my-homelab-configs/apps/mlops-platform/README.md

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.

This directory contains the FastAPI service and model artifacts. It is not yet registered as a Kubernetes application in bootstrap/apps; the public website currently links to the reserved static placeholder under apps/demos-static/public/mlops-platform/.

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.

Local Smoke Test

docker build -t mlops-platform:local apps/mlops-platform
docker run --rm -p 8080:8080 mlops-platform:local

In another shell:

curl -fsS http://127.0.0.1:8080/healthz
curl -fsS http://127.0.0.1:8080/predict \
  -H 'Content-Type: application/json' \
  -d '{"latency_ms":120,"error_rate":0.01,"cpu_utilization":0.55,"memory_utilization":0.62,"queue_depth":8}'
curl -fsS http://127.0.0.1:8080/metrics

The next deployment step is to add Kubernetes manifests or a Kustomize app with blue and green Deployments, a Service selector for the active track, resource requests and limits, and Prometheus scraping.