Exam AI-102 topic 1 question 62 discussion

Deployment name: This specifies which deployment of the model you want to use. In Azure OpenAI, you might have multiple deployments of the same model optimized for different tasks. Endpoint: This is the URL where your AI1 model is hosted. It directs the API requests to the correct Azure service instance. Key: This is the authentication key that allows your web app to access the Azure OpenAI service securely. It ensures that only authorized applications can use the service. C is the answer

This was in the exam on 15/08/2024

"AI1" is deployment name. https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython-new&pivots=rest-api#retrieve-key-and-endpoint DEPLOYMENT-NAME This value will correspond to the custom name you chose for your deployment when you deployed a model.

C. the deployment name, endpoint, and key . Endpoint should include model name

Correct, remember that Model Name and Type aren't relevant, we only need the deployment details and key.

Correct answer.

Correct. When you access the model via the API you will need to refer to the deployment name rather than the underlying model name in API calls. https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal

To connect to an Azure OpenAI model using the Azure OpenAI SDK, you need to provide: The deployment name of the model that you want to use. This is the name that you assigned to the model when you deployed it. The endpoint of your Azure OpenAI resource. This is the URL that you can find in the Overview section of your resource in the Azure portal or by using the Azure CLI. The key of your Azure OpenAI resource. This is the API key that you can find in the Keys and Endpoint section of your resource in the Azure portal or by using the Azure CLI.

Answer seems to be correct