AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
You are building a knowledge mining solution with Azure AI Search. The solution indexes scanned PDF reports stored in Azure Blob Storage. Each report contains multiple embedded images with text that must be searchable. You have already created a data source, index, and indexer. You need to ensure that text from the embedded images is extracted and mapped to the 'content' field in the index. Which two actions should you perform? (Choose two.)
⚠ Common exam trap
The trap here is assuming that adding an OCR skill alone is sufficient, but without image extraction the OCR skill has no normalized images to process.
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
✓
Enable image extraction by setting the 'imageAction' parameter to 'generateNormalizedImages' in the indexer definition.
To make text from embedded images searchable, you must first extract the images from the documents by setting imageAction to generateNormalizedImages. Then, you add an OCR skill with context /document/normalized_images/* to process each image and output the recognized text. This text can then be mapped to the content field. Without both actions, the OCR skill either has no input or does not run per image.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Enable image extraction by setting the 'imageAction' parameter to 'generateNormalizedImages' in the indexer definition.
Why this is correct
This is correct because imageAction must be set to generateNormalizedImages to create normalized images from embedded images in the document. Without this, the OCR skill has no image inputs to process. The normalized images become available at /document/normalized_images/*, which is the required input path for the OCR skill.
- ✗
Configure the indexer to use the 'text' parsing mode instead of the default 'json' mode.
Why it's wrong here
The parsing mode determines how the indexer interprets the document structure (e.g., JSON vs. text). It does not enable image processing or OCR. Changing parsing mode would not extract text from embedded images; it might even cause errors if the documents are PDFs. The parsing mode is unrelated to image text extraction.
- ✓
Add an OCR skill to the skillset and set its context to /document/normalized_images/*.
Why this is correct
This is correct because the OCR skill extracts text from images. Setting the context to /document/normalized_images/* ensures the skill runs once per image, producing text output that can be mapped to the content field. Without this context, the skill would not process each image individually, and embedded text would be missed.
- ✗
Add an Entity Recognition skill to detect and extract text from images.
Why it's wrong here
Entity Recognition skill identifies entities such as people, organizations, and locations from text. It does not perform optical character recognition and cannot read text from images. Using it would not extract embedded image text; it would only analyze existing text content, which is not the requirement here.
- ✗
Add a Shaper skill that merges all image text into a single string before indexing.
Why it's wrong here
A Shaper skill is used to reshape data into a complex object; it does not perform OCR or merge text from images. It cannot extract text from images, so it would not make embedded image text searchable. While it could be used later to combine outputs, it does not address the core requirement of extracting text from images.
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
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.