Which Document AI feature should you use to train a model to recognize fields on a unique, custom form for which Google does not have a pre-trained model?

A law firm wants to digitize millions of scanned contracts. You need an AI service to extract text, forms, and tables from these PDF documents automatically. Which service is designed for this?

What is the primary function of Google Cloud 'Document AI'?

Which Document AI component is used to process a specific type of document, such as an Invoice or a Driver's License, using a pre-trained Google model?

What is a 'Human-in-the-Loop' (HITL) system in Document AI?

Can Document AI process handwritten text in documents?