Building a Question Answering Solution from PDFs Using Azure AI Language
You need to build a solution that can answer questions based on a set of PDF documents, such as product manuals. The solution should allow users to ask questions in natural language and receive answers with citations. Which Azure AI service should you use?
Quick Answer
The correct choice is Azure AI Custom Question Answering, because it is the only service within Azure AI Language specifically designed to ingest PDF documents and other source files to create a knowledge base that returns direct, natural language answers along with citation evidence. This service uses a deep-learning-based extractive model to locate the precise answer span within the source text, then surfaces the supporting document excerpt as a citation. On the AI-102 exam, this scenario tests your understanding of the distinction between search and question answering: Azure Cognitive Search retrieves ranked documents but does not generate a concise answer, while Custom Question Answering is built for conversational Q&A. A common trap is confusing Form Recognizer’s text extraction or Text Analytics’ entity recognition with the answer-generation capability. Remember the memory tip: “Custom QA gives you the answer and the proof; search only gives you the map.”
⚠ Common exam trap
Candidates often confuse Azure Cognitive Search's document retrieval capability with the extractive QA and citation features of Custom Question Answering, assuming that a search engine alone can provide direct answers with citations without additional AI processing.
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
✓
Azure AI Custom Question Answering
Azure AI Custom Question Answering (part of Azure AI Language) is specifically designed to extract question-answer pairs from semi-structured content like PDFs and provide answers with citations. It uses a deep learning-based extractive QA model that can locate answer spans within documents and return the source text as a citation, directly meeting the requirement for natural language questions and cited answers from product manuals.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure AI Text Analytics
Why it's wrong here
Analyzes sentiment, key phrases, etc., not question answering.
- ✗
Azure Cognitive Search
Why it's wrong here
Returns search results, not direct answers with citations.
- ✓
Azure AI Custom Question Answering
Why this is correct
Builds a knowledge base from documents and provides answers with citations.
- ✗
Azure AI Document Intelligence (formerly Form Recognizer)
Why it's wrong here
Extracts structured data, does not answer questions.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 945 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 →
Same concept, more angles
1 more way this is tested on AI-102
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A company is implementing a question-answering system using Azure AI Language Service. They have a set of FAQ documents in PDF format. Which feature should they use to automatically generate question-answer pairs?
medium- A.Key Phrase Extraction
- B.Extractive Summarization
- ✓ C.Custom Question Answering
- D.Conversational Language Understanding
Why C: Custom Question Answering (C) is the correct feature because it is specifically designed to ingest semi-structured content like FAQ PDFs and automatically generate question-answer pairs. It uses a built-in extraction pipeline that parses the document structure (e.g., headings, bullet points) to identify likely questions and their corresponding answers, which can then be reviewed and refined in the Azure Language Studio portal.
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.