Adding observability notebook (#96)

Author: jam-jee

examples/observability/observability.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b5f69c26-af46-4380-9df0-bea0f6e4963c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sagemaker.hyperpod.utils import get_monitoring_config, is_observability_addon_enabled"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6a86998a-59dc-46e5-9aa7-33d5386b16f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "monitor_config = get_monitoring_config()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "15fffc00-d8d0-44e2-98b4-005e654e3cf4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://g-b4a6fed76b.grafana-workspace.us-west-2.amazonaws.com/d/aws-sm-hp-observability-cluster-v1_0'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "monitor_config.grafanaURL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "14c00535-7274-48ac-8c94-9fa10bbf2324",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'https://aps-workspaces.us-west-2.amazonaws.com/workspaces/ws-e372a1c1-d909-45f8-9c0d-d0912095f4d6'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "monitor_config.prometheusURL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42d930cb-7655-4409-99c9-e0240d4346a0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/sagemaker/hyperpod/utils.py

@@ -44,10 +44,21 @@ def get_monitoring_config() -> Optional[MonitoringConfig]:
     response = boto3.client("eks").describe_addon(clusterName=eks_cluster_name, addonName=AMAZON_HYPERPOD_OBSERVABILITY)
     config_values = yaml.safe_load(response['addon']['configurationValues'])
 
-    prometheus_url = config_values['ampWorkspace']['prometheusEndpoint']
-    region = get_hyperpod_cluster_region()
-    workspace_arn = config_values['amgWorkspace']['arn']
-    grafana_url = build_grafana_url(get_grafana_ws_name_from_arn(workspace_arn), region, GRAFANA_DASHBOARD_UID)
-    metrics_data = config_values['metricsProvider']
+    try:
+        prometheus_url = config_values['ampWorkspace']['prometheusEndpoint']
+    except KeyError:
+        prometheus_url = None
+    try:
+        region = get_hyperpod_cluster_region()
+        workspace_arn = config_values['amgWorkspace']['arn']
+        grafana_url = build_grafana_url(
+            get_grafana_ws_name_from_arn(workspace_arn) if workspace_arn else "default-workspace", region,
+            GRAFANA_DASHBOARD_UID)
+    except KeyError:
+        grafana_url = None
+    try:
+        metrics_data = config_values['metricsProvider']
+    except KeyError:
+        metrics_data = None
 
     return MonitoringConfig(grafanaURL=grafana_url, prometheusURL=prometheus_url, availableMetrics=metrics_data)