AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You have an Azure AI Search indexer that enriches documents with a custom skill that calls an external API. The custom skill returns a JSON object containing a list of product codes. You need to store these product codes in a collection field named 'productCodes' in the index, and you want the field to be searchable and filterable. What should you do?
⚠ Common exam trap
The trap here is using a field mapping instead of an output field mapping for enriched skill output, and forgetting that collection types are needed for multiple values.
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
✓
In the index definition, set the 'productCodes' field to type Collection(Edm.String) and mark it as searchable and filterable. Then in the indexer, map the custom skill output to this field using an output field mapping.
To store multiple product codes from a custom skill, the index field must be a collection of strings. Collection(Edm.String) supports multiple values and can be marked searchable and filterable to meet query requirements. The custom skill's output is part of the enriched document, so an output field mapping is the correct mechanism to project it into the index field. Using a single string field or omitting searchable would not satisfy the scenario.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
In the index definition, set the 'productCodes' field to type Edm.String and mark it as searchable and filterable. Then in the indexer, map the custom skill output to this field using an output field mapping.
Why it's wrong here
A single Edm.String field cannot store a collection of product codes; it can only hold one string value. While searchable and filterable attributes are correct for querying, the field type must be a collection to accommodate multiple codes. This option would fail to store all product codes and would not meet the requirement.
- ✗
In the index definition, set the 'productCodes' field to type Collection(Edm.String) and mark it as retrievable only. Then in the indexer, map the custom skill output using a field mapping.
Why it's wrong here
Making the field retrievable only allows it to be returned in results but not searched or filtered. The requirement explicitly states the field must be searchable and filterable. Field mappings are also used for source-to-index mappings, not for enriched skill outputs; output field mappings are needed for that. This option fails on both attributes and mapping type.
- ✓
In the index definition, set the 'productCodes' field to type Collection(Edm.String) and mark it as searchable and filterable. Then in the indexer, map the custom skill output to this field using an output field mapping.
Why this is correct
Collection(Edm.String) is the correct field type for storing multiple string values. Marking it searchable and filterable enables full-text search and filtering on individual codes. An output field mapping connects the custom skill's JSON array to the index field. This combination correctly stores and exposes the product codes for search and filter operations.
- ✗
In the index definition, set the 'productCodes' field to type Collection(Edm.String) and mark it as filterable and facetable. Then in the indexer, use a field mapping to map the custom skill output.
Why it's wrong here
While filterable and facetable are useful attributes, the requirement includes searchable, which is missing here. Additionally, field mappings are for source fields, not enriched outputs; output field mappings are required to map skill results. This option would not make the field searchable and would not correctly map the custom skill output.
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.