Registered users can ask their own questions, contribute to discussions, and be part of the Community!
I'm trying to understand how can we use REST APIs to create model endpoints. I could find some API docs but not much relevant & clear to understand the flow clearly.
Can someone pls share some use-cases with flows/documents around it?
Also, it would be great if it could be shared how to integrate API integrated with AWS API Gateway?
Any suggestions would be really helpful.
Additional query going through the video, "machine learning model deployment", there is deployment Id mentioned which can be Kubernetes / Static environment.
Can the Kubernetes be scaled up for production versions? And is there any other methods we can do deployment like using AWS/Azure backend?Looking forward to solutions!