Capstone
Cloud & DevOps
Cloud-Native CI/CD Platform
GitOps pipeline with Kubernetes, Helm and progressive delivery
- Kubernetes
- Docker
- Helm
- Argo CD
- +2
₹5,299₹8,999
4.8/74 reviews
Cloud & DevOps · Mini Project
Package & Deploy an ML Model as an API
Takes a trained model to a versioned, containerised FastAPI service
1-2 weeks build
Overview
The step most projects skip. A trained scikit-learn model is serialised with its preprocessing, wrapped in a FastAPI service with validated inputs, packaged into a slim Docker image and deployed to a cloud host. Each model version is tagged, served side by side, and rolled back with one change, while a CI workflow tests and builds every push.
What makes it stand up
- 01Model and preprocessing saved together as one pipeline
- 02Pydantic request validation and clear error responses
- 03Multi-stage Dockerfile for a small image
- 04Versioned model endpoints with a one-line rollback
- 05CI that tests, builds and pushes the image
Module breakdown
- 01
Packaging
Pipeline serialisation with a metadata file per version.
- 02
API
FastAPI predict, health and version endpoints.
- 03
Container
Multi-stage Docker build and local compose setup.
- 04
Deployment
Step-by-step deploy to a free-tier cloud host.
- 05
CI and tests
Pytest suite and a GitHub Actions build workflow.
After this, you will be able to
- Explain why preprocessing must ship with the model
- Defend your versioning and rollback approach
- Demo a live prediction call against the deployed API
Technology stack
- Python
- scikit-learn
- FastAPI
- Docker
- GitHub Actions
- Level
- Mini Project
- Domain
- Cloud & DevOps
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support