Implement knowledge mining and document intelligence solutions →mediumMultiple Select

AI-102 Practice Question: Implement knowledge mining and document intelligence solutions

You are building an Azure AI Search knowledge mining solution over a repository of scanned product manuals. You need to extract structured entities such as product names and part numbers from the OCR text and store them in an index field. (Choose two.)

⚠ Common exam trap

The trap here is assuming that enriching text with any language skill automatically stores results in the index, when a field mapping is also required.

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 that writes the entity recognition output to an index field.

Extracting structured entities from OCR text requires a skill that performs entity recognition, and the results must be persisted through an output field mapping. The entity recognition skill with configured categories identifies the relevant named entities, while the field mapping writes those values into the index so they can be queried. Skills that only detect language or key phrases do not produce the required structured 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.

✗
Add Microsoft.Skills.Text.LanguageDetectionSkill to the skillset.
Why it's wrong here
LanguageDetectionSkill identifies the language of the input text so that other skills can use the correct language code. It does not extract product names or part numbers. Adding it could help choose a language for downstream analysis, but it does not satisfy the requirement to capture structured entities in an index field.
✓
Define an outputFieldMapping that writes the entity recognition output to an index field.
Why this is correct
Skill outputs live only in the enrichment tree until they are mapped. An outputFieldMapping connects the entity recognition output node to a field defined in the index. Without this mapping the extracted entities would be discarded after enrichment, so this step is required to make the data queryable.
✗
Add Microsoft.Skills.Text.KeyPhraseExtractionSkill to the skillset.
Why it's wrong here
KeyPhraseExtractionSkill returns the main talking points in a document as a list of phrases. It does not classify phrases into entity categories or guarantee that product names and part numbers are isolated. While useful for topic discovery, it cannot reliably produce the structured entity types the scenario requires.
✗
Configure the indexer to use a JSON parsing mode.
Why it's wrong here
JSON parsing mode is appropriate when source documents are JSON and you want to control which nodes are indexed. The manuals here are scanned documents whose content is extracted by OCR, so JSON parsing mode would not expose product names or part numbers. It does not perform entity extraction.
✓
Add Microsoft.Skills.Text.EntityRecognitionSkill to the skillset and set its categories to include the needed entity types.
Why this is correct
EntityRecognitionSkill analyzes text and returns entities with categories such as organizations, locations, and other named types. By configuring the categories parameter, you can target the entity types relevant to product manuals. Its output can then be mapped into an index field so that the extracted entities become searchable and filterable.

Go deeper

AI-102 Practice Question: Implement knowledge mining and document intelligence solutions

Why each option matters

Option-by-option breakdown

Related to this question