AI-300: Operationalizing Machine Learning and Generative AI SolutionsDemo

HOTSPOT -

You manage an Azure Machine Learning workspace named workspace1 by using the Python SDK v2. You create a General Purpose v2 Azure storage account named mlstorage1. The storage account includes a publicly accessible container named mlcontainer1. The container stores 10 blobs with files in the CSV format.

You must develop Python SDK v2 code to create a data asset referencing all blobs in the container named mlcontainer1.

You need to complete the Python SDK v2 code. How should you complete the code?

sample_dataset = Data(
    path=Select…://mlstorage1.blob.core.windows.net/mlcontainer1,
    type=AssetTypes.Select…,
    description="sample_dataset",
    name="sample_dataset",
    version='1.0'
)

A team is validating a generative AI assistant for an organization. The assistant generates responses using internal knowledge sources.

The organization requires assurance that responses are accurate, source-supported, and relevant to user prompts before production access is enabled.

You need to implement quality metrics that verify the assistant produces dependable and meaningful responses.

Which two evaluation metrics should you use? Each correct answer presents part of the solution.

NOTE: Each correct selection is worth one point.

An organization uses Microsoft Foundry to develop generative AI projects that access shared Azure resources, including storage accounts and vector databases.

The organization’s security policy requires eliminating secret key-based authentication and enforcing least-privilege access. Configure identity and access so that:

• Services authenticate without stored credentials.
• Permissions are appropriately scoped across projects and shared resources.

Configure the appropriate identity or access mechanism for each requirement. Each configuration mechanism may be used once, more than once, or not at all.

A team is experimenting with traditional models for a classification workflow in Azure Machine Learning.

The team needs a consistent method to manage assets created during experimentation.

You need to ensure that artifacts can be reused and governed across projects.

Which asset should you register?

A Retrieval-Augmented Generation (RAG) solution produces incomplete answers because relevant content is retrieved inconsistently from the knowledge source.

You need to increase RAG accuracy without changing the embedding model that is currently used. You must meet this goal while minimizing operational costs.

Which two actions should you take? Each correct answer represents part of the solution.

NOTE: Each correct selection is worth one point.