Exam AI-901 Topic 1 Question 9 Discussion
Actual exam question for Microsoft's AI-901 exam
Question #: 9
Topic #: 1
Question #: 9
Topic #: 1
You have a Microsoft Foundry project that contains a vision-enabled model deployment.
You need to develop an application that sends a message containing text and an image URL.
The solution must ensure the quickest response time.
Which message structure should you include in the request?
You need to develop an application that sends a message containing text and an image URL.
The solution must ensure the quickest response time.
Which message structure should you include in the request?
Suggested Answer: D Vote an answer
To achieve the fastest possible response time in Microsoft Foundry/Azure AI, you must combine the text prompt and image URL into a single user message, utilizing a system message for instructions, and opting for a low-latency model like gpt-4o-mini.
Sending separate requests or splitting the text and image into different messages increases network overhead and conversation context length, both of which add unnecessary latency.
Note:
1. Required Message Structure
You should include both a system message and a custom user message in your API request payload:
System Message: Use this to define the context, guardrails, and explicit format requirements. It sets up the model behavior before the image is even processed, optimizing processing efficiency.
User Message (Custom Message): This is where you pass your text prompt and the actual image reference.
2. Request Handling: Single vs. Separate Requests
You must send the text item and the image item in the same single request.
Reference:
https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/transitioning-from-azure-language-features-to-foundry-models/4524092
Sending separate requests or splitting the text and image into different messages increases network overhead and conversation context length, both of which add unnecessary latency.
Note:
1. Required Message Structure
You should include both a system message and a custom user message in your API request payload:
System Message: Use this to define the context, guardrails, and explicit format requirements. It sets up the model behavior before the image is even processed, optimizing processing efficiency.
User Message (Custom Message): This is where you pass your text prompt and the actual image reference.
2. Request Handling: Single vs. Separate Requests
You must send the text item and the image item in the same single request.
Reference:
https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/transitioning-from-azure-language-features-to-foundry-models/4524092
by Nigel at Jul 08, 2026, 05:12 AM
0
0
0
10
Comments
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
Report Comment
Commenting
You can sign-up / login (it's free).