←back to thread

1303 points serjester | 5 comments | | HN request time: 0.773s | source
1. nickandbro ◴[] No.42953976[source]
I think very soon a new model will destroy whatever startups and services are built around document ingestion. As in a model that can take in a pdf page as a image and transcribe it to text with near perfect accuracy.
replies(2): >>42954513 #>>42955074 #
2. depr ◴[] No.42954513[source]
I think the Azure Document Intelligence, Google Document AI and Amazon Textract are among the best if not the best services though and they offer these models.
replies(1): >>42959514 #
3. layer8 ◴[] No.42955074[source]
Extracting plain text isn’t that much of a problem, relatively speaking. It’s interpreting more complex elements like nested lists, tables, side bars, footnotes/endnotes, cross-references, images and diagrams where things get challenging.
replies(1): >>42959407 #
4. visarga ◴[] No.42959407[source]
OCR is not 100% either. Reading order is also fragile, it might OCR the word but mess up the line structure.
5. nnurmanov ◴[] No.42959514[source]
I have not tested Azure Document Intelligence, Google Document AI, but AWS Textract, LLamaparse, Unstructured and Omni made to my shortlist. I have not tested Docling, as I could not install it on my Windows laptop.