Building Serverless ML Applications
Serverless computing is the new paradigm within cloud computing. It allows us to build and run applications and services without thinking about servers. In reality, the application we build still runs on a cloud server, but the entire process for server management is done by the cloud service provider, such as AWS. By leveraging the serverless platform, we can build and deploy robust, large-scale, complex applications by only focusing on our application code instead of worrying about provisioning, configuring, and managing servers.
We have explored some important components of the AWS serverless platform such as AWS Lambda in this chapter, and we can now leverage these solutions to build a machine learning application where we can only focus on the core ML code and forget about provisioning infrastructure and scaling applications.
Exercise 101: Building a Serverless Application Using API Gateway, AWS Lambda, and SageMaker
In this exercise, we will build a...