Building a Streamlit Frontend for FastAPI & Scikit Learn Model
In this video, we continue our project from our last episode where we created an API using FastAPI and Scikit-Learn. We built a Random Forest classifier, saved the model with Joblib, and set up endpoints to serve data and predictions. This episode focuses on creating a frontend using Streamlit to interact with our FastAPI backend. We demonstrate how to build input forms, handle requests, and display predictions, alongside the technical steps to integrate both platforms. Finally, we discuss deployment options for making the application publicly accessible. Join us to seamlessly connect a machine learning model to a user-friendly web interface.
Previous video
• FastAPI and scikit-learn tutorial to creat...
Code repo
https://github.com/AIgineerAB/AI_engi...
00:00 Introduction and Recap
02:01 Setting Up the Environment
02:16 Exploring the FastAPI Endpoints
05:21 Connecting Streamlit Frontend
07:39 Building the Streamlit Form
17:36 Deploying the Application
19:08 Conclusion and Next Steps