Week 11: AI Applications – From Models to Products
Building real-world applications on top of foundation models
Time Estimate: 3-4 hours
Topics Covered
- Retrieval Augmented Generation (RAG)
- Function calling and tool use
- Prompt engineering and chain-of-thought reasoning
- Vector databases and semantic search
- Building AI-first products
Featured Speaker
DH
David Holz
Founder, Midjourney
Learn from industry leaders who are building the future of AI infrastructure and applications.
Video Resources
📹 Video content will be added here by Agent 2
Videos include keynotes, technical talks, and tutorials from industry leaders.
Reading Materials
📚 Reading list will be added here by Agent 3
Research papers, blog posts, and technical documentation.
🛠️ Hands-On Lab
Build an End-to-End ML Pipeline
Advanced 4 hoursObjective
Create a production-grade ML pipeline with data versioning, model registry, and A/B testing.
Prerequisites
- Python web frameworks (FastAPI)
- Docker basics
- MLflow or DVC experience helpful
- Understanding of CI/CD concepts
Setup Instructions
- Install MLflow:
pip install mlflow - Install FastAPI:
pip install fastapi uvicorn - Clone starter:
git clone https://github.com/stanford-cs153/mlops-lab - Set up local MLflow tracking server
Tasks
- Build data → train → eval → deploy pipeline
- Version datasets and models with MLflow
- Create FastAPI inference endpoint
- Implement A/B testing with traffic splitting
- Add monitoring and logging
- Document deployment process