Merge pull request #338 from Srushti-Kamble14/feat/grafana-dashboard-templates

grafana_dashboard.json

@@ -0,0 +1,1025 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "System monitoring dashboard for PDF-Assistant-RAG covering API latency, LLM token usage, active users, request volume, error rate, and backend memory.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "panels": [],
+      "title": "Service Overview",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "decimals": 0,
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 500
+              },
+              {
+                "color": "red",
+                "value": 1500
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 0,
+        "y": 1
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{handler=~\"$handler\"}[$__rate_interval])) by (le)) * 1000",
+          "legendFormat": "p95 latency",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "API p95 Latency",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "decimals": 2,
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "blue",
+                "value": null
+              }
+            ]
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 6,
+        "y": 1
+      },
+      "id": 3,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(http_requests_total{handler=~\"$handler\"}[$__rate_interval]))",
+          "legendFormat": "requests/sec",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "API Throughput",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Requires an application counter named llm_tokens_total with labels such as direction=\"input|output\".",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "continuous-BlPu"
+          },
+          "decimals": 0,
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "purple",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 12,
+        "y": 1
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(llm_tokens_total[$__rate_interval])) * 60",
+          "legendFormat": "tokens/min",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "LLM Tokens / min",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Requires an application gauge named active_users.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "continuous-GrYlRd"
+          },
+          "decimals": 0,
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 100
+              },
+              {
+                "color": "red",
+                "value": 500
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 18,
+        "y": 1
+      },
+      "id": 5,
+      "options": {
+        "colorMode": "background",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(active_users)",
+          "legendFormat": "active users",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Active Users",
+      "type": "stat"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 5
+      },
+      "id": 6,
+      "panels": [],
+      "title": "API Health",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 18,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 6
+      },
+      "id": 7,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "max"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.50, sum(rate(http_request_duration_seconds_bucket{handler=~\"$handler\"}[$__rate_interval])) by (le)) * 1000",
+          "legendFormat": "p50",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket{handler=~\"$handler\"}[$__rate_interval])) by (le)) * 1000",
+          "legendFormat": "p95",
+          "range": true,
+          "refId": "B"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket{handler=~\"$handler\"}[$__rate_interval])) by (le)) * 1000",
+          "legendFormat": "p99",
+          "range": true,
+          "refId": "C"
+        }
+      ],
+      "title": "API Latency Percentiles",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 6
+      },
+      "id": 8,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(http_requests_total{handler=~\"$handler\"}[$__rate_interval])) by (handler)",
+          "legendFormat": "{{handler}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Request Rate by Route",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 25,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 1
+              },
+              {
+                "color": "red",
+                "value": 5
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 0,
+        "y": 14
+      },
+      "id": 9,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "max"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "100 * sum(rate(http_requests_total{handler=~\"$handler\", status=~\"5..\"}[$__rate_interval])) / clamp_min(sum(rate(http_requests_total{handler=~\"$handler\"}[$__rate_interval])), 0.001)",
+          "legendFormat": "5xx error rate",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "API Error Rate",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "align": "auto",
+            "cellOptions": {
+              "type": "color-background"
+            },
+            "inspect": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 500
+              },
+              {
+                "color": "red",
+                "value": 1500
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 12,
+        "y": 14
+      },
+      "id": 10,
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, sum(rate(http_request_duration_seconds_sum{handler=~\"$handler\"}[$__rate_interval])) by (handler) / clamp_min(sum(rate(http_request_duration_seconds_count{handler=~\"$handler\"}[$__rate_interval])) by (handler), 0.001) * 1000)",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{handler}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Slowest Routes - Average Latency",
+      "type": "table"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 21
+      },
+      "id": 11,
+      "panels": [],
+      "title": "LLM and User Activity",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Requires llm_tokens_total. Suggested labels: direction, model, route.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 25,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 22
+      },
+      "id": 12,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "sum"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(rate(llm_tokens_total[$__rate_interval])) by (direction) * 60",
+          "legendFormat": "{{direction}} tokens/min",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "LLM Token Usage by Direction",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "Requires active_users gauge. Optional labels such as auth_provider or plan are supported.",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "continuous-GrYlRd"
+          },
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 30,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 22
+      },
+      "id": 13,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "max"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "sum(active_users)",
+          "legendFormat": "active users",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Active Users Over Time",
+      "type": "timeseries"
+    },
+    {
+      "collapsed": false,
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 30
+      },
+      "id": 14,
+      "panels": [],
+      "title": "Runtime",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "opacity",
+            "lineInterpolation": "smooth",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "showPoints": "never",
+            "spanNulls": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "decbytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 0,
+        "y": 31
+      },
+      "id": 15,
+      "options": {
+        "legend": {
+          "calcs": [
+            "lastNotNull",
+            "max"
+          ],
+          "displayMode": "table",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "app_process_resident_memory_bytes",
+          "legendFormat": "backend RSS",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Backend Memory",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "red",
+                "value": null
+              },
+              {
+                "color": "green",
+                "value": 1
+              }
+            ]
+          },
+          "unit": "none"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 7,
+        "w": 12,
+        "x": 12,
+        "y": 31
+      },
+      "id": 16,
+      "options": {
+        "displayMode": "lcd",
+        "maxVizHeight": 300,
+        "minVizHeight": 16,
+        "minVizWidth": 8,
+        "namePlacement": "auto",
+        "orientation": "horizontal",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showUnfilled": true,
+        "sizing": "auto",
+        "valueMode": "color"
+      },
+      "pluginVersion": "10.4.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "editorMode": "code",
+          "expr": "up",
+          "legendFormat": "{{job}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Prometheus Target Health",
+      "type": "bargauge"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "pdf-assistant-rag",
+    "fastapi",
+    "prometheus",
+    "llm",
+    "rag"
+  ],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": false,
+          "text": "Prometheus",
+          "value": "prometheus"
+        },
+        "hide": 0,
+        "includeAll": false,
+        "label": "Prometheus",
+        "multi": false,
+        "name": "DS_PROMETHEUS",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "regex": "",
+        "type": "datasource"
+      },
+      {
+        "allValue": ".*",
+        "current": {
+          "selected": true,
+          "text": "All",
+          "value": "$__all"
+        },
+        "datasource": {
+          "type": "prometheus",
+          "uid": "${DS_PROMETHEUS}"
+        },
+        "definition": "label_values(http_requests_total, handler)",
+        "hide": 0,
+        "includeAll": true,
+        "label": "Route",
+        "multi": true,
+        "name": "handler",
+        "options": [],
+        "query": {
+          "query": "label_values(http_requests_total, handler)",
+          "refId": "PrometheusVariableQueryEditor-VariableQuery"
+        },
+        "refresh": 2,
+        "regex": "",
+        "sort": 1,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "timepicker": {
+    "refresh_intervals": [
+      "10s",
+      "30s",
+      "1m",
+      "5m",
+      "15m"
+    ]
+  },
+  "timezone": "browser",
+  "title": "PDF-Assistant-RAG System Monitoring",
+  "uid": "pdf-assistant-rag-system-monitoring",
+  "version": 1,
+  "weekStart": ""
+}