MDFT Pro, a well-known training agency, has acquired a massive collection of 50,000 scanned historical training documents, certification materials, and educational resources from various industry partnerships and acquisitions.
Claire, the Digital Transformation Manager, needs to make this content searchable and accessible through Azure Cognitive Search by implementing an enrichment pipeline that performs optical character recognition to extract text and applies text analytics to identify key concepts, entities, and topics. The solution must handle the large volume of documents efficiently while keeping processing costs as low as possible for this one-time digitization project.
What should Claire attach to the skillset to minimize costs for the OCR and text analytics enrichment pipeline?
Choose the correct answer from the options below.
Explanations for each answer: