Rename capacity parameters to match deployment usage

- Rename gptModelCapacity to gptDeploymentCapacity
- Rename embeddingModelCapacity to embeddingDeploymentCapacity
- Update all references in bicep, parameter files, and CI workflow
- Regenerate main.json from bicep template

This aligns parameter names with their actual usage as deploymentCapacity
and matches the environment variable naming convention.

Author: Prachig-Microsoft

.github/workflows/CI.yml

@@ -208,10 +208,10 @@ jobs:
                 azureAiServiceLocation=${{ env.AZURE_LOCATION }} \
                 gptModelDeploymentType="GlobalStandard" \
                 gptModelName="gpt-4.1-mini" \
-                gptModelCapacity=${{ env.GPT_CAPACITY }} \
+                gptDeploymentCapacity=${{ env.GPT_CAPACITY }} \
                 gptModelVersion="2025-04-14" \
                 embeddingModelName="text-embedding-3-large" \
-                embeddingModelCapacity=${{ env.TEXT_EMBEDDING_CAPACITY }} \
+                embeddingDeploymentCapacity=${{ env.TEXT_EMBEDDING_CAPACITY }} \
                 embeddingModelVersion="1" \
                 enablePrivateNetworking=false \
                 enableMonitoring=false \

infra/main.bicep

@@ -43,7 +43,7 @@ param gptModelVersion string = '2025-04-14'
 
 @description('Optional. Capacity of the GPT model deployment:')
 @minValue(10)
-param gptModelCapacity int = 100
+param gptDeploymentCapacity int = 100
 
 @minLength(1)
 @description('Optional. Name of the Text Embedding model to deploy:')
@@ -57,7 +57,7 @@ param embeddingModelVersion string = '1'
 
 @description('Optional. Capacity of the Text Embedding model deployment:')
 @minValue(10)
-param embeddingModelCapacity int = 100
+param embeddingDeploymentCapacity int = 100
 
 @description('Optional: Existing Log Analytics Workspace Resource ID')
 param existingLogAnalyticsWorkspaceId string = ''
@@ -164,14 +164,14 @@ var gptModelDeployment = {
   modelName: gptModelName
   deploymentName: gptModelName
   deploymentVersion: gptModelVersion
-  deploymentCapacity: gptModelCapacity
+  deploymentCapacity: gptDeploymentCapacity
 }
 
 var embeddingModelDeployment = {
   modelName: embeddingModelName
   deploymentName: embeddingModelName
   deploymentVersion: embeddingModelVersion
-  deploymentCapacity: embeddingModelCapacity
+  deploymentCapacity: embeddingDeploymentCapacity
 }
 
 var openAiDeployments = [

infra/main.json

@@ -6,7 +6,7 @@
     "_generator": {
       "name": "bicep",
       "version": "0.42.1.51946",
-      "templateHash": "14044897368623114174"
+      "templateHash": "6929838218794441010"
     }
   },
   "parameters": {
@@ -64,7 +64,7 @@
         "description": "Optional. Version of the GPT model to deploy."
       }
     },
-    "gptModelCapacity": {
+    "gptDeploymentCapacity": {
       "type": "int",
       "defaultValue": 100,
       "minValue": 10,
@@ -90,7 +90,7 @@
         "description": "Optional. Version of the Text Embedding model to deploy."
       }
     },
-    "embeddingModelCapacity": {
+    "embeddingDeploymentCapacity": {
       "type": "int",
       "defaultValue": 100,
       "minValue": 10,
@@ -226,13 +226,13 @@
       "modelName": "[parameters('gptModelName')]",
       "deploymentName": "[parameters('gptModelName')]",
       "deploymentVersion": "[parameters('gptModelVersion')]",
-      "deploymentCapacity": "[parameters('gptModelCapacity')]"
+      "deploymentCapacity": "[parameters('gptDeploymentCapacity')]"
     },
     "embeddingModelDeployment": {
       "modelName": "[parameters('embeddingModelName')]",
       "deploymentName": "[parameters('embeddingModelName')]",
       "deploymentVersion": "[parameters('embeddingModelVersion')]",
-      "deploymentCapacity": "[parameters('embeddingModelCapacity')]"
+      "deploymentCapacity": "[parameters('embeddingDeploymentCapacity')]"
     },
     "openAiDeployments": [
       {
@@ -26702,6 +26702,10 @@
           },
           "keyValues": {
             "value": [
+              {
+                "name": "ApplicationInsights:ConnectionString",
+                "value": "[if(parameters('enableMonitoring'), reference('applicationInsights').outputs.connectionString.value, '')]"
+              },
               {
                 "name": "Application:AIServices:GPT-4o-mini:Endpoint",
                 "value": "[reference('avmOpenAi').outputs.endpoint.value]"
@@ -28778,6 +28782,7 @@
         }
       },
       "dependsOn": [
+        "applicationInsights",
         "avmCosmosDB",
         "avmOpenAi",
         "avmSearchSearchServices",
@@ -36561,8 +36566,8 @@
         }
       },
       "dependsOn": [
-        "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').storageQueue)]",
         "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').storageBlob)]",
+        "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').storageQueue)]",
         "userAssignedIdentity",
         "virtualNetwork"
       ]
@@ -42285,8 +42290,8 @@
       },
       "dependsOn": [
         "avmOpenAi",
-        "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').openAI)]",
         "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').cognitiveServices)]",
+        "[format('avmPrivateDnsZones[{0}]', variables('dnsZoneIndex').openAI)]",
         "virtualNetwork"
       ]
     },
@@ -49866,6 +49871,27 @@
         "description": "Contains Azure OpenAI Embedding Model Deployment Name."
       },
       "value": "[variables('embeddingModelDeployment').deploymentName]"
+    },
+    "APPLICATIONINSIGHTS_CONNECTION_STRING": {
+      "type": "string",
+      "metadata": {
+        "description": "Contains Application Insights Connection String."
+      },
+      "value": "[if(parameters('enableMonitoring'), reference('applicationInsights').outputs.connectionString.value, '')]"
+    },
+    "APPLICATIONINSIGHTS_INSTRUMENTATION_KEY": {
+      "type": "string",
+      "metadata": {
+        "description": "Contains Application Insights Instrumentation Key."
+      },
+      "value": "[if(parameters('enableMonitoring'), reference('applicationInsights').outputs.instrumentationKey.value, '')]"
+    },
+    "APPLICATIONINSIGHTS_NAME": {
+      "type": "string",
+      "metadata": {
+        "description": "Contains Application Insights Name."
+      },
+      "value": "[if(parameters('enableMonitoring'), reference('applicationInsights').outputs.name.value, '')]"
     }
   }
 }

infra/main.parameters.json

@@ -17,7 +17,7 @@
     "gptModelName": {
       "value": "${AZURE_ENV_GPT_MODEL_NAME}"
     },
-    "gptModelCapacity": {
+    "gptDeploymentCapacity": {
       "value": "${AZURE_ENV_GPT_MODEL_CAPACITY}"
     },
     "gptModelVersion": {
@@ -29,7 +29,7 @@
     "embeddingModelVersion": {
       "value": "${AZURE_ENV_EMBEDDING_MODEL_VERSION}"
     },
-    "embeddingModelCapacity": {
+    "embeddingDeploymentCapacity": {
       "value": "${AZURE_ENV_EMBEDDING_DEPLOYMENT_CAPACITY}"
     },
     "existingLogAnalyticsWorkspaceId": {

infra/main.waf.parameters.json

@@ -17,7 +17,7 @@
     "gptModelName": {
       "value": "${AZURE_ENV_GPT_MODEL_NAME}"
     },
-    "gptModelCapacity": {
+    "gptDeploymentCapacity": {
       "value": "${AZURE_ENV_GPT_MODEL_CAPACITY}"
     },
     "gptModelVersion": {
@@ -29,7 +29,7 @@
     "embeddingModelVersion": {
       "value": "${AZURE_ENV_EMBEDDING_MODEL_VERSION}"
     },
-    "embeddingModelCapacity": {
+    "embeddingDeploymentCapacity": {
       "value": "${AZURE_ENV_EMBEDDING_DEPLOYMENT_CAPACITY}"
     },
     "existingLogAnalyticsWorkspaceId": {