Merge pull request #288 from microsoft/psl-azdquotacheck

feat: Added code changes related azd quota check

Author: Roopan-Microsoft

azure.yaml

@@ -1,20 +1,4 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/Azure/azure-dev/main/schemas/v1.0/azure.yaml.json
 name: multi-agent-custom-automation-engine-solution-accelerator
 metadata:
-  template: [email protected]
-hooks:
-  preprovision:
-    posix:
-      shell: sh
-      run: >
-        chmod u+r+x ./infra/scripts/validate_model_deployment_quota.sh; chmod u+r+x ./infra/scripts/validate_model_quota.sh; ./infra/scripts/validate_model_deployment_quota.sh --subscription "$AZURE_SUBSCRIPTION_ID" --location "${AZURE_ENV_OPENAI_LOCATION:-swedencentral}" --models-parameter "aiModelDeployments"
-      interactive: false
-      continueOnError: false
-
-    windows:
-      shell: pwsh
-      run: >
-        $location = if ($env:AZURE_ENV_OPENAI_LOCATION) { $env:AZURE_ENV_OPENAI_LOCATION } else { "swedencentral" };
-        ./infra/scripts/validate_model_deployment_quotas.ps1 -SubscriptionId $env:AZURE_SUBSCRIPTION_ID -Location $location -ModelsParameter "aiModelDeployments"
-      interactive: false
-      continueOnError: false
+  template: [email protected]

docs/CustomizingAzdParameters.md

@@ -16,7 +16,7 @@ By default this template will use the environment name as the prefix to prevent
 | `AZURE_ENV_MODEL_VERSION`       | string | `2024-08-06`      | Version of the GPT model to be used for deployment.                                                |
 | `AZURE_ENV_IMAGETAG`            | string | `latest`          | Docker image tag used for container deployments.                                                   |
 | `AZURE_ENV_ENABLE_TELEMETRY`    | bool   | `true`            | Enables telemetry for monitoring and diagnostics.                                                  |
-
+| `AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID` | string  | `<Existing Workspace Id>`     | Set this if you want to reuse an existing Log Analytics Workspace instead of creating a new one.     |
 ---
 
 ## How to Set a Parameter
@@ -27,6 +27,11 @@ To customize any of the above values, run the following command **before** `azd
 azd env set <PARAMETER_NAME> <VALUE>
 ```
 
+Set the Log Analytics Workspace Id if you need to reuse the existing workspace which is already existing
+```shell
+azd env set AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID '/subscriptions/<subscription-id>/resourceGroups/<resource-group>/providers/Microsoft.OperationalInsights/workspaces/<workspace-name>'
+```
+
 **Example:**
 
 ```bash

infra/main.bicep

@@ -1,6 +1,9 @@
 metadata name = 'Multi-Agent Custom Automation Engine'
 metadata description = 'This module contains the resources required to deploy the Multi-Agent Custom Automation Engine solution accelerator for both Sandbox environments and WAF aligned environments.'
 
+@description('Set to true if you want to deploy WAF-aligned infrastructure.')
+param useWafAlignedArchitecture bool
+
 @description('Optional. The prefix to add in the default names given to all deployed Azure resources.')
 @maxLength(19)
 param solutionPrefix string = 'macae${uniqueString(deployer().objectId, deployer().tenantId, subscription().subscriptionId, resourceGroup().id)}'
@@ -11,7 +14,17 @@ param solutionLocation string = resourceGroup().location
 @description('Optional. Enable/Disable usage telemetry for module.')
 param enableTelemetry bool = true
 
+param existingLogAnalyticsWorkspaceId string = ''
+
 // Restricting deployment to only supported Azure OpenAI regions validated with GPT-4o model
+@metadata({
+  azd : {
+    type: 'location'
+    usageName : [
+      'OpenAI.GlobalStandard.gpt-4o, 150'
+    ]
+  }
+})
 @allowed(['australiaeast', 'eastus2', 'francecentral', 'japaneast', 'norwayeast', 'swedencentral', 'uksouth', 'westus'])
 @description('Azure OpenAI Location')
 param azureOpenAILocation string
@@ -26,6 +39,9 @@ param gptModelVersion string = '2024-08-06'
 @description('GPT model deployment type:')
 param modelDeploymentType string = 'GlobalStandard'
 
+@description('Optional. AI model deployment token capacity.')
+param gptModelCapacity int = 150
+
 @description('Set the image tag for the container images used in the solution. Default is "latest".')
 param imageTag string = 'latest'
 
@@ -46,8 +62,8 @@ param logAnalyticsWorkspaceConfiguration logAnalyticsWorkspaceConfigurationType
   location: solutionLocation
   sku: 'PerGB2018'
   tags: tags
-  dataRetentionInDays: 365
-  existingWorkspaceResourceId: ''
+  dataRetentionInDays: useWafAlignedArchitecture ? 365 : 30
+  existingWorkspaceResourceId: existingLogAnalyticsWorkspaceId
 }
 
 @description('Optional. The configuration to apply for the Multi-Agent Custom Automation Engine Application Insights resource.')
@@ -56,7 +72,7 @@ param applicationInsightsConfiguration applicationInsightsConfigurationType = {
   name: 'appi-${solutionPrefix}'
   location: solutionLocation
   tags: tags
-  retentionInDays: 365
+  retentionInDays: useWafAlignedArchitecture ? 365 : 30
 }
 
 @description('Optional. The configuration to apply for the Multi-Agent Custom Automation Engine Managed Identity resource.')
@@ -105,7 +121,7 @@ param networkSecurityGroupAdministrationConfiguration networkSecurityGroupConfig
 
 @description('Optional. The configuration to apply for the Multi-Agent Custom Automation Engine virtual network resource.')
 param virtualNetworkConfiguration virtualNetworkConfigurationType = {
-  enabled: true
+  enabled: useWafAlignedArchitecture ? true : false
   name: 'vnet-${solutionPrefix}'
   location: solutionLocation
   tags: tags
@@ -131,7 +147,7 @@ param virtualMachineConfiguration virtualMachineConfigurationType = {
   location: solutionLocation
   tags: tags
   adminUsername: 'adminuser'
-  adminPassword: guid(solutionPrefix, subscription().subscriptionId)
+  adminPassword: useWafAlignedArchitecture? 'P@ssw0rd1234' : guid(solutionPrefix, subscription().subscriptionId)
   vmSize: 'Standard_D2s_v3'
   subnetResourceId: null //Default value set on module configuration
 }
@@ -144,7 +160,7 @@ param aiFoundryAiServicesConfiguration aiServicesConfigurationType = {
   sku: 'S0'
   deployments: null //Default value set on module configuration
   subnetResourceId: null //Default value set on module configuration
-  modelCapacity: 50
+  modelCapacity: gptModelCapacity
 }
 
 @description('Optional. The configuration to apply for the AI Foundry AI Project resource.')
@@ -199,8 +215,8 @@ param webServerFarmConfiguration webServerFarmConfigurationType = {
   enabled: true
   name: 'asp-${solutionPrefix}'
   location: solutionLocation
-  skuName: 'P1v3'
-  skuCapacity: 3
+  skuName: useWafAlignedArchitecture? 'P1v3' : 'B2'
+  skuCapacity: useWafAlignedArchitecture ? 3 : 1
   tags: tags
 }
 
@@ -729,7 +745,7 @@ var aiFoundryAiServicesModelDeployment = {
   sku: {
     name: modelDeploymentType
     //Curently the capacity is set to 140 for opinanal performance. 
-    capacity: aiFoundryAiServicesConfiguration.?modelCapacity ?? 50
+    capacity: aiFoundryAiServicesConfiguration.?modelCapacity ?? gptModelCapacity
   }
   raiPolicyName: 'Microsoft.Default'
 }

infra/main.bicepparam

@@ -18,12 +18,36 @@
           }
         ]
       },     
-      "environmentName": {
+      "solutionPrefix": {
         "value": "${AZURE_ENV_NAME}"
       },
-      "location": {
+      "solutionLocation": {
         "value": "${AZURE_LOCATION}"
       },
+      "azureOpenAILocation": {
+        "value": "${AZURE_ENV_OPENAI_LOCATION}"
+      },
+      "modelDeploymentType": {
+        "value": "${AZURE_ENV_MODEL_DEPLOYMENT_TYPE}"
+      },
+      "gptModelName": {
+        "value": "${AZURE_ENV_MODEL_NAME}"
+      },
+      "gptModelVersion": {
+        "value": "${AZURE_ENV_MODEL_VERSION}"
+      },
+      "gptModelCapacity": {
+        "value": "${AZURE_ENV_MODEL_CAPACITY}"
+      },
+      "imageTag": {
+        "value": "${AZURE_ENV_IMAGE_TAG}"
+      },
+      "enableTelemetry": {
+        "value": "${AZURE_ENV_ENABLE_TELEMETRY}"
+      },
+      "existingLogAnalyticsWorkspaceId": {
+        "value": "${AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID}"
+      },
       "backendExists": {
         "value": "${SERVICE_BACKEND_RESOURCE_EXISTS=false}"
       },