Hard1 markMultiple Choice
Domain 2.4: Non-Relational Data StorageDomain 2Cognitive SearchAI EnrichmentArchitecture

AZ-305 · Question 29 · Domain 2.4: Non-Relational Data Storage

A legal firm has 10 million scanned PDF documents stored in Azure Blob Storage.

You are designing a search solution using Azure Cognitive Search. Users must be able to search for specific keywords contained within the scanned images of the PDFs. Additionally, the solution must automatically identify and extract the names of people and organizations mentioned in the text.

Which feature of Azure Cognitive Search must you configure?

Answer options:

A.

A standard indexer with a custom analyzer.

B.

An AI enrichment skillset with OCR and Entity Recognition skills.

C.

A synonym map.

D.

Semantic Search.

How to approach this question

Identify the Cognitive Search feature that applies AI models (like OCR and NLP) during the indexing phase.

Full Answer

B.An AI enrichment skillset with OCR and Entity Recognition skills.✓ Correct
An AI enrichment skillset with OCR and Entity Recognition skills.
Azure Cognitive Search supports AI enrichment, which allows you to attach Azure Cognitive Services to the indexing pipeline via a 'skillset'. To read text from scanned PDFs (images), you must use the Optical Character Recognition (OCR) cognitive skill. To extract names of people and organizations, you must use the Entity Recognition cognitive skill. These skills process the documents as they are pulled from Blob Storage and add the extracted data to the search index.

Common mistakes

Thinking a standard indexer can read scanned PDFs. Standard indexers only read digital text; images require the OCR skillset.

Practice the full Azure Solutions Architect Expert AZ-305 Practice Exam 5

55 questions · hints · full answers · grading

More questions from this exam