From 25252fc709b920fefbf8202c5328166ea83cc233 Mon Sep 17 00:00:00 2001
From: Marcel <marcel@familienarchiv>
Date: Sat, 6 Jun 2026 13:55:07 +0200
Subject: [PATCH] feat(observability): add Grafana Ollama inference latency
 dashboard (#737)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 .../provisioning/dashboards/ollama.json       | 218 ++++++++++++++++++
 1 file changed, 218 insertions(+)
 create mode 100644 infra/observability/grafana/provisioning/dashboards/ollama.json

diff --git a/infra/observability/grafana/provisioning/dashboards/ollama.json b/infra/observability/grafana/provisioning/dashboards/ollama.json
new file mode 100644
index 00000000..47536e2d
--- /dev/null
+++ b/infra/observability/grafana/provisioning/dashboards/ollama.json
@@ -0,0 +1,218 @@
+{
+  "id": null,
+  "uid": "ollama-dashboard",
+  "title": "Ollama",
+  "description": "Ollama inference latency and request rate",
+  "version": 1,
+  "schemaVersion": 39,
+  "tags": ["ollama", "inference"],
+  "timezone": "browser",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "links": [],
+  "liveNow": false,
+  "refresh": "30s",
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "weekStart": "",
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": { "type": "datasource", "uid": "grafana" },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "timeseries",
+      "title": "Inference Latency p50",
+      "description": "50th percentile of Ollama request duration over a 5-minute window",
+      "gridPos": { "h": 8, "w": 8, "x": 0, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "red", "value": 80 }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "list", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "single", "sort": "none" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.5, rate(ollama_request_duration_seconds_bucket[5m]))",
+          "instant": false,
+          "legendFormat": "p50",
+          "range": true,
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Inference Latency p95",
+      "description": "95th percentile of Ollama request duration over a 5-minute window",
+      "gridPos": { "h": 8, "w": 8, "x": 8, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "red", "value": 80 }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "list", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "single", "sort": "none" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "editorMode": "code",
+          "expr": "histogram_quantile(0.95, rate(ollama_request_duration_seconds_bucket[5m]))",
+          "instant": false,
+          "legendFormat": "p95",
+          "range": true,
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Request Rate",
+      "description": "Ollama requests per second over a 5-minute window",
+      "gridPos": { "h": 8, "w": 8, "x": 16, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "fieldConfig": {
+        "defaults": {
+          "color": { "mode": "palette-classic" },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": { "legend": false, "tooltip": false, "viz": false },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": { "type": "linear" },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": { "group": "A", "mode": "none" },
+            "thresholdsStyle": { "mode": "off" }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "red", "value": 80 }
+            ]
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": { "calcs": ["mean", "max"], "displayMode": "list", "placement": "bottom", "showLegend": true },
+        "tooltip": { "mode": "single", "sort": "none" }
+      },
+      "targets": [
+        {
+          "datasource": { "type": "prometheus", "uid": "prometheus" },
+          "editorMode": "code",
+          "expr": "rate(ollama_requests_total[5m])",
+          "instant": false,
+          "legendFormat": "req/s",
+          "range": true,
+          "refId": "A"
+        }
+      ]
+    }
+  ],
+  "preload": false,
+  "templating": {
+    "list": []
+  }
+}