AI-102 Practice Question: Implement knowledge mining and information extraction solutions
Your organization is implementing a knowledge mining solution for a research institute that needs to extract chemical compound names and reactions from scientific articles in PDF format. The solution must use a custom model because the scientific terminology is not covered by built-in skills. You have trained a custom model using Azure AI Language's custom entity recognition (NER) and deployed it as a REST endpoint. You are using Azure AI Search with a skillset. How should you integrate the custom NER model into the enrichment pipeline?
⚠ Common exam trap
The trap is assuming that built-in skills can be customized with a custom endpoint; candidates may choose the built-in Entity Recognition skill, but it does not support custom models.
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
✓
Create a custom skill that calls the custom NER endpoint and map the output to the index fields.
To integrate a custom NER model into an Azure AI Search enrichment pipeline, you must create a custom skill that calls the custom NER endpoint. The custom skill is a web API that the skillset invokes, and it can map the JSON output to index fields. This allows the enrichment pipeline to use the custom model's predictions.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Create a custom skill that calls the custom NER endpoint and map the output to the index fields.
Why this is correct
A custom skill in the skillset invokes the deployed custom NER REST endpoint, passing enriched document text and writing returned entities into index fields. Built-in skills cannot cover the scientific terminology, so wrapping the endpoint as a custom skill is the only integration path.
- ✗
Use a Language Understanding (LUIS) app to extract entities and call it from a custom skill.
Why it's wrong here
LUIS performs intent classification and utterance-level entity extraction, not the document-level custom NER model already trained and deployed. It is tempting because LUIS is a familiar Azure AI service for conversational language tasks, which suits bot intent routing rather than scientific terminology extraction.
- ✗
Use the built-in Entity Recognition skill and configure it with your custom model's endpoint.
Why it's wrong here
The built-in Entity Recognition skill queries Microsoft's fixed pre-trained model and offers no parameter for substituting a custom endpoint. It is tempting because built-in skills require no custom skill scaffolding, which suits scenarios where the pre-trained entity categories already cover the required terminology.
- ✗
Configure the indexer to call the custom NER endpoint directly during indexing.
Why it's wrong here
Indexers cannot invoke a custom NER REST endpoint directly; enrichment requires a skillset skill, such as a custom Web API skill wrapping the endpoint. Direct indexer calls suit built-in field mappings and change detection, so this would only fit if no enrichment pipeline existed.
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 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.