Implement natural language processing solutions →hardMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Refer to the exhibit.

{
  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#",
  "contentVersion": "1.0.0.0",
  "parameters": {
    "sku": {
      "type": "string",
      "defaultValue": "S"
    },
    "location": {
      "type": "string",
      "defaultValue": "[resourceGroup().location]"
    }
  },
  "resources": [
    {
      "type": "Microsoft.CognitiveServices/accounts",
      "apiVersion": "2023-05-01",
      "name": "myLanguageService",
      "location": "[parameters('location')]",
      "sku": {
        "name": "[parameters('sku')]"
      },
      "kind": "TextAnalytics",
      "properties": {
        "customSubDomainName": "mylanguageservice"
      }
    }
  ]
}

You deploy the ARM template above to create an Azure AI Language resource. After deployment, you try to use the custom question answering feature but it is not available. What is the most likely reason?

⚠ Common exam trap

Test-takers frequently assume the feature is missing due to an outdated API version or insufficient SKU, when in fact the root cause is the incorrect resource 'kind' property, which is a subtle but critical distinction in Azure AI resource provisioning.

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 'kind' property is set to 'TextAnalytics', which does not enable custom question answering.

The 'kind' property in the ARM template is set to 'TextAnalytics', which provisions a general-purpose Text Analytics resource. Custom question answering is a feature of the Azure AI Language service that requires the resource to be created with the 'kind' set to 'Language' or 'ConversationalLanguageUnderstanding' (depending on the API version). Because the resource is of the wrong kind, the custom question answering capability is not available, even though the deployment succeeds.

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 apiVersion is too old to support custom question answering.
Why it's wrong here
2023-05-01 supports custom question answering.
✓
The 'kind' property is set to 'TextAnalytics', which does not enable custom question answering.
Why this is correct
TextAnalytics kind does not include custom question answering.
✗
The SKU is set to S, but custom question answering requires a higher SKU.
Why it's wrong here
S SKU supports custom question answering.
✗
The location does not support custom question answering.
Why it's wrong here
Most regions support it.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question