Merge pull request #432 from microsoft/main

feat: Down merge from main to dev

Author: Prajwal-Microsoft

.github/workflows/CI.yml

@@ -196,15 +196,15 @@ jobs:
           # Increase the TPM for the Azure OpenAI models
           echo "Increasing TPM for Azure OpenAI models..."
           openai_gpt_deployment_url="/subscriptions/${{ secrets.AZURE_SUBSCRIPTION_ID }}/resourceGroups/${{ env.rg_name }}/providers/Microsoft.CognitiveServices/accounts/$openai_resource_name/deployments/gpt-4o-mini?api-version=2023-05-01"
-          az rest -m put -u "$openai_gpt_deployment_url" -b "{'sku':{'name':'Standard','capacity':${{ env.GPT_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'gpt-4o-mini','version': '2024-07-18'}}}"
+          az rest -m put -u "$openai_gpt_deployment_url" -b "{'sku':{'name':'GlobalStandard','capacity':${{ env.GPT_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'gpt-4o-mini','version': '2024-07-18'}}}"
           if [ $? -ne 0 ]; then
             echo "Failed to increase TPM for GPT deployment."
             exit 1
           else
             echo "Successfully increased TPM for GPT deployment."
           fi
           openai_embedding_deployment_url="/subscriptions/${{ secrets.AZURE_SUBSCRIPTION_ID }}/resourceGroups/${{ env.rg_name }}/providers/Microsoft.CognitiveServices/accounts/$openai_resource_name/deployments/text-embedding-large?api-version=2023-05-01"
-          az rest -m put -u "$openai_embedding_deployment_url" -b "{'sku':{'name':'Standard','capacity': ${{ env.TEXT_EMBEDDING_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'text-embedding-3-large','version': '1'}}}"
+          az rest -m put -u "$openai_embedding_deployment_url" -b "{'sku':{'name':'GlobalStandard','capacity': ${{ env.TEXT_EMBEDDING_CAPACITY }}},'properties': {'model': {'format': 'OpenAI','name': 'text-embedding-3-large','version': '1'}}}"
           if [ $? -ne 0 ]; then
             echo "Failed to increase TPM for Text Embedding deployment."
             exit 1

Deployment/bicep/azureopenaiservicemodel.bicep

@@ -10,7 +10,7 @@ resource gpt4Deployment 'Microsoft.CognitiveServices/accounts/deployments@2023-0
   parent: openAIService
   name: name
   sku: {
-    name: 'Standard'
+    name: 'GlobalStandard'
     capacity: model.capacity
   }
   properties: {

Deployment/checkquota.ps1

@@ -45,8 +45,8 @@ Write-Host "✅ Azure subscription set successfully."
 
 # Define models and their minimum required capacities
 $MIN_CAPACITY = @{
-    "OpenAI.Standard.gpt-4o-mini" = $GPT_MIN_CAPACITY
-    "OpenAI.Standard.text-embedding-3-large" = $TEXT_EMBEDDING_MIN_CAPACITY
+    "OpenAI.GlobalStandard.gpt-4o-mini" = $GPT_MIN_CAPACITY
+    "OpenAI.GlobalStandard.text-embedding-3-large" = $TEXT_EMBEDDING_MIN_CAPACITY
 }
 
 $VALID_REGION = ""

Deployment/main.bicep

@@ -119,7 +119,7 @@ module gs_openaiservicemodels_gpt4o 'bicep/azureopenaiservicemodel.bicep' = {
         version: '2024-07-18'
         raiPolicyName: ''
         capacity: 1
-        scaleType: 'Standard'
+        scaleType: 'GlobalStandard'
       }
 
   }
@@ -139,7 +139,7 @@ module gs_openaiservicemodels_text_embedding 'bicep/azureopenaiservicemodel.bice
         version: '1'
         raiPolicyName: ''
         capacity: 1
-        scaleType: 'Standard'
+        scaleType: 'GlobalStandard'
       }
     }
     dependsOn: [

docs/QuotaCheck.md

@@ -77,9 +77,9 @@ The final table lists regions with available quota. You can select any of these
 1. Open the terminal in VS Code or Codespaces.
 2. If you're using VS Code, click the dropdown on the right side of the terminal window, and select `Git Bash`.
    ![git_bash](images/readme/git_bash.png)
-3. Navigate to the `scripts` folder where the script files are located and make the script as executable:
+3. Navigate to the `deployment` folder where the script files are located and make the script as executable:
    ```sh
-    cd infra/scripts
+    cd Deployment
     chmod +x quota_check_params.sh
     ```
 4. Run the appropriate script based on your requirement: