I am unable to get OCR to work… I want to open a image file(s) on my desktop and run them through Google Vision API to get text for each of those files.
How do I start this automation?
Hello,
You need to enable Google Vision API from your account and create a service account to use. Than you can use the Google Vision API package. First you need to use the Connect node and then Image to Text node.
A minimal flow could be something like this:
This tutorial may help you to create a service account