AI-102 Question 366
Select 3You are building an Azure Cognitive Search index for a document processing solution. Your data source includes images containing text and PDFs stored in Azure Blob Storage. You need to extract text and metadata from these files using AI enrichment. Which of the following components must you define in the skillset configuration to achieve this?
- A
A Cognitive Skill to perform OCR (Optical Character Recognition) on images
- B
A Cognitive Skill to extract content and structure from PDF files
- C
A Search Indexer to define the fields for the index
- D
A Cognitive Skill to translate the extracted text into multiple languages
- E
Input and output field mappings for the skillset
Show answer and explanation
Correct answers: A, B, E
Explanation
In this scenario, a skillset is used to define the AI enrichment pipeline for Azure Cognitive Search. Skillsets include Cognitive Skills (such as OCR and PDF text extraction) and field mappings to specify how data is processed and transformed. Translation is not required here, and the Search Indexer is a separate component that works after the skillset has processed the data.
- A. Correct.
Correct. A Cognitive Skill to perform OCR is required to extract text from images as part of the skillset.
- B. Correct.
Correct. A Cognitive Skill to process and extract text from PDFs is required to handle the PDF files in the data source.
- C. Incorrect.
Incorrect. The Search Indexer is not part of the skillset configuration; it is used to populate the index after the skillset processes the data.
- D. Incorrect.
Incorrect. Translation is not specified as a requirement in this scenario, so adding a translation skill is unnecessary.
- E. Correct.
Correct. Input and output field mappings are mandatory in a skillset to define how data flows into and out of the skills.