AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
You are designing an Azure AI Search solution that uses an AI enrichment pipeline to extract text and key phrases from scanned documents. You need to ensure the pipeline can process image-heavy PDFs and produce searchable text and key phrases. Which two actions should you include in the skillset? (Choose two.)
⚠ Common exam trap
The trap here is choosing skills that seem related to text analysis but do not actually extract text from images or generate key phrases, such as Language Detection or Entity Recognition.
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
✓
Add the built-in Key Phrase Extraction skill to identify important phrases from the OCR text.
To process image-heavy PDFs, the OCR skill extracts text from embedded images. Once text is available, the Key Phrase Extraction skill identifies important phrases. Together, these skills enable the pipeline to produce searchable text and key phrases. Other skills like Language Detection, Text Merge, or Entity Recognition serve different purposes and do not fulfill both requirements.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Add the built-in Key Phrase Extraction skill to identify important phrases from the OCR text.
Why this is correct
The Key Phrase Extraction skill analyzes text and returns a list of key phrases. Applied after OCR, it operates on the extracted text to surface salient terms, which can be mapped to a collection field in the index. This directly fulfills the requirement to produce key phrases from the scanned documents.
- ✗
Add the built-in Language Detection skill to determine the language of each document.
Why it's wrong here
Language Detection identifies the language of text, which can be useful for routing to language-specific analyzers, but it does not extract text from images or generate key phrases. While it may be a helpful preprocessing step, it alone does not satisfy the need to process image-heavy PDFs and produce searchable text and key phrases.
- ✗
Add the built-in Text Merge skill to combine multiple text inputs into a single field.
Why it's wrong here
The Text Merge skill concatenates text from multiple fields or skills into one, which can be useful for consolidating content. However, it does not perform OCR or key phrase extraction. It is a utility skill and would not by itself enable processing of image-heavy PDFs or generation of key phrases from their content.
- ✗
Add the built-in Entity Recognition skill to extract people, organizations, and locations.
Why it's wrong here
Entity Recognition extracts specific entity types such as people, organizations, and locations. While valuable for knowledge mining, it does not extract general text from images nor produce key phrases. The requirement focuses on making image-heavy PDFs searchable and generating key phrases, which are handled by other skills.
- ✓
Add the built-in OCR skill to extract text from images embedded in the PDFs.
Why this is correct
The OCR skill is specifically designed to recognize text from image files or embedded images in documents. For image-heavy PDFs, it extracts the textual content that would otherwise be inaccessible, enabling subsequent skills and indexing to work on that text. Without OCR, the pipeline would miss text in scanned pages.
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.