# visent-telemetry.yml
prometheus:
  enabled: true
  port: 9090
  path: /metrics
  interval: 30s
  labels:
    environment: production
    cluster: gpu-cluster

# Enable Prometheus export
visent telemetry config prometheus --enable

# Configure export endpoint
visent telemetry config prometheus --endpoint localhost:9090

# Test metric export
visent telemetry prometheus test

# GPU utilization percentage
visent_gpu_utilization{gpu="0", node="worker-1"} 85.2

# GPU memory usage in bytes
visent_gpu_memory_used{gpu="0", node="worker-1"} 16106127360

# GPU temperature in Celsius
visent_gpu_temperature{gpu="0", node="worker-1"} 72.5

groups:
  - name: visent-gpu-alerts
    rules:
      - alert: HighGPUTemperature
        expr: visent_gpu_temperature > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "GPU temperature is high"
          description: "GPU {{ $labels.gpu }} temperature is {{ $value }}°C"