Implement knowledge mining and information extraction solutions →hardMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

Exhibit

Refer to the exhibit.

{
  "name": "my-skillset",
  "description": "Custom skillset",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Text.SplitSkill",
      "context": "/document",
      "textSplitMode": "pages",
      "maximumPageLength": 5000,
      "defaultLanguageCode": "en",
      "inputs": [
        { "name": "text", "source": "/document/content" }
      ],
      "outputs": [
        { "name": "textItems", "targetName": "pages" }
      ]
    },
    {
      "@odata.type": "#Microsoft.Skills.Text.V3.SentimentSkill",
      "context": "/document/pages/*",
      "defaultLanguageCode": "en",
      "inputs": [
        { "name": "text", "source": "/document/pages/*" }
      ],
      "outputs": [
        { "name": "sentiment", "targetName": "sentiment" }
      ]
    }
  ]
}

You are reviewing a skillset definition for an Azure AI Search indexer. The indexer is configured to index 1000 PDF documents. After running the indexer, you notice that only 500 documents have sentiment scores. What is the most likely cause?

⚠ Common exam trap

A common mix-up: candidates assume the issue is with skill ordering or regional availability, but the real cause is the misalignment of skill context and input/output mappings, which is a subtle but critical detail in skillset definitions.

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 SplitSkill outputs are not correctly mapped to the SentimentSkill input; the skill runs only on the first page of each document

The SplitSkill divides each PDF into pages, and by default the SentimentSkill runs in the context of each page (e.g., /document/pages/*). If the SplitSkill outputs are not correctly mapped to the SentimentSkill input, the sentiment skill may only process the first page or fail to receive the split content, resulting in sentiment scores for only a subset of documents. Correct mapping ensures that each page's content is passed to the SentimentSkill for analysis.

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 skills are defined in the wrong order; sentiment should run before split
Why it's wrong here
Sentiment needs text; split must come first.
✗
The SentimentSkill is not supported in this region
Why it's wrong here
SentimentSkill is available globally.
✓
The SplitSkill outputs are not correctly mapped to the SentimentSkill input; the skill runs only on the first page of each document
Why this is correct
The context "/document/pages/*" should iterate over pages, but if split output is only one item, it only processes one page.
✗
The context of the SentimentSkill should be "/document" instead of "/document/pages/*"
Why it's wrong here
Context "/document/pages/*" is correct for per-page sentiment.

Go deeper

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question