parent model name, the command would attempt to create a brand-new model rather than adding a version to the existing 'my_model'. The `gcloud ai models upload` command uses this flag to associate the new version with the specified parent model.

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.