https://huggingface.co/blog/document-ai
#documentAI
- OCR: Turning typed, handwritten, or printed text into machine-encoded text

- Classifying documents into the appropriate category, such as forms, invoices, or letters

- Document layout analysis: determining the physical structure of a document

- Document parsing: identifying and extracting key information from a document, such as names, items, and totals from an invoice form.

- Table detection, extraction, and table structure recognition

- Document visual question answering: After being given a question, the model analyzes the image and responds with an answer

And more in the article