AI-102 Practice Question: Implement natural language processing solutions
A developer is creating a custom question answering project in Azure AI Language. The knowledge base contains product manuals in PDF format. Which step is essential before importing the PDFs?
⚠ Common exam trap
The trap here is that candidates might assume creating an Azure AI Search index is required because custom question answering uses search under the hood, but the Azure AI Language service manages its own index automatically, making Option B a distractor that tests knowledge of Azure AI Language service boundaries.
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
✓
Ensure PDFs are in a supported format and accessible
Before importing PDFs into a custom question answering project in Azure AI Language, the essential step is to ensure the PDFs are in a supported format (e.g., searchable PDF, not scanned images without OCR) and accessible via a valid URL or local path. This is because the import process relies on the service being able to read and extract text from the documents; unsupported or inaccessible files will cause the import to fail.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Ensure PDFs are in a supported format and accessible
Why this is correct
Azure AI Language's question answering ingestion accepts PDFs only when they are text-based and within size and page limits; scanned image-only files must be converted first. Ensuring supported formatting and accessible storage satisfies the prerequisite for successful import, since unsupported or inaccessible documents fail extraction before any knowledge base training can begin.
- ✗
Create an Azure AI Search index
Why it's wrong here
Azure AI Search is provisioned automatically as the underlying retrieval layer when the project is created, so manually building an index beforehand is not required. It is tempting because question answering does rely on Azure AI Search, and creating an index manually would be correct when building a separate custom search solution.
- ✗
Deploy a QnA Maker service
Why it's wrong here
QnA Maker is the retired predecessor service; custom question answering is provisioned through Azure AI Language, so no separate QnA Maker deployment is needed. It is tempting because QnA Maker was the original tool for this task, and would have been correct before its deprecation and migration into Azure AI Language.
- ✗
Translate PDFs to English
Why it's wrong here
Translation is unnecessary because Azure AI Language question answering ingests source-language PDFs directly, matching questions in the same language. Translation would be the correct step only when manuals exist in a language your users do not query in and you need cross-language answering.
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 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.