Integration with PEGA

I'm trying to set up OCR capabilities in PEGA(Basically reading text from an image and converting them into a text). How do I integrate with google vision api? I have logged in google vision api and went through the code and algos. But I'm not able to understand how that integrates with any application like PEGA. What I have understood is like this, I need to send an image file with DOCUMENT_TEXT_DETECTION feature, and it would return me result in a JSON format. I'm fine with it. But how do I send the APIKey and how do I integrate? Any prompt suggestion is highly appreciated.