{
  "annotations": {
    "list": []
  },
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 0,
  "id": null,
  "links": [],
  "liveNow": false,
  "panels": [
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "showPoints": "auto",
            "fillOpacity": 10
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          }
        }
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 0
      },
      "id": 1,
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "llama_stack_completion_tokens_total",
          "legendFormat": "{{model_id}} ({{provider_id}})",
          "refId": "A"
        }
      ],
      "title": "Completion Tokens",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "showPoints": "auto",
            "fillOpacity": 10
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          }
        }
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 0
      },
      "id": 2,
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "llama_stack_prompt_tokens_total",
          "legendFormat": "Prompt - {{model_id}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "llama_stack_tokens_total",
          "legendFormat": "Total - {{model_id}}",
          "refId": "B"
        }
      ],
      "title": "Prompt & Total Tokens",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "showPoints": "auto",
            "fillOpacity": 10
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "ms"
        }
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 8
      },
      "id": 3,
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "histogram_quantile(0.95, rate(llama_stack_http_server_duration_milliseconds_bucket[5m]))",
          "legendFormat": "p95",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "histogram_quantile(0.99, rate(llama_stack_http_server_duration_milliseconds_bucket[5m]))",
          "legendFormat": "p99",
          "refId": "B"
        }
      ],
      "title": "HTTP Request Duration (p95, p99)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          }
        }
      },
      "gridPos": {
        "h": 8,
        "w": 6,
        "x": 12,
        "y": 8
      },
      "id": 4,
      "options": {
        "colorMode": "value",
        "graphMode": "area",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "sum(llama_stack_http_server_duration_milliseconds_count)",
          "refId": "A"
        }
      ],
      "title": "Total Requests",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          }
        }
      },
      "gridPos": {
        "h": 8,
        "w": 6,
        "x": 18,
        "y": 8
      },
      "id": 5,
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "justifyMode": "auto",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "lastNotNull"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "auto"
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "sum(llama_stack_http_server_active_requests)",
          "refId": "A"
        }
      ],
      "title": "Active Requests",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "showPoints": "auto",
            "fillOpacity": 10
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "reqps"
        }
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 16
      },
      "id": 6,
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "rate(llama_stack_http_server_duration_milliseconds_count[5m])",
          "legendFormat": "{{http_target}} - {{http_status_code}}",
          "refId": "A"
        }
      ],
      "title": "Request Rate",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "prometheus"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "showPoints": "auto",
            "fillOpacity": 10
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              }
            ]
          },
          "unit": "Bps"
        }
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 16
      },
      "id": 7,
      "options": {
        "legend": {
          "calcs": [],
          "displayMode": "list",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "none"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "rate(llama_stack_http_server_request_size_bytes_sum[5m])",
          "legendFormat": "Request",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "prometheus"
          },
          "expr": "rate(llama_stack_http_server_response_size_bytes_sum[5m])",
          "legendFormat": "Response",
          "refId": "B"
        }
      ],
      "title": "Request/Response Sizes",
      "type": "timeseries"
    }
  ],
  "refresh": "5s",
  "schemaVersion": 38,
  "tags": [
    "llama-stack"
  ],
  "templating": {
    "list": []
  },
  "time": {
    "from": "now-15m",
    "to": "now"
  },
  "timepicker": {},
  "timezone": "browser",
  "title": "Llama Stack Metrics",
  "uid": "llama-stack-metrics",
  "version": 0,
  "weekStart": ""
}