feat: quota check during azd up (#579)

* quota-check-during azd up

* updated bicep and parameter json

Author: Priyanka-Microsoft

infra/main.bicep

@@ -10,7 +10,7 @@ param environmentName string
 param existingLogAnalyticsWorkspaceId string = ''
 
 @description('CosmosDB Location')
-param cosmosLocation string
+param cosmosLocation string = 'eastus2'
 
 @minLength(1)
 @description('GPT model deployment type:')
@@ -27,13 +27,13 @@ param deploymentType string = 'GlobalStandard'
 ])
 param gptModelName string = 'gpt-4o-mini'
 
-param azureOpenaiAPIVersion string = '2025-04-01-preview'
+param azureOpenaiAPIVersion string = '2025-01-01-preview'
 
 @minValue(10)
 @description('Capacity of the GPT deployment:')
 // You can increase this, but capacity is limited per model/region, so you will get errors if you go over
 // https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits
-param gptDeploymentCapacity int = 30
+param gptDeploymentCapacity int = 200
 
 @minLength(1)
 @description('Name of the Text Embedding model to deploy:')
@@ -53,14 +53,27 @@ param imageTag string = 'latest'
 
 //restricting to these regions because assistants api for gpt-4o-mini is available only in these regions
 @allowed(['australiaeast','eastus', 'eastus2','francecentral','japaneast','swedencentral','uksouth', 'westus', 'westus3'])
-@description('Azure OpenAI Location')
-param AzureOpenAILocation string = 'eastus2'
+// @description('Azure OpenAI Location')
+// param AzureOpenAILocation string = 'eastus2'
+
+@metadata({
+  azd:{
+    type: 'location'
+    usageName: [
+      'OpenAI.GlobalStandard.gpt-4o-mini,200'
+      'OpenAI.Standard.text-embedding-ada-002,80'
+    ]
+  }
+})
+@description('Location for AI Foundry deployment. This is the location where the AI Foundry resources will be deployed.')
+param aiDeploymentsLocation string
 
 @description('Set this if you want to deploy to a different region than the resource group. Otherwise, it will use the resource group location by default.')
 param AZURE_LOCATION string=''
 var solutionLocation = empty(AZURE_LOCATION) ? resourceGroup().location : AZURE_LOCATION
 
 var uniqueId = toLower(uniqueString(environmentName, subscription().id, solutionLocation))
+
 var solutionPrefix = 'ca${padLeft(take(uniqueId, 12), 12, '0')}'
 
 // Load the abbrevations file required to name the azure resources.
@@ -133,7 +146,7 @@ module aifoundry 'deploy_ai_foundry.bicep' = {
   name: 'deploy_ai_foundry'
   params: {
     solutionName: solutionPrefix
-    solutionLocation: AzureOpenAILocation
+    solutionLocation: aiDeploymentsLocation
     keyVaultName: keyvaultModule.outputs.keyvaultName
     deploymentType: deploymentType
     gptModelName: gptModelName

infra/main.bicepparam

@@ -0,0 +1,39 @@
+{
+  "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentParameters.json#",
+  "contentVersion": "1.0.0.0",
+  "parameters": {
+    "environmentName": {
+      "value": "${AZURE_ENV_NAME}"
+    },
+    "cosmosLocation": {
+      "value": "${AZURE_ENV_COSMOS_LOCATION}"
+    },
+    "deploymentType": {
+      "value": "${AZURE_ENV_MODEL_DEPLOYMENT_TYPE}"
+    },
+    "gptModelName": {
+      "value": "${AZURE_ENV_MODEL_NAME}"
+    },
+    "azureOpenaiAPIVersion": {
+      "value": "${AZURE_ENV_MODEL_VERSION}"
+    },
+    "gptDeploymentCapacity": {
+      "value": "${AZURE_ENV_MODEL_CAPACITY}"
+    },
+    "embeddingModel": {
+      "value": "${AZURE_ENV_EMBEDDING_MODEL_NAME}"
+    },
+    "embeddingDeploymentCapacity": {
+      "value": "${AZURE_ENV_EMBEDDING_MODEL_CAPACITY}"
+    },
+    "imageTag": {
+      "value": "${AZURE_ENV_IMAGETAG}"
+    },
+    "location": {
+      "value": "${AZURE_LOCATION}"
+    },
+    "existingLogAnalyticsWorkspaceId": {
+      "value": "${AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID}"
+    }
+  }
+}