AI-102 Plan and manage an Azure AI solution Practice Question
You are deploying a custom Azure AI Language question answering project. The solution must only answer questions based on a specific set of internal FAQ documents. Which data source type should you use when creating the project?
⚠ Common exam trap
It's easy for candidates to confuse the data source types for creating a custom project with the broader integration options (like Cognitive Search or SQL), leading them to select a wrong option that is technically possible but not the correct data source type for the initial project creation.
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
✓
URLs or files containing FAQ content
Azure AI Language custom question answering is designed to ingest structured FAQ content from URLs or files. When you create a custom project, selecting 'URLs or files containing FAQ content' as the data source type allows the service to automatically extract question-answer pairs from the provided documents, ensuring the solution only answers questions based on that specific set of internal FAQs.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
URLs or files containing FAQ content
Why this is correct
Custom question answering grounds answers strictly in supplied content, so URLs or files containing FAQ content constrain the knowledge base to those internal documents. This satisfies the requirement that responses derive only from the specified FAQ set, excluding general or external knowledge.
- ✗
Prebuilt model from Azure AI Language
Why it's wrong here
A prebuilt model answers from its own trained domain knowledge, not from your internal FAQ documents, so it cannot restrict answers to that set. The scenario requires importing those documents. Prebuilt models suit general, out-of-the-box question answering where no custom document grounding is needed.
- ✗
Azure SQL Database with a QnA Maker schema
Why it's wrong here
Azure SQL Database with a QnA Maker schema requires an existing database populated in that legacy schema, which the scenario does not provide. The FAQ documents must be imported directly. This source suits migrating an existing QnA Maker knowledge base already stored in SQL, not ingesting raw documents.
- ✗
Azure Cognitive Search index
Why it's wrong here
An Azure Cognitive Search index supplies its own indexed content, so answers would come from that index rather than the specified FAQ documents. The scenario requires importing those documents directly. A Cognitive Search index is the right source when answers must be drawn from an existing search index you already maintain.
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.