V gsampath/get started notebook----quickstart

.github/workflows/tutorials-get-started-notebooks-quickstart.yml

@@ -79,6 +79,15 @@ jobs:
           az account get-access-token --scope https://management.azure.com/.default --output none
           # ML
           az account get-access-token --scope https://ml.azure.com/.default --output none
+    - name: delete stale online endpoints
+      run: |
+          source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh";
+          source "${{ github.workspace }}/infra/bootstrapping/init_environment.sh";
+          for ep in $(az ml online-endpoint list --query "[].name" -o tsv | grep "^credit-endpoint-"); do
+            echo "Deleting stale endpoint: $ep";
+            az ml online-endpoint delete -n "$ep" -y --no-wait || true;
+          done
+      continue-on-error: true
     - name: run get-started-notebooks/quickstart.ipynb
       run: |
           source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh";
@@ -88,6 +97,21 @@ jobs:
           [ -f "../../.azureml/config" ] && cat "../../.azureml/config";
           papermill -k python quickstart.ipynb quickstart.output.ipynb
       working-directory: tutorials/get-started-notebooks
+    - name: collect endpoint logs on failure
+      if: ${{ failure() }}
+      run: |
+          source "${{ github.workspace }}/infra/bootstrapping/sdk_helpers.sh";
+          source "${{ github.workspace }}/infra/bootstrapping/init_environment.sh";
+          endpoint_name=$(az ml online-endpoint list --query "[?starts_with(name, 'credit-endpoint-')]|sort_by(@,&properties.creation_context.created_at)[-1].name" -o tsv);
+          if [ -z "$endpoint_name" ]; then
+            echo "No credit-endpoint-* endpoints found for log collection.";
+            exit 0;
+          fi
+          echo "Collecting logs for endpoint: $endpoint_name";
+          az ml online-deployment list -e "$endpoint_name" --query "[].name" -o tsv;
+          az ml online-deployment get -n blue -e "$endpoint_name" --query "{provisioning_state:provisioning_state,status:status,errors:errors}" -o json || true;
+          az ml online-deployment logs -n blue -e "$endpoint_name" --lines 200 || true;
+      continue-on-error: true
     - name: upload notebook's working folder as an artifact
       if: ${{ always() }}
       uses: ./.github/actions/upload-artifact

infra/scripts/remove_role_assignments.ps1

@@ -23,7 +23,7 @@ try
     Write-Output "Pre-checking the RoleAssignment count..."
     Get-RoleAssignmentCount
     # Remove only limited RoleDefinitions
-    $staleRoleAssignments = Get-AzRoleAssignment -ResourceGroupName "$ResourceGroupName" | Where-Object {($_.ObjectType -eq $OBJTYPE) -and ($_.RoleDefinitionName -match "Storage Blob Data Reader|AzureML Metrics Writer \(preview\)|AcrPull")}
+    $staleRoleAssignments = Get-AzRoleAssignment -ResourceGroupName "$ResourceGroupName" | Where-Object {($_.ObjectType -eq $OBJTYPE) -and ($_.RoleDefinitionName -match "Storage Blob Data Reader|AzureML Metrics Writer \(preview\)|AcrPull|AzureML Compute Operator|Contributor")}
     $unknownRoleAssignmentCount = $staleRoleAssignments.Count
     Write-Output "Initiating the cleanup of unknownRole in the ResourceGroup:$ResourceGroupName having count as $unknownRoleAssignmentCount..."
     $staleRoleAssignments | Remove-AzRoleAssignment

tutorials/get-started-notebooks/pipeline.ipynb

@@ -234,10 +234,12 @@
     "  - scipy=1.7.1\n",
     "  - pandas>=1.1,<1.2\n",
     "  - pip:\n",
-    "    - inference-schema[numpy-support]==1.3.0\n",
+    "    - inference-schema[numpy-support]==1.8.0\n",
     "    - xlrd==2.0.1\n",
-    "    - mlflow== 2.4.1\n",
-    "    - azureml-mlflow==1.51.0"
+    "    - mlflow==2.16.2\n",
+    "    - azureml-mlflow==1.51.0\n",
+    "    - azureml-ai-monitoring\n",
+    "    - azureml-inference-server-http==1.3.4"
    ]
   },
   {
@@ -269,20 +271,26 @@
     "from azure.ai.ml.entities import Environment\n",
     "\n",
     "custom_env_name = \"aml-scikit-learn\"\n",
-    "\n",
-    "pipeline_job_env = Environment(\n",
-    "    name=custom_env_name,\n",
-    "    description=\"Custom environment for Credit Card Defaults pipeline\",\n",
-    "    tags={\"scikit-learn\": \"0.24.2\"},\n",
-    "    conda_file=os.path.join(dependencies_dir, \"conda.yaml\"),\n",
-    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:latest\",\n",
-    "    version=\"0.2.0\",\n",
-    ")\n",
-    "pipeline_job_env = ml_client.environments.create_or_update(pipeline_job_env)\n",
-    "\n",
-    "print(\n",
-    "    f\"Environment with name {pipeline_job_env.name} is registered to workspace, the environment version is {pipeline_job_env.version}\"\n",
-    ")"
+    "env_version = \"0.2.0\"\n",
+    "\n",
+    "# Check if the environment already exists\n",
+    "try:\n",
+    "    pipeline_job_env = ml_client.environments.get(name=custom_env_name, version=env_version)\n",
+    "    print(f\"Environment with name {pipeline_job_env.name} already exists, using existing version {pipeline_job_env.version}\")\n",
+    "except Exception:\n",
+    "    # If it doesn't exist, create it\n",
+    "    pipeline_job_env = Environment(\n",
+    "        name=custom_env_name,\n",
+    "        description=\"Custom environment for Credit Card Defaults pipeline\",\n",
+    "        tags={\"scikit-learn\": \"0.24.2\"},\n",
+    "        conda_file=os.path.join(dependencies_dir, \"conda.yaml\"),\n",
+    "        image=\"mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:latest\",\n",
+    "        version=env_version,\n",
+    "    )\n",
+    "    pipeline_job_env = ml_client.environments.create_or_update(pipeline_job_env)\n",
+    "    print(\n",
+    "        f\"Environment with name {pipeline_job_env.name} is registered to workspace, the environment version is {pipeline_job_env.version}\"\n",
+    "    )"
    ]
   },
   {
@@ -543,6 +551,7 @@
     "import os\n",
     "import pandas as pd\n",
     "import mlflow\n",
+    "import joblib\n",
     "\n",
     "\n",
     "def select_first_file(path):\n",
@@ -560,7 +569,7 @@
     "mlflow.start_run()\n",
     "\n",
     "# enable autologging\n",
-    "mlflow.sklearn.autolog()\n",
+    "mlflow.sklearn.autolog(log_models=False)\n",
     "\n",
     "os.makedirs(\"./outputs\", exist_ok=True)\n",
     "\n",
@@ -607,19 +616,15 @@
     "\n",
     "    print(classification_report(y_test, y_pred))\n",
     "\n",
-    "    # Registering the model to the workspace\n",
-    "    print(\"Registering the model via MLFlow\")\n",
-    "    mlflow.sklearn.log_model(\n",
-    "        sk_model=clf,\n",
-    "        registered_model_name=args.registered_model_name,\n",
-    "        artifact_path=args.registered_model_name,\n",
-    "    )\n",
+    "    print(\"Saving the model to the component output folder\")\n",
+    "    os.makedirs(args.model, exist_ok=True)\n",
     "\n",
-    "    # Saving the model to a file\n",
-    "    mlflow.sklearn.save_model(\n",
-    "        sk_model=clf,\n",
-    "        path=os.path.join(args.model, \"trained_model\"),\n",
-    "    )\n",
+    "    model_path = os.path.join(args.model, \"model.pkl\")\n",
+    "    joblib.dump(clf, model_path)\n",
+    "\n",
+    "    mlflow.log_artifact(model_path, artifact_path=\"model_output\")\n",
+    "\n",
+    "    print(f\"Model saved to: {model_path}\")\n",
     "\n",
     "    # Stop Logging\n",
     "    mlflow.end_run()\n",
@@ -924,9 +929,9 @@
    "name": "python310-sdkv2"
   },
   "kernelspec": {
-   "display_name": "Python 3.10 - SDK v2",
+   "display_name": ".venv",
    "language": "python",
-   "name": "python310-sdkv2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -938,7 +943,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.9.5"
   },
   "nteract": {
    "version": "nteract-front-end@1.0.0"