AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
You are building an Azure AI Search knowledge mining pipeline that enriches scanned PDF invoices. The PDFs are stored in Azure Blob Storage, and you need to extract text from each page before running downstream entity recognition. The solution must minimize development effort and rely on a built-in cognitive skill. Which skill should you add to the skillset?
⚠ Common exam trap
The trap here is assuming any cognitive skill that produces text can read scanned images, when only the OCR skill performs image-to-text extraction.
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
✓
OcrSkill
The pipeline must convert image-based invoice content into text before any language skill can run. OcrSkill is the built-in Azure AI Search cognitive skill designed for that conversion and outputs a text field that downstream skills consume. Image analysis, entity recognition, and key phrase extraction all assume text already exists, so they cannot satisfy the extraction requirement on their own.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
OcrSkill
Why this is correct
OcrSkill is the built-in cognitive skill that extracts text from image files and embedded images in PDFs, producing a text output that downstream skills can consume. In this scenario, the scanned invoices contain image-based text, so OCR is required before entity recognition. It minimizes development effort because no custom code or external endpoint is needed.
- ✗
EntityRecognitionSkill
Why it's wrong here
EntityRecognitionSkill identifies entities such as organizations, locations, and dates from text that already exists in the enrichment tree. It does not extract text from scanned images or PDFs, so it cannot be the first step. Using it alone would leave the invoice content unreadable and the entity output empty.
- ✗
ImageAnalysisSkill
Why it's wrong here
ImageAnalysisSkill extracts visual features such as tags, captions, and faces from images, but it does not perform optical character recognition to produce searchable text. Adding it would not satisfy the requirement to extract text from scanned invoice pages, and downstream entity recognition would still receive no usable text content.
- ✗
KeyPhraseExtractionSkill
Why it's wrong here
KeyPhraseExtractionSkill returns salient phrases from text input, but it requires text to already be present in the enrichment pipeline. It performs no image-to-text conversion, so scanned invoices would produce no meaningful key phrases. This skill is useful after OCR, not instead of it.
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.