How to Deploy ML Solutions with FastAPI, Docker, & AWS

Get exclusive access to AI resources and project ideas: https://the-data-entrepreneurs.kit.com/shaw

This is the 5th video in a series on Full Stack Data Science. Here, I walk through a simple 3-step approach for deploying machine learning solutions.

More Resources:
💻 Example Code: https://github.com/ShawhinT/YouTube-Blog/tree/main/full-stack-data-science/ml-engineering
📰 Read more: https://medium.com/towards-data-science/how-to-deploy-ml-solutions-with-fastapi-docker-and-gcp-de1bb8bfc59a?sk=5048e53b3599a37a126379514328e2e3

🛠️ Previous Video: https://youtu.be/sNa_uiqSlJo
➡️ Data Pipeline Video: https://youtu.be/Ylz779Op9Pw

References:
[1] FastAPI Tutorial: https://fastapi.tiangolo.com/tutorial/first-steps/
[2] FastAPI + Docker: https://fastapi.tiangolo.com/deployment/docker/
[3] Deploying on AWS ECS: https://www.youtube.com/watch?v=1H83IRK4RXw

--
Homepage: https://www.shawhintalebi.com/

Intro - 0:00
ML Deployment - 0:33
3-Step Deployment Approach - 1:52
Example Code: Deploying Semantic Search for YT Videos - 3:21
Creating API with FastAPI - 4:31
Create Docker Image - 11:13
Push Image to Docker Hub - 17:15
Deploy Container on AWS ECS - 19:46
Testing Gradio UI - 25:54
What's Next? - 27:07