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

v3ss0n just now

How this is better over Surya/Marker or kreuzberg https://github.com/kreuzberg-dev/kreuzberg.

jadbox just now

Sounds like someone needs to run their own test cases and report back on which solution does a better job...

hersko 1 hour ago

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?

saaaaaam just now

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

trollbridge just now

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.

mimim1mi 1 hour ago

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.

sgc 1 hour ago

How does this compare to dots.ocr? I got fantastic results when I tested dots.

https://github.com/rednote-hilab/dots.ocr

mjrpes just now

Ocrbase is CUDA only while dots.ocr uses vLLM, so should support ROCm/AMD cards?

actionfromafar just now

How about CPU?

mechazawa 1 hour ago

Is only bun supported or also regular node?