Hello, basically I have a website running as a container on google cloud run (Flask application with basic html / css). It’s the first website i ever created and I’m a bit lost on how to add a new functionality in my website.
I have made a local ML application in python that take an image as input and return images and text as outputs. The thing is that I want this application to be added in my website in a way that the visitor have an option to upload a file and once the upload is done it triggers the ML pipeline and wait on site for the response.
My question is how should I proceed to do this on GCP ? I need to have a place to store the input images and I also need to find a way to trigger the ML pipeline once the user uploaded an img file. Should I build a distinct API for the ML pipeline ? Where do I store my trained neural network ? Is it possible to call an API with an image ? I really open to all suggestions.
Thanks in advance ![]()