MLOps deployment to Azure Container Apps

Learn how to deploy a Machine Learning model with FastAPI and deploy it to #Azure Container Apps with GitHub Actions from the GitHub container registry. This lesson (and repository) uses #MLOps strategies and gives you a good starting point with a Dockerfile, GitHub Actions workflow, and Python code that already works for generating text using GPT-2 with HuggingFace Transformers. ▬▬🥇 Learn Objectives ▬▬ 🚀 Use GitHub Container Registry to push a built container 🚀 Use the Azure CLI in a GItHub Action to authenticate to Azure 🚀 Configure Azure Container Apps to correctly serve a model with enough resources 🚀 How to generate an Azure Service Principal and a Personal Access Token to authenticate 🚀 Use the Azure CLI in a GItHub Action to authenticate to Azure ▬▬ C H A P T E R S ⏰ ▬▬ 00:00 Introduction 00:46 Architectural overview 02:15 Project requirements 04:40 Azure Container App 05:10 GitHub Automation steps 08:54 Trigger workflow 10:40 Azure Portal 11:40 Change ingress 12:15 Log output 13:26 Update CPU and Memory 14:40 Validate deployment 16:20 Scale 16:39 Lesson Recap ▬▬ 🔗 R E S O U R C E S ▬▬ Example repository → https://github.com/alfredodeza/huggingface-deploy-azure Practical MLOps book → https://www.amazon.com/Practical-MLOps-Operationalizing-Machine-Learning/dp/1098103017/ Packaging ML models → https://learning.oreilly.com/videos/packaging-machine-learning/50116VIDEOPAIML/ MLOps packaging: HuggingFace and Docker → https://learning.oreilly.com/videos/mlops-packaging-huggingface/50143VIDEOPAIML/ MLOps packaging: HuggingFace and Azure Container Registry → https://learning.oreilly.com/videos/mlops-packaging-huggingface/50144VIDEOPAIML/