This is a simple Streamlit application that showcases how to utilize MLRun in the context of a larger ML application.

Within this app, there are multiple demos with interactive UI's that inference live machine models via MLRun model serving functions.

Heart Disease Prediction UI

In addition to the interactive UI, there are also short code snippets that show the "behind the scenes" of how the models are deployed and inferenced within the application.

Iris Inferencing and Deployment

There are 2 ways to get started:

Simply go to https://mlrun-ai-apps.herokuapp.com/ and immediately start using the app. No installation required!

Note it may take a minute for the app to wake up

To deploy the applicaiton locally on your own machine, follow the local deployment instructions using docker-compose