Learn how to deploy your Python RAG/AI project to the cloud in this advanced tutorial. We will turn the app into a public API, and host it on AWS Lambda (which makes it scalable and high-performance).
🔗 Code: https://github.com/pixegami/deploy-rag-to-aws
👉 Related Videos (in case you need it)
RAG Project Basic Tutorial: https://youtu.be/tcqEUSNCn8I
RAG Project Advanced Tutorial: https://youtu.be/2TJxpyO3ei4
FastAPI Tutorial: https://youtu.be/iWS9ogMPOI0
Get Started with AWS: https://youtu.be/LFCTFzcMQuA
AWS Bedrock (AI): https://youtu.be/kwkaBrK_-Bs
Using Docker on Lambda: https://youtu.be/wbsbXfkv47A
📚 Chapters
00:00 - Introduction
04:12 - RAG Recap
11:25 - Project Architecture
13:57 - Adding FastAPI
18:44 - Building a Docker Image
20:54 - Deployment Hacks
25:53 - Local Testing With Docker
29:17 - Build AWS Infrastructure with CDK
42:12 - Creating an Async API
54:11 - Wrapping Up