Welcome to this third article of my MLOps Series. In the first articleWe explore Docker and how it simplifies application packaging. In the second articlewe manage machine learning models using ml flow, Azureand Stevedore. Now, in this third part, we will put everything together by creating a Fast API application that serves our model previously stored in Azure. This allows us to create a prediction service that can be accessed globally!
A API It's like a bridge. Every time you interact with a library in Python, you are using its API. It's the public part of an app that you can interact with, while everything behind it is hidden.
APIs are commonly used to communicate with web applications and provide a set of URLs that return data (you send a request with some parameters and receive a response). Most of the time, data is returned in formats such as JSON or XML, which are easy to parse. This is different from websites that return HTML, which includes information to render pages. With APIs, you get just the raw data.
Some APIs are public, while others are private. When creating an API, you decide what data to share, how…
