Merge pull request #149 from microsoft/psl-azdquotacheck

feat: Added code changes related azd quota check

Author: Roopan-Microsoft

.github/workflows/deploy.yml

@@ -95,7 +95,7 @@ jobs:
             --template-file infra/main.bicep \
             --parameters \
                 Prefix="${{ env.SOLUTION_PREFIX }}" \
-                AzureAiServiceLocation="eastus" \
+                aiDeploymentsLocation="eastus" \
                 capacity=${{ env.GPT_MIN_CAPACITY }} \
                 imageVersion="${IMAGE_TAG}"\
             --debug

azure.yaml

@@ -18,19 +18,3 @@ deployment:
     AzureAiServiceLocation: ${{ parameters.AzureAiServiceLocation }}
     Prefix: ${{ parameters.Prefix }}
     baseUrl: ${{ parameters.baseUrl }}
-hooks:
-  preprovision:
-    posix:
-      shell: sh
-      run: >
-        chmod u+r+x ./scripts/validate_model_deployment_quota.sh; chmod u+r+x ./scripts/validate_model_quota.sh; ./scripts/validate_model_deployment_quota.sh --SubscriptionId "$AZURE_SUBSCRIPTION_ID" --Location "${AZURE_AISERVICE_LOCATION:-japaneast}" --ModelsParameter "aiModelDeployments"
-      interactive: false
-      continueOnError: false
-
-    windows:
-      shell: pwsh
-      run: >
-        $location = if ($env:AZURE_AISERVICE_LOCATION) { $env:AZURE_AISERVICE_LOCATION } else { "japaneast" };
-        ./scripts/validate_model_deployment_quota.ps1 -SubscriptionId $env:AZURE_SUBSCRIPTION_ID -Location $location -ModelsParameter "aiModelDeployments"
-      interactive: false
-      continueOnError: false

infra/main.bicep

@@ -2,6 +2,9 @@ metadata name = 'Modernize Your Code Solution Accelerator'
 metadata description = '''CSA CTO Gold Standard Solution Accelerator for Modernize Your Code. 
 '''
 
+@description('Set to true if you want to deploy WAF-aligned infrastructure.')
+param useWafAlignedArchitecture bool
+
 @minLength(3)
 @maxLength(16)
 @description('Required. A unique application/solution name for all resources in this deployment. This should be 3-16 characters long.')
@@ -29,19 +32,25 @@ param location string = resourceGroup().location
   'westus'
   'westus3'
 ])
-@metadata({ azd: { type: 'location' } })
+@metadata({
+  azd : {
+    type: 'location'
+    usageName : [
+      'OpenAI.GlobalStandard.gpt-4o, 150'
+    ]
+  }
+})
 @description('Optional. Location for all AI service resources. This location can be different from the resource group location.')
-param azureAiServiceLocation string = location
-
+param aiDeploymentsLocation string
 
-@description('Optional. AI model deployment token capacity. Defaults to 5K tokens per minute.')
-param capacity int = 5 // was 5 before = 5K
+@description('Optional. AI model deployment token capacity. Defaults to 150K tokens per minute.')
+param capacity int = 150
 
 @description('Optional. Enable monitoring for the resources. This will enable Application Insights and Log Analytics. Defaults to false.')
-param enableMonitoring bool = false
+param enableMonitoring bool = useWafAlignedArchitecture? true : false
 
 @description('Optional. Enable scaling for the container apps. Defaults to false.')
-param enableScaling bool = false
+param enableScaling bool = useWafAlignedArchitecture? true : false
 
 @description('Optional. Enable redundancy for applicable resources. Defaults to false.')
 param enableRedundancy bool = false
@@ -50,7 +59,7 @@ param enableRedundancy bool = false
 param secondaryLocation string?
 
 @description('Optional. Enable private networking for the resources. Set to true to enable private networking. Defaults to false.')
-param enablePrivateNetworking bool = false
+param enablePrivateNetworking bool = useWafAlignedArchitecture? true : false
 
 @description('Optional. Admin username for the Jumpbox Virtual Machine. Set to custom value if enablePrivateNetworking is true.')
 @secure()
@@ -210,7 +219,7 @@ module aiServices 'modules/ai-foundry/main.bicep' = {
   dependsOn: [logAnalyticsWorkspace, network] // required due to optional flags that could change dependency
   params: {
     name: 'ais-${resourcesName}'
-    location: azureAiServiceLocation
+    location: aiDeploymentsLocation
     sku: 'S0'
     kind: 'AIServices'
     deployments: [modelDeployment]

infra/main.bicepparam

@@ -2,9 +2,39 @@
   "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentParameters.json#",
   "contentVersion": "1.0.0.0",
   "parameters": {
+    "solutionName": {
+      "value": "${AZURE_ENV_NAME}"
+    },
     "location": {
       "value": "${AZURE_LOCATION}"
     },
+    "deploymentType": {
+      "value": "${AZURE_ENV_MODEL_DEPLOYMENT_TYPE}"
+    },
+    "llmModel": {
+      "value": "${AZURE_ENV_MODEL_NAME}"
+    },
+    "capacity": {
+      "value": "${AZURE_ENV_MODEL_CAPACITY}"
+    },
+    "gptModelVersion": {
+      "value": "${AZURE_ENV_MODEL_VERSION}"
+    },
+    "imageVersion": {
+      "value": "${AZURE_ENV_IMAGETAG}"
+    },
+    "existingLogAnalyticsWorkspaceId": {
+      "value": "${AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID}"
+    },
+    "secondaryLocation": {
+      "value": "${AZURE_ENV_COSMOS_SECONDARY_LOCATION}"
+    },
+    "vmAdminUsername": {
+      "value": "${AZURE_ENV_JUMPBOX_ADMIN_USERNAME}"
+    },
+    "vmAdminPassword": {
+      "value": "${AZURE_ENV_JUMPBOX_ADMIN_PASSWORD}"
+    },
     "backendExists": {
       "value": "${SERVICE_BACKEND_RESOURCE_EXISTS=false}"
     },