News for hackers. Stuff that matters.

A comment on Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API.

Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by hersko on Tuesday January 20, 2026 @09:19AM (#46692075)
I have a flow where i extract text from a pdf with pdf-parse and then feed that to an ai for data extraction. If that fails i convert it to a png and send the image for data extraction. This works very well and would presumably be far cheaper as i'm generally sending text to the model instead of relying on images. Isn't just sending the images for ocr significantly more expensive?
[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by saaaaaam on Tuesday January 20, 2026 @10:29AM (#46692812)
There was an interesting discussion on here a couple of months back about images vs text, driven by this article: https://www.seangoedecke.com/text-tokens-as-image-tokens/

Discussion is here: https://news.ycombinator.com/item?id=45652952

[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by trollbridge on Tuesday January 20, 2026 @10:27AM (#46692781)
I always render an image and OCR that so I don’t get odd problems from invisible text and it also avoids being affected by anything for SEO.
[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by mimim1mi on Tuesday January 20, 2026 @09:47AM (#46692332)
By definition, OCR means optical character recognition. It depends on the contents of the PDF what kind of extraction methodology can work. Often some available PDFs are just scans of printed documents or handwritten notes. If machine readable text is available your approach is great.
[ Parent | on HN ]
Re:Show HN: Ocrbase – pdf → .md/.json document OCR and struc... by unrahul on Tuesday January 20, 2026 @01:21PM (#46695699)
I have seen this flow in what people in some startups call "Agentic OCR", its essentially a control flow that is coded that tries pdf-parse first or a similar non expensive approach, and if it fails a threshold then use screenshot to text extraction.
[ Parent | on HN ]