ml-deployment-helper - ML Model Production Deployment
Generates deployment artifacts for ML models with APIs, containerization, monitoring, and A/B testing infrastructure
Tags
Updated: 2026-05-11Typical Inputs
Typical Outputs
What this skill does
- containerize model
- create API endpoint
- setup monitoring
- configure A/B test
- register model version
- load test model
- deploy to production
- rollback model version
Inputs
- model path
- increment version
- framework name
- python version
- API URL
- traffic split ratio
- input data path
- output data path
Outputs
- Dockerfile
- API code
- monitoring configuration
- A/B test framework
- deployment artifacts
- REST API endpoints
- batch prediction jobs
- real-time stream predictions
- monitoring dashboards
- deployment increment directory
Requirements
- Python environment
- Docker
- Prometheus
- Grafana
- Kubernetes
- Airflow
- Kafka