stack/infra/grafana/dashboards/llm.json

{
  "title": "LLM service",
  "uid": "llm",
  "tags": [
    "homelab",
    "stack"
  ],
  "timezone": "browser",
  "schemaVersion": 39,
  "time": {
    "from": "now-6h",
    "to": "now"
  },
  "refresh": "30s",
  "panels": [
    {
      "id": 1,
      "title": "HTTP request rate (status)",
      "type": "timeseries",
      "gridPos": {
        "x": 0,
        "y": 0,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (http_status_code) (rate(http_server_duration_milliseconds_count{job=\"llm\"}[1m]))",
          "legendFormat": "{{http_status_code}}"
        }
      ]
    },
    {
      "id": 2,
      "title": "Chat answers by outcome",
      "type": "timeseries",
      "gridPos": {
        "x": 12,
        "y": 0,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (outcome) (rate(stack_llm_chat_total[5m]))",
          "legendFormat": "{{outcome}}"
        }
      ]
    },
    {
      "id": 3,
      "title": "Dispatch rate per host",
      "type": "timeseries",
      "gridPos": {
        "x": 0,
        "y": 8,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (host, kind) (rate(stack_llm_dispatch_total[5m]))",
          "legendFormat": "{{host}} {{kind}}"
        }
      ]
    },
    {
      "id": 4,
      "title": "In-flight requests per host",
      "type": "timeseries",
      "gridPos": {
        "x": 12,
        "y": 8,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (host) (stack_llm_inflight)",
          "legendFormat": "{{host}}"
        }
      ]
    },
    {
      "id": 5,
      "title": "Dispatch latency p50/p95 (host, kind)",
      "type": "timeseries",
      "gridPos": {
        "x": 0,
        "y": 16,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "unit": "s"
        },
        "overrides": []
      },
      "targets": [
        {
          "expr": "histogram_quantile(0.50, sum by (le, host, kind) (rate(stack_llm_dispatch_seconds_bucket[5m])))",
          "legendFormat": "p50 {{host}} {{kind}}"
        },
        {
          "expr": "histogram_quantile(0.95, sum by (le, host, kind) (rate(stack_llm_dispatch_seconds_bucket[5m])))",
          "legendFormat": "p95 {{host}} {{kind}}"
        }
      ]
    },
    {
      "id": 6,
      "title": "Chat latency by stage (p50/p95)",
      "type": "timeseries",
      "gridPos": {
        "x": 12,
        "y": 16,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "unit": "s"
        },
        "overrides": []
      },
      "targets": [
        {
          "expr": "histogram_quantile(0.50, sum by (le, stage) (rate(stack_llm_chat_seconds_bucket[5m])))",
          "legendFormat": "p50 {{stage}}"
        },
        {
          "expr": "histogram_quantile(0.95, sum by (le, stage) (rate(stack_llm_chat_seconds_bucket[5m])))",
          "legendFormat": "p95 {{stage}}"
        }
      ]
    },
    {
      "id": 7,
      "title": "Embedding throughput per host (texts/s)",
      "type": "timeseries",
      "gridPos": {
        "x": 0,
        "y": 24,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (host) (rate(stack_llm_embedded_texts_total[5m]))",
          "legendFormat": "{{host}}"
        }
      ]
    },
    {
      "id": 8,
      "title": "Chat tokens by direction",
      "type": "timeseries",
      "gridPos": {
        "x": 12,
        "y": 24,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (direction) (rate(stack_llm_chat_tokens_total[5m]))",
          "legendFormat": "{{direction}}"
        }
      ]
    },
    {
      "id": 9,
      "title": "Indexed chunks per collection",
      "type": "timeseries",
      "gridPos": {
        "x": 0,
        "y": 32,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (collection) (rate(stack_llm_indexed_chunks_total[5m]))",
          "legendFormat": "{{collection}}"
        }
      ]
    },
    {
      "id": 10,
      "title": "Indexed items (indexed vs skipped)",
      "type": "timeseries",
      "gridPos": {
        "x": 12,
        "y": 32,
        "w": 12,
        "h": 8
      },
      "datasource": {
        "uid": "prometheus"
      },
      "targets": [
        {
          "expr": "sum by (collection, outcome) (rate(stack_llm_indexed_items_total[5m]))",
          "legendFormat": "{{collection}} {{outcome}}"
        }
      ]
    },
    {
      "id": 11,
      "title": "LLM service log tail",
      "type": "logs",
      "gridPos": {
        "x": 0,
        "y": 40,
        "w": 24,
        "h": 8
      },
      "datasource": {
        "uid": "loki"
      },
      "targets": [
        {
          "expr": "{container=\"llm\"}"
        }
      ]
    }
  ]
}