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?
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.
What matters most is how well OCR and structured data extraction tools handle documents with high variation at production scale. In real workflows like accounting, every invoice, purchase order, or contract can look different. The extraction system must still work reliably across these variations with minimal ongoing tweaks.
Equally important is how easily you can build a human-in-the-loop review layer on top of the tool. This is needed not only to improve accuracy, but also for compliance—especially in regulated industries like insurance.
The "guts" are here: https://github.com/majcheradam/ocrbase/blob/7706ef79493c47e8...
Discussion is here: https://news.ycombinator.com/item?id=45652952
https://github.com/rednote-hilab/dots.ocr
Equally important is how easily you can build a human-in-the-loop review layer on top of the tool. This is needed not only to improve accuracy, but also for compliance—especially in regulated industries like insurance.
Other tools in this space:
LLMWhisperer/Unstract(AGPL)
Reducto
Extend Ai
LLamaparse
Docling