Felix Falkenberg

@tobiascornille any progress on the fine-tuned handwriting model? :v:

@charlesmindee we're keenly interested in the handwritten text recognition feature as well. Has there been any progress or can you provide an estimated timeline?

Hi @ryanchesler, Thank you for your efforts in enhancing `h2ogpt` by adding support for pdfs https://github.com/h2oai/h2ogpt/pull/787 I just wanne hightlight that one essential requirement for our use-case is the ability...

Thank you, that helps a lot! While I found the information incredibly detailed, I must admit that I personally felt a bit overwhelmed first time sifting through it all. Here's...

@pseudotensor Is there a specific API endpoint or method to download the OCR-ed PDF after it has gone through OCR? I couldn't find any reference to a `download_file_api` or similar...

Wow this is just amazing, thank you so much for your work!

@pseudotensor using /get_document_api returns a dictionary or raw text. Is it also possible to get the OCR-ed PDF back itself? Similair to how doctr seems to works. 

@martindurant ahh thank you alot, that explains it :) another question if i may: Shouldn't the following work then as well? ``` file = "s3:///.jpg" fsspec.open(file, "rb", s3={"client_kwargs": {'endpoint_url': os.environ['S3_ENDPOINT']}})...

okay, thank you