Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
1–10 of 37 posts
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#2Is only bun supported or also regular node?
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#3I 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?
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#4I 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?
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.
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#5How does this compare to dots.ocr? I got fantastic results when I tested dots.
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#6How does this compare to dots.ocr? I got fantastic results when I tested dots. https://github.com/rednote-hilab/dots.ocr
Ocrbase is CUDA only while dots.ocr uses vLLM, so should support ROCm/AMD cards?
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#7How this is better over Surya/Marker or kreuzberg https://github.com/kreuzberg-dev/kreuzberg.
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#8I 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?
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.
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#9I 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?
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
Re: Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API
#10How this is better over Surya/Marker or kreuzberg https://github.com/kreuzberg-dev/kreuzberg .
Sounds like someone needs to run their own test cases and report back on which solution does a better job...