Feature request

PR #18414 has a number of TODOs left over which we'd like to track as follow up tasks.

Pipeline

• Add support for documents which have more than the tokenizer span (e.g. 512) words
• Add support for multi-page documents (e.g. for Donut, we need to present one image per page)
• Rework use of tokenizer to avoid the need for add_prefix_space=True
• Re-add support for Donut
• Refactor Donut usage in the pipeline or move logic into the tokenizer, so that pipeline does not have as much Donut-specific code

Testing

• Enable test_small_model_pt_donut once hf-internal-testing/tiny-random-donut is implemented

Documentation / Website

• Add DocumentQuestionAnswering demo to Hosted Inference API so that model demos work
• Add tutorial documentation to Task Summary

Motivation

These are follow ups that we cut from the initial scope of PR #18414.

Your contribution

Happy to contribute many or all of these.