AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are building an Azure AI Search knowledge mining pipeline that enriches PDF documents with key phrases. The enrichment must be applied after text extraction and before the data is written to the index. You need to ensure the enriched key phrases are available for downstream skills and are mapped to an index field. Which component of the skillset defines the output of the Key Phrase Extraction skill and its mapping to the index?
⚠ Common exam trap
A common mix-up: candidates confuse the skill's output definition with the indexer's output field mappings, which serve different roles in the enrichment pipeline.
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
✓
The outputs array of the skill definition
The outputs array within a skill definition is where you declare the name of the output and the enriched document node it targets. This makes the enriched data available to later skills and to the indexer's output field mappings. The indexer's outputFieldMappings then connects that enriched node to a specific index field. The context property scopes the skill's input, but does not define its output.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The input parameter of the indexer
Why it's wrong here
Indexers do not have an input parameter that defines skill outputs. The indexer's parameters control runtime behavior such as batch size, max failed items, and parsing modes. Skill outputs are defined within the skillset, not the indexer. Therefore, this option is not relevant to defining the output of a skill and its mapping.
- ✗
The context property of the skill
Why it's wrong here
The context property specifies the portion of the enriched document that a skill operates on, such as /document/pages/*. It does not define the skill's output or its mapping. While context is important for scoping the skill to the correct part of the document, it is not where outputs are declared. Thus, this option is incorrect for defining the output of the Key Phrase Extraction skill.
- ✗
The outputFieldMappings of the indexer
Why it's wrong here
Output field mappings in the indexer map enriched document nodes to index fields, but they do not define the output of an individual skill. They are used after the skillset executes to route enriched data into the index. In this scenario, the skill's output is defined within the skill definition itself, not in the indexer's outputFieldMappings. Therefore, this option does not satisfy the requirement of defining the skill's output.
- ✓
The outputs array of the skill definition
Why this is correct
In an Azure AI Search skillset, each skill has an outputs array that names the output produced by the skill and specifies the target enriched document node. For the Key Phrase Extraction skill, the output is typically named keyPhrases and is mapped to a node like /document/keyPhrases. This definition makes the output available to subsequent skills and to the indexer's outputFieldMappings, which then maps it to an index field. This is the correct place to define the skill's output.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.