From the course: Deploying Scalable Machine Learning for Data Science
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
APIs for ML model services
From the course: Deploying Scalable Machine Learning for Data Science
APIs for ML model services
- [Instructor] In this course, we concentrate on the architectural issues around scaling machine-learning models. APIs are an essential part of that architecture. So let's take a closer look at what a machine-learning API will look like. Let's start with a simple example. Restful APIs are invoked using HTTP commands. It's probably no surprise, since we're working with HTTP, the commands we issue will include a URL. So here's a simple example of a hypothetical domain called scalablemodels.com. This command makes a call to the server at scalablemodels.com, and requests a list of predictors, or models that are available for making predictions. When invoking an API call, we could use different HTTP Commands, including GET, POST, PUT, and DELETE. Now since we're focused on machine-learning models, which take in a set of parameters, and return a JSON object, we will use the POST and GET commands. APIs that allow users to change a database, or the state of the program, may use the other…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.