Model Deployment Skill for Claude

from fastapi import FastAPI
from pydantic import BaseModel
import joblib
import numpy as np

app = FastAPI()
model = joblib.load('model.pkl')

class PredictionRequest(BaseModel):
    features: list[float]

class PredictionResponse(BaseModel):
    prediction: float
    probability: float

@app.get('/health')
def health():
    return {'status': 'healthy'}

@app.post('/predict', response_model=PredictionResponse)
def predict(request: PredictionRequest):
    features = np.array(request.features).reshape(1, -1)
    prediction = model.predict(features)[0]
    probability = model.predict_proba(features)[0].max()
    return PredictionResponse(prediction=prediction, probability=probability)

FROM python:3.11-slim

WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY model.pkl .
COPY app.py .

EXPOSE 8000
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

class ModelMonitor:
    def __init__(self):
        self.predictions = []
        self.latencies = []

    def log_prediction(self, input_data, prediction, latency):
        self.predictions.append({
            'input': input_data,
            'prediction': prediction,
            'latency': latency,
            'timestamp': datetime.now()
        })

    def detect_drift(self, reference_distribution):
        # Compare current predictions to reference
        pass

# 1. Save trained model
import joblib
joblib.dump(model, 'model.pkl')

# 2. Create FastAPI app (see references/fastapi-production-server.md)
# app.py with /predict and /health endpoints

# 3. Create Dockerfile
cat > Dockerfile << 'EOF'
FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py model.pkl ./
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
EOF

# 4. Build and test locally
docker build -t model-api:v1.0.0 .
docker run -p 8000:8000 model-api:v1.0.0

# 5. Push to registry
docker tag model-api:v1.0.0 registry.example.com/model-api:v1.0.0
docker push registry.example.com/model-api:v1.0.0

# 6. Deploy to Kubernetes
kubectl apply -f deployment.yaml
kubectl rollout status deployment/model-api

# app.py
@app.get("/health")  # Liveness: Is service alive?
async def health():
    return {"status": "healthy"}

@app.get("/ready")  # Readiness: Can handle traffic?
async def ready():
    try:
        _ = model_store.model  # Verify model loaded
        return {"status": "ready"}
    except:
        raise HTTPException(503, "Not ready")

# deployment.yaml
livenessProbe:
  httpGet:
    path: /health
    port: 8000
  initialDelaySeconds: 30
readinessProbe:
  httpGet:
    path: /ready
    port: 8000
  initialDelaySeconds: 5

# ❌ Wrong: Model in wrong directory
COPY model.pkl /app/models/  # But code expects /app/model.pkl

# ✅ Correct: Consistent paths
COPY model.pkl /models/model.pkl
ENV MODEL_PATH=/models/model.pkl

# In Python:
model_path = os.getenv("MODEL_PATH", "/models/model.pkl")

from pydantic import BaseModel, Field, validator

class PredictionRequest(BaseModel):
    features: List[float] = Field(..., min_items=1, max_items=100)

    @validator('features')
    def validate_finite(cls, v):
        if not all(np.isfinite(val) for val in v):
            raise ValueError("All features must be finite")
        return v

# FastAPI auto-validates and returns 422 for invalid requests
@app.post("/predict")
async def predict(request: PredictionRequest):
    # Request is guaranteed valid here
    pass

monitor = ModelMonitor(reference_data=training_data, drift_threshold=0.1)

@app.post("/predict")
async def predict(request: PredictionRequest):
    prediction = model.predict(features)
    monitor.log_prediction(features, prediction, latency)

    # Alert if drift detected
    if monitor.should_retrain():
        alert_manager.send_alert("Model drift detected - retrain recommended")

    return prediction

resources:
  requests:
    memory: "512Mi"  # Guaranteed
    cpu: "500m"
  limits:
    memory: "1Gi"    # Max allowed
    cpu: "1000m"

# Monitor actual usage:
kubectl top pods

# Deploy with version tag
kubectl set image deployment/model-api model-api=registry/model-api:v1.2.0

# If issues, rollback to previous
kubectl rollout undo deployment/model-api

# Or specify version
kubectl set image deployment/model-api model-api=registry/model-api:v1.1.0

@app.post("/predict/batch")
async def predict_batch(request: BatchPredictionRequest):
    # Process all at once (vectorized)
    features = np.array(request.instances)
    predictions = model.predict(features)  # Much faster!
    return {"predictions": predictions.tolist()}

# .github/workflows/deploy.yml
- name: Validate model performance
  run: |
    python scripts/validate_model.py \
      --model model.pkl \
      --test-data test.csv \
      --min-accuracy 0.85  # Fail if below threshold