A developer is building a Python application that uses Azure OpenAI to generate both code and natural language responses. They have deployed a gpt-4o model. What should they use to authenticate API calls?

The deployment name as the API key

The Azure subscription ID as the API key

The API key from the Azure OpenAI resource

A developer needs to deploy a model for a code-generation feature. They have provisioned an Azure OpenAI resource and want to use the Foundry Models deployment page. What must they do to make the model available for API calls?

Create a custom model in Azure Machine Learning and register it in Foundry

Upload the model weights to the Foundry Models catalog

Use the Azure AI Vision service to deploy the model

Select the model, choose a deployment name, and create the deployment

A developer wants to generate a SQL query from a natural language question. They are using Azure OpenAI in Foundry Models. What is the best way to structure the prompt?

Provide only the natural language question without any schema

Use a DALL-E 3 deployment to generate the SQL query

Provide the database schema and the natural language question, and ask for a SQL query

Ask the model to generate an image of the SQL query

Microsoft Certified:Azure AI Engineer Associate

Domain 2Objective 2

Use Azure OpenAI in Foundry Models to Generate Content AI-102 Practice Questions (Page 8)

Part of the Implement generative AI solutions domain, which accounts for 15-20% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~6–13 in this domain), expect 2–4 from this objective — we provide 49 practice questions to prepare you well beyond it. (estimate)

49questions here

10free pages

8concepts

15-20%of the exam

Questions 36–40

36application · easy
A developer is building a Python application that uses Azure OpenAI to generate both code and natural language responses. They have deployed a gpt-4o model. What should they use to authenticate API calls?
Select an answer first
37application · easy
A developer needs to deploy a model for a code-generation feature. They have provisioned an Azure OpenAI resource and want to use the Foundry Models deployment page. What must they do to make the model available for API calls?
Select an answer first
38foundation · easy
Which Azure OpenAI model can accept both text and image inputs?
Select an answer first
39foundation · easy
What is the typical output of a natural language prompt submitted to GPT-4 in Azure OpenAI?
Select an answer first
40application · medium
A developer wants to generate a SQL query from a natural language question. They are using Azure OpenAI in Foundry Models. What is the best way to structure the prompt?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-102

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 Microsoft. “AI-102” is a trademark of its owner, used for identification only.

Use Azure OpenAI in Foundry Models to Generate Content AI-102 Practice Questions (Page 8)

Questions 36–40

A developer is building a Python application that uses Azure OpenAI to generate both code and natural language responses. They have deployed a gpt-4o model. What should they use to authenticate API calls?

A developer needs to deploy a model for a code-generation feature. They have provisioned an Azure OpenAI resource and want to use the Foundry Models deployment page. What must they do to make the model available for API calls?

Which Azure OpenAI model can accept both text and image inputs?

What is the typical output of a natural language prompt submitted to GPT-4 in Azure OpenAI?

A developer wants to generate a SQL query from a natural language question. They are using Azure OpenAI in Foundry Models. What is the best way to structure the prompt?

Keep studying — Implement generative AI solutions