Logo Lanfrica

Azubi-Africa/Career_Accelerator_P5-ML_API

Record type:

software
Creator:
Azu
Host:
Building ML API endpoints and deploying them using docker. # Machine Learning API using FastAPI Develop a Machine Learning API (Application Programming Interface) using FastAPI. ## Introduction This is the last project of the program, congratulations for all the work done until now. In this project, we aim to help you to discover how to create an API that might be requested to interact with a ML model. This is an interesting solution when you want to keep your model architecture secret or to make your model available to users already having an API. By creating an API, and deploying it, your model can so that receive request using the internet protocol as presented by the illustration below. **Source** : *The benefits of Machine Learning APIs - UbiOps* ## Description You will have a minimal API demo with FastAPI, this will just serve you to make sure that everything works correctly. Then, you will have to make your own API, this allowing you to interact with a Machine Learning model, that is to say: - Pass data through a request; - Get the data in using the API; - Apply the necessary processing; - Submit the processed data to the ML model to make the predictions; - Process the predictions obtained and return them as the API's response ot the input request. ## Instructions Your task is to build an API integrating a ML model using FastAPI. Clone this repository to use it as a template, do not forget to change the readme at the end of the project. Your work should follow these next steps. 1. Build a ML model to predict the Sepsis(**Data set here**), during the 2 first weeks. 2. Build an API using Fast API, during the remaining weeks, to embed the ML model built. Upon completion of your project, you are required to write a blog post on your thought process on medium, LinkedIn, personal blog, or any other suitable blogging site. ## Rubrics Machine Learning : - **Excellent:** Have a pipeline/function that takes inputs and make accurate predictions. - **Good:** Have a pipeline/function that takes inpu …