AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are implementing a knowledge mining solution using Azure AI Search. The data source is a large Azure Cosmos DB collection containing customer support tickets. Each ticket has fields: ticket_id, description, category, and resolution. You need to ensure that the search index can support fuzzy search and autocomplete suggestions. What should you configure in the index definition?
⚠ Common exam trap
Candidates often confuse 'searchable' with 'filterable' or 'facetable', thinking any attribute that enables querying will also support fuzzy search and autocomplete, but only 'searchable' fields are analyzed and tokenized for these features, and a suggester is a separate required configuration.
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
✓
Set the 'searchable' attribute on the description field and define a suggester
Fuzzy search requires the 'searchable' attribute on fields to enable full-text search, and autocomplete suggestions require a 'suggester' configured on the index. The suggester defines which fields are used to generate suggestion candidates, and the 'searchable' attribute allows the description field to be tokenized and matched against partial or misspelled queries.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Set the 'searchable' attribute on the description field and define a suggester
Why this is correct
Marking the description field searchable enables full-text tokenisation, which underpins fuzzy matching, while a suggester builds the dedicated autocomplete and suggestions structures. Both are required because fuzzy search and autocomplete read from different index constructs, and the stem demands support for both.
- ✗
Set the 'filterable' attribute on the description field
Why it's wrong here
Filterable permits $filter expressions on description but does not create the tokenisation or suggester structures that fuzzy matching and autocomplete depend on. It is tempting because filtering narrows results and feels related to query refinement. Fuzzy search needs a language analyser, and autocomplete needs a suggester declared over the relevant fields.
- ✗
Set the 'sortable' attribute on the ticket_id field
Why it's wrong here
Sortable orders results by ticket_id but has no bearing on text analysis, so fuzzy matching and autocomplete stay unavailable. It is tempting because sorting improves result presentation in search applications. Fuzzy search requires a language analyser on the field, and autocomplete requires a suggester defined in the index definition.
- ✗
Set the 'facetable' attribute on the category field
Why it's wrong here
Facetable enables filtering and counting on category values; it does not affect how the analyser tokenises text, so fuzzy matching and autocomplete remain unsupported. It is tempting because facets power drill-down navigation in search UIs. Fuzzy search and autocomplete instead require a language analyser plus suggester configured on the description field.
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 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.