AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A retail company wants to build a knowledge mining solution that indexes product descriptions stored in an Azure SQL Database and makes them searchable through a web application. The descriptions are already plain text. You need to configure Azure AI Search to pull the data into an index with the least effort. What should you create first?
⚠ Common exam trap
The trap here is reaching for enrichment skills or document intelligence when the source data is already structured text that a built-in indexer can ingest directly.
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
✓
An indexer with a data source connection to Azure SQL Database.
Azure AI Search integrates directly with Azure SQL Database through indexers and data source connections. When the source content is already plain text, the indexer can read rows and populate the index without any enrichment skills. This is the least-effort approach and avoids custom code or document extraction models.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A cognitive skillset that applies OCR to each product description.
Why it's wrong here
OCR converts images of text into machine-readable characters. The descriptions already exist as text, so OCR would have no useful input and would not improve indexing. Adding such a skillset increases cost and pipeline complexity without addressing the ingestion requirement.
- ✗
A custom skill that queries the SQL database and writes documents to the index.
Why it's wrong here
A custom skill operates inside an enrichment pipeline and is meant to transform content that is already being processed, not to serve as the primary ingestion mechanism. Building one to connect to SQL and push documents would duplicate capabilities that the built-in SQL indexer already provides, increasing effort and maintenance.
- ✓
An indexer with a data source connection to Azure SQL Database.
Why this is correct
An indexer connects to a supported data source, reads documents, and populates an index. Creating the data source connection to Azure SQL Database and an indexer that targets the index is the standard low-effort way to ingest plain text records. No enrichment skills are needed because the content is already machine-readable.
- ✗
An Azure AI Document Intelligence model trained on the product descriptions.
Why it's wrong here
Document Intelligence extracts fields from forms and documents using layout and OCR analysis. The product descriptions are already plain text in a database, so there is nothing to extract. Training a model would add unnecessary cost and complexity and would not directly populate the search index.
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 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.