Azure OpenAI SDK Connection Configuration

AI-103 By islever Editorial Last updated

Set up AI solutions in Foundry

Short answer

C You must provide the deployment name, endpoint, and key to configure App1 to connect to AI1.

Question

You have an Azure OpenAI model named AI1.
You are building a web app named App1 by using the Azure OpenAI SDK.
You need to configure App1 to connect to AI1.
What information must you provide?
  1. the deployment name, key, and model name
  2. the endpoint, key, and model type
  3. the deployment name, endpoint, and key Correct Answer
  4. the endpoint, key, and model name

Key Takeaways

Tests knowledge of Azure OpenAI connection strings, with the common trap being confusion between model names and deployment names.

Configuring an Azure OpenAI web app requires the endpoint, API key, and deployment name. This guide explains why these three credentials are essential for SDK authentication.

Common mistake: Candidates often select options including 'model name' instead of 'deployment name', not realizing that deployments are versioned instances of models.

Expert Analysis

Why the Answer Is Correct

To connect an application to an Azure OpenAI resource using the SDK, you must provide the Azure OpenAI endpoint (the URL), a valid API key for authentication, and the specific deployment name. The deployment name identifies the exact versioned instance of the model you wish to use.

Why the Other Options Are Wrong

Options A, B, and D all include incorrect or missing fields. Model name alone is insufficient because multiple deployments can exist for one model. Model type is irrelevant to the connection string. Endpoint is mandatory in all correct scenarios, which eliminates options lacking it.

Community Comment Notes

Community consensus strongly supports option C. As Amelia233 noted, "When using the Azure OpenAI SDK, you need the endpoint, API key, and the deployment name to connect to the deployed model." Users confirm that model name is not required for the connection setup itself.

Exam Strategy

Memorize the three pillars of Azure AI connection: Endpoint, Key, and Deployment Name. Do not confuse 'Model Name' with 'Deployment Name'.

Frequently Asked Questions

Why isn't the model name required?

The model name defines the architecture, but the deployment name specifies the exact versioned instance running on the server.

Can I use just the API key?

No, the endpoint URL is required to locate the resource, and the deployment name is needed to target the specific model instance.

More AI-103 FAQ →

Discussion 1 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 1

  1. Amelia233 👍 1 Answered C
    When using the Azure OpenAI SDK, you need the endpoint, API key, and the deployment name to connect to the deployed model. A ❌ Model name isn't required; the deployment name identifies the deployed model. B ❌ Model type isn't required. C ✅ Deployment name + endpoint + key. D ❌ Model name is not required. Answer: C

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Which Request Parameters Maximize Foundry Output Stability and Reasoning?

S-grade

Azure Custom Vision: ordered steps to detect factory component faults

S-grade

Improving Agent Response Completeness in Microsoft Foundry

S-grade

Restricting Access to Microsoft Foundry Service via VNet

S-grade

Practice All AI-103 Questions

Access 88 questions with complete answers and detailed explanations.

View Full AI-103 Practice Test →

← Back to AI-103 Study Guide