Today I'm excited to have the opportunity to contribute to the 30DaysofStreamlit challenge via this hands-on tutorial! We will create a zero-shot learning text classifier using Hugging Face's API inference and Distilbart! With it you will have the mighty power to classify keyphrases on-the-fly, fast, and without any ML training! You can set these labels dynamically to anything, e.g.: Zero-shot learning (ZSL) differs from traditional machine learning methods as it deals with the ability to recognise objects *without* any training samples. Yet it can build and train models efficiently with the help of transferring intelligence from previously seen categories and auxiliary information.

To build a web app you'd typically use such Python web frameworks as Django and Flask. But the steep learning curve and the big time investment for implementing these apps present a major hurdle. Streamlit makes the app creation process as simple as writing Python scripts! In this article, you'll learn how to master Streamlit when getting started with data science. The data science process boils down to converting data to knowledge/insights while summarizing the conversion with the CRISP-DM and OSEMN data frameworks.