AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are creating an Azure AI Search indexer that processes documents from Azure Blob Storage. The documents include PDFs and images. You need to extract both text and image content, and then use the image content to generate captions via the Image Analysis skill. Which indexer configuration is required to enable image extraction and passing images to the skillset?
⚠ Common exam trap
Many candidates confuse parameters that allow access to file data with those that actually extract and normalize images for skills.
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
✓
Set the imageAction to generateNormalizedImages in the indexer's parameters.
To extract images from documents and make them available for enrichment, you must set the imageAction parameter to generateNormalizedImages in the indexer definition. This extracts images and places them in the enriched document under /document/normalized_images/*. The Image Analysis skill can then use those images as input to generate captions. Other parsing modes or parameters do not enable image extraction for skills.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Set the parsingMode to json.
Why it's wrong here
Parsing mode json is used when the source documents are JSON files, not for extracting images from PDFs or images. It changes how the indexer parses content, but it does not enable image extraction. For image extraction, you need to use the appropriate parsing mode and enable image action. Thus, this option is incorrect.
- ✗
Set the allowSkillsetToReadFileData parameter to true.
Why it's wrong here
The allowSkillsetToReadFileData parameter allows skills to access the raw file data, but it does not extract images or make them available as normalized images. It is used for custom skills that need the original file. For image extraction, imageAction is the correct parameter. Thus, this option is not sufficient.
- ✗
Set the parsingMode to delimitedText and specify a delimiter.
Why it's wrong here
Delimited text parsing is for plain text files with delimiters, such as CSV. It is not used for PDFs or images. This mode does not extract images or text from binary formats. Therefore, it does not meet the requirement of extracting image content for the Image Analysis skill.
- ✓
Set the imageAction to generateNormalizedImages in the indexer's parameters.
Why this is correct
The imageAction parameter in the indexer configuration controls image extraction. Setting it to generateNormalizedImages extracts images from documents and normalizes them, making them available in the enriched document for skills like Image Analysis. This is the correct configuration to enable image content to be passed to the skillset for caption generation.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.