Implementing an OCR solution using API

Hey, i’m not familiar with API’s but i think i need an OCR api because i want to read image text ( for resumes in image format). There is a way to implement the OCR api in openRPA or there is another approach to consider. If anybody worked in a similar type of project, i would appreciate the help. I hope i was clear about it and excuse me for my english it’s not my native language.

normally that would be handled by using nodered as middle man.
There is an example on how send an image from robot → nodered → google vision api
here examples-files/object-detection at master · open-rpa/examples-files · GitHub
you will need to change the api from object detection to text detection
But you could also update the workflow to talk to abby, azure, ibm etc.

( and maybe here examples-files/ocr-with-google-vision at master · open-rpa/examples-files · GitHub )

do i really need nodered or openflow to integrate ocr? Or can i set up OCR api directly in openrpa and how? thank you

you could do it your self using Invoke Code, and add any libraries you may need using nuget packages.
But I have no examples on how to do that.

i’m trying to use easyocr, i installed it in my machine and when i try to import it in openrpa using invoke code i get no module named … error.

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.