Microsoft Certified: Azure AI Engineer AssociateImplement knowledge mining solutionsEasy
A company is building an Azure AI Search solution over a large repository of PDF documents. These documents contain both text and embedded images that include important diagrams and charts. The company needs to ensure that content within these images is also searchable. Which component of an Azure AI Search indexer configuration should be used to achieve this?
- AA custom text analyzer
- BA scoring profile for image relevance
- CA skillset with an OCR skill
- DA suggester for image content
Show answer & explanationAnswer & explanation
Correct answer: C. A skillset with an OCR skill
To make content within embedded images searchable, Azure AI Search needs to extract text from those images. This is accomplished by adding an Optical Character Recognition (OCR) skill to a skillset, which is then attached to the indexer.
Why the other options are wrong
- A. Custom text analyzers process textual content, they do not extract text from images.
- B. Scoring profiles influence result ranking, they do not extract content from images.
- D. Suggesters provide query suggestions, they do not extract content from documents.
OCR Skill in Azure AI Search
An Azure AI Search built-in skill that extracts printed or handwritten text from images within documents.
- Part of an Azure AI Search skillset.
- Processes image content (e.g., within PDFs, JPEGs).
- Outputs extracted text which can then be indexed.
Memory trick: To search images, you need a 'skill' to 'see' the text inside them, like a super-powered OCR eye.