News for hackers. Stuff that matters.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by nickandbro on Wednesday February 05, 2025 @02:41PM (#42953976)
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.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by layer8 on Wednesday February 05, 2025 @04:02PM (#42955074)
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.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by visarga on Thursday February 06, 2025 @12:33AM (#42959407)
OCR is not 100% either. Reading order is also fragile, it might OCR the word but mess up the line structure.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by depr on Wednesday February 05, 2025 @03:18PM (#42954513)
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.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by nnurmanov on Thursday February 06, 2025 @01:00AM (#42959514)
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.