Hello there,
I am new to Wappler and am starting my journey at the moment and one of my project ideas is to run a postal scanner which delivers pdf’s to a folder. The pdf shall then be processed for OCR first and an AI second to create metadata. is there any framework or extension that provides OCR? Or shall I look for that externally? hints greatly appreciated
thank you in advance,
Kolja
No, there is OCR extension available in Wappler - at this moment.
You would have to use a third party API for this, I think there will be a lot of them out there, here’s an example:
Wappler is great at plugging in to third party APIs. I’ve a feeling you would be able to do what you suggested above using one API call and not two (for the AI part).
Not build in, but you could use Google Vision to extract the text from a PDF or OCR (visual recognition) of a scanned document and then feed the document into any AI (OpenAI, Google PaLM…) for examination / summary / meta data.
(all this options of course come with a cost)
You also have:
Which is just a web assembly wrapper for the tesseract ocr engine.
Tesseract is used also by chatGPT