Building a Model Prediction Server

Building a Model Prediction Server

Learn how to build a working FastAPI application to serve predictions from a trained scikit-learn model in real-time. This 1 hour 45 minute tutorial, presented at PyCon US, guides you through the process of creating a production-ready API for delivering model predictions to other systems. Gain hands-on experience in API development as you transform a trained predictive model into a functional server application. Suitable for those with no prior API development experience, explore the crucial steps beyond model training to effectively deploy and serve machine learning models in production environments.