Merge branch 'main' into hotfix

Author: VishalS-Microsoft

.github/workflows/deploy-waf.yml

@@ -21,7 +21,7 @@ jobs:
           export AZURE_TENANT_ID=${{ secrets.AZURE_TENANT_ID }}
           export AZURE_CLIENT_SECRET=${{ secrets.AZURE_CLIENT_SECRET }}
           export AZURE_SUBSCRIPTION_ID="${{ secrets.AZURE_SUBSCRIPTION_ID }}"
-          export GPT_MIN_CAPACITY="50"
+          export GPT_MIN_CAPACITY="140"
           export AZURE_REGIONS="${{ vars.AZURE_REGIONS }}"
 
           chmod +x infra/scripts/checkquota.sh

infra/main.bicep

@@ -144,7 +144,7 @@ param aiFoundryAiServicesConfiguration aiServicesConfigurationType = {
   sku: 'S0'
   deployments: null //Default value set on module configuration
   subnetResourceId: null //Default value set on module configuration
-  modelCapacity: 140
+  modelCapacity: 50
 }
 
 @description('Optional. The configuration to apply for the AI Foundry Storage Account resource.')
@@ -749,7 +749,7 @@ var aiFoundryAiServicesModelDeployment = {
   sku: {
     name: modelDeploymentType
     //Curently the capacity is set to 140 for opinanal performance. 
-    capacity: aiFoundryAiServicesConfiguration.?modelCapacity ?? 140
+    capacity: aiFoundryAiServicesConfiguration.?modelCapacity ?? 50
   }
   raiPolicyName: 'Microsoft.Default'
 }

src/backend/app_kernel.py

@@ -38,7 +38,7 @@
 connection_string = os.getenv("APPLICATIONINSIGHTS_CONNECTION_STRING")
 if connection_string:
     # Configure Application Insights if the Instrumentation Key is found
-    configure_azure_monitor(connection_string=connection_string)
+    #configure_azure_monitor(connection_string=connection_string)
     logging.info(
         "Application Insights configured with the provided Instrumentation Key"
     )