Plan and manage an Azure AI solution →easyMultiple ChoiceObjective-mapped

AI-102 Plan and manage an Azure AI solution Practice Question

Exhibit

{
  "properties": {
    "description": "My custom skill",
    "type": "Custom.WebApiSkill",
    "context": "/document",
    "inputs": [
      {
        "name": "text",
        "source": "/document/content"
      }
    ],
    "outputs": [
      {
        "name": "entities",
        "targetName": "entities"
      }
    ],
    "uri": "https://myfunctionapp.azurewebsites.net/api/extract-entities",
    "httpMethod": "POST",
    "timeout": "00:00:30",
    "batchSize": 1,
    "degreeOfParallelism": 10
  }
}

Refer to the exhibit. You have an Azure AI Search skillset with the custom skill shown. When you run the indexer, you notice that many documents fail with a timeout error. What is the most likely cause of the timeouts?

⚠ Common exam trap

Microsoft often tests the misconception that timeouts are always caused by a short timeout value or large batch size, but here the trap is that the `degreeOfParallelism` setting is the hidden culprit that overwhelms the function, not the batch size or timeout duration.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

The degreeOfParallelism is set too high, overwhelming the Azure Function.

The custom skill in Azure AI Search is configured with a `degreeOfParallelism` of 10, meaning up to 10 concurrent requests are sent to the Azure Function. If the function cannot handle this level of concurrency (e.g., due to limited resources or cold starts), requests will queue up and eventually time out. Reducing the `degreeOfParallelism` would throttle the load and prevent the function from being overwhelmed.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
The HTTP method should be GET instead of POST.
Why it's wrong here
POST is the correct method for sending input data; GET would not work.
✗
The timeout value is too short for the function to complete.
Why it's wrong here
30 seconds is the maximum allowed; increasing it is not possible beyond that limit.
✓
The degreeOfParallelism is set too high, overwhelming the Azure Function.
Why this is correct
High parallelism can cause the function to throttle, leading to timeouts.
✗
The batch size is too large, causing each request to process too many documents.
Why it's wrong here
Batch size is 1, so each request handles a single document.

Go deeper

AI-102 Plan and manage an Azure AI solution Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question