Implement knowledge mining and information extraction solutions →mediumMultiple Choice

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

You are building an Azure AI Search enrichment pipeline that enriches documents with key phrases detected by Azure AI Language. You need the key phrases to be returned as a structured collection that can be mapped to a Collection(Edm.String) field in the search index, and you must avoid storing the enriched text in the enrichment cache. Which output mapping configuration should you use in the indexer?

⚠ Common exam trap

The trap here is assuming the Key Phrases skill emits per-page results under /document/pages/*/keyPhrases, when it actually writes a single array at /document/keyPhrases for the whole document.

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

✓

Define an outputFieldMapping with a source of /document/keyPhrases and a targetField of keyPhrases.

The Key Phrases skill writes its output to the enrichment tree at /document/keyPhrases as an array of strings. To persist that array into a Collection(Edm.String) field, the indexer needs an outputFieldMapping whose source is that exact path and whose target is the index field. Cache behavior is configured separately on the indexer and is not part of output mapping.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Define an outputFieldMapping with a source of /document/keyPhrases and a targetField of keyPhrases.
Why this is correct
The Key Phrases skill emits its result at the enrichment tree path /document/keyPhrases as a JSON array of strings. Mapping that source directly to a Collection(Edm.String) index field stores the phrases as a structured collection. Because the mapping targets an index field rather than a cache-only enrichment, the correct configuration preserves the intended behavior without persisting the enriched text in the cache.
✗
Define an outputFieldMapping with a source of /document/pages/*/keyPhrases and a targetField of keyPhrases.
Why it's wrong here
The wildcard path /document/pages/*/keyPhrases is used when a skill runs once per page or per element, such as OCR or image analysis on a multi-page document. The Key Phrases skill operates on the whole document text, so its output is not nested under pages. Using this path would produce no values for the target field and would leave the index field empty.
✗
Define an outputFieldMapping with a source of /document/keyPhrases and a targetField of keyPhrases, and set the indexer cache to disabled.
Why it's wrong here
Disabling the enrichment cache is not part of output mapping configuration and would not solve the stated requirement. The cache is controlled by the indexer's cache property, not by outputFieldMapping. Adding this setting changes incremental enrichment behavior but does not affect how key phrases are routed from the enrichment tree into the index field.
✗
Define an outputFieldMapping with a source of /document/keyPhrases and a targetField of keyPhrases, and mark the field as retrievable and filterable.
Why it's wrong here
Marking a Collection(Edm.String) field as filterable is not supported for collection fields in Azure AI Search; only searchable and retrievable attributes apply. Filtering on a collection of strings requires separate fields or a different modeling approach. Adding these attributes does not change the mapping behavior and may cause index creation to fail.

Go deeper

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

Why each option matters

Option-by-option breakdown

Related to this question