Introduction

I decided to write this post to demonstrate how to test my ML API deployed on AWS, you may find the API project in my repository: Machine Learning AWS API. This project aims to create a Python API using FastAPI and deploy it to AWS Lambda. The API is designed to serve predictions based on models imported from an external repository: Machine Learning Models Repository. The application is containerized with Docker, providing an isolated and reproducible development environment.

Through this post, you will have the opportunity to interact with the deployed API to check its health, list available machine learning models, and detect the language of a given text (which is the unique ML model avaliable at this moment).

Let’s dive into how to interact with the API and explore the various endpoints.

Check API Health

Click the button below to check if the API is healthy:

Check API Health

List Available Machine Learning Models

Click the button below to list the available models in the API:

List Available Models

Test the Language Detection Model

Type some text in the field below and click the button to detect the language:

Detect Language