AI-102 Question 367
Select 2You are designing an Azure Cognitive Search solution for a company that needs to extract metadata and content from various types of documents, including PDFs and images. To achieve this, you need to define a skillset. Which of the following components should you include in the skillset to meet the requirements?
- A
OCR (Optical Character Recognition) skill
- B
Image Analysis skill
- C
Entity Recognition skill
- D
Key Phrase Extraction skill
- E
Custom Web API skill
Show answer and explanation
Correct answers: A, B
Explanation
A skillset in Azure Cognitive Search defines a collection of cognitive skills to enrich data during the indexing process. For the given scenario, the OCR skill is crucial for extracting text from images and PDFs, while the Image Analysis skill is used to extract metadata from image files. Other skills, like Entity Recognition or Key Phrase Extraction, are not directly applicable to the stated requirements.
- A. Correct.
The OCR skill is essential to extract text from images and PDFs, making it a critical component for handling content extraction from images and scanned documents.
- B. Correct.
The Image Analysis skill is used to extract metadata from images, such as identifying objects or features, which is relevant for processing image-based documents.
- C. Incorrect.
The Entity Recognition skill is used to identify entities like people, organizations, or locations in text, but this is not necessary for the given scenario of extracting metadata and content from documents.
- D. Incorrect.
The Key Phrase Extraction skill identifies key phrases in text but does not directly contribute to the extraction of metadata or content from PDFs and images.
- E. Incorrect.
The Custom Web API skill allows for custom processing logic, but it is not required for the standard OCR and metadata extraction scenario described in this case.