AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are extracting text from scanned documents that are in French. Which capability of Azure AI Document Intelligence should you use?
⚠ Common exam trap
It's easy for candidates to confuse the Read API with the Layout model, assuming that structural analysis is required for text extraction, but the Read API is the dedicated OCR solution for plain text extraction from scanned documents.
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
✓
Read API
The Read API is the correct choice because it is specifically designed for extracting printed and handwritten text from scanned documents, including support for multiple languages like French. It performs optical character recognition (OCR) to digitize text without requiring any additional training or customization, making it ideal for general text extraction from scanned documents.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Custom model
Why it's wrong here
A custom model extracts fields defined by your own labelled samples, so it cannot read arbitrary French text from scanned pages. It is tempting because custom models suit domain-specific forms with fixed layouts. The scenario needs the prebuilt read model, which returns printed text across languages without training.
- ✓
Read API
Why this is correct
The Read API performs OCR and extracts printed and handwritten text, including French, from scanned documents without needing language-specific training. It satisfies the stem's requirement for extracting text from scanned French documents, unlike custom or prebuilt models that target structured fields.
- ✗
Layout model
Why it's wrong here
The layout model extracts text and structural elements such as tables, selection marks and paragraphs, but it does not perform language-specific recognition for French scanned content. It suits documents where structure matters, not multilingual OCR. The read model, by contrast, handles printed and handwritten text across languages, making it the fit here.
- ✗
Prebuilt invoice model
Why it's wrong here
The prebuilt invoice model extracts structured fields from invoices, not free-form text, and its OCR is tuned to invoice layouts rather than arbitrary scanned pages. It is tempting because it does read French documents, but it would be correct only when parsing invoice-specific fields such as totals and vendor details.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.