# MLOps Platform Demo

Production-shaped inference demo for the portfolio site. The model is intentionally small: logistic regression coefficients trained with scikit-learn and exported to JSON so the runtime stays light enough for the homelab.

## Endpoints

- `GET /healthz` reports service, track, and active model metadata.
- `POST /predict` scores service health risk from latency, error rate, CPU, memory, and queue depth.
- `GET /metrics` exposes Prometheus metrics for request count, latency, errors, model version, confidence, and drift score.

## Model Rollout

- `MODEL_VERSION=v1`, `MODEL_TRACK=blue` is the stable route.
- `MODEL_VERSION=v2`, `MODEL_TRACK=green` is the canary route.
- Kubernetes service selectors choose the active track, so rollback is a service selector change instead of an image rebuild.