From 8af47cee44dbb7e44594273a567daf9a51d16b20 Mon Sep 17 00:00:00 2001 From: Priyanka-Microsoft Date: Mon, 9 Jun 2025 18:11:45 +0530 Subject: [PATCH] replace gpt-4o with gpt-4.1 --- .github/workflows/deploy.yml | 4 +- README.md | 2 +- docs/AzureGPTQuotaSettings.md | 2 +- docs/CustomizingAzdParameters.md | 4 +- docs/DeploymentGuide.md | 4 +- docs/ProcessingPipelineApproach.md | 6 +- docs/TechnicalArchitecture.md | 2 +- docs/quota_check.md | 8 +- infra/main.bicep | 4 +- infra/main.bicepparam | 4 +- infra/main.json | 125 +++++++++++++++++----------- infra/scripts/checkquota.sh | 2 +- infra/scripts/quota_check_params.sh | 5 +- 13 files changed, 100 insertions(+), 72 deletions(-) diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml index 22ead88a..3707010c 100644 --- a/.github/workflows/deploy.yml +++ b/.github/workflows/deploy.yml @@ -124,8 +124,8 @@ jobs: secondaryLocation="EastUs2" \ contentUnderstandingLocation="WestUS" \ deploymentType="GlobalStandard" \ - gptModelName="gpt-4o" \ - gptModelVersion="2024-08-06" \ + gptModelName="gpt-4.1" \ + gptModelVersion="2025-04-14" \ gptDeploymentCapacity="30" \ minReplicaContainerApp="1" \ maxReplicaContainerApp="1" \ diff --git a/README.md b/README.md index 1d0e904d..b0ae7e01 100644 --- a/README.md +++ b/README.md @@ -102,7 +102,7 @@ Use the [Azure pricing calculator](https://azure.microsoft.com/en-us/pricing/cal | Product | Description | Cost | |---|---|---| | [Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/) | Build generative AI applications on an enterprise-grade platform | [Pricing](https://azure.microsoft.com/pricing/details/ai-studio/) | -| [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/) | Provides REST API access to OpenAI's powerful language models including o3-mini, o1, o1-mini, GPT-4o, GPT-4o mini | [Pricing](https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/) | +| [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/) | Provides REST API access to OpenAI's powerful language models including o3-mini, o1, o1-mini, GPT-4.1, GPT-4.1 mini | [Pricing](https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/) | | [Azure AI Content Understanding Service](https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/) | Analyzes various media content—such as audio, video, text, and images—transforming it into structured, searchable data | [Pricing](https://azure.microsoft.com/en-us/pricing/details/content-understanding/) | | [Azure Blob Storage](https://learn.microsoft.com/en-us/azure/storage/blobs/) | Microsoft's object storage solution for the cloud. Blob storage is optimized for storing massive amounts of unstructured data | [Pricing](https://azure.microsoft.com/pricing/details/storage/blobs/) | | [Azure Container Apps](https://learn.microsoft.com/en-us/azure/container-apps/) | Allows you to run containerized applications without worrying about orchestration or infrastructure. | [Pricing](https://azure.microsoft.com/pricing/details/container-apps/) | diff --git a/docs/AzureGPTQuotaSettings.md b/docs/AzureGPTQuotaSettings.md index 7a6f3f7a..49c5a3fe 100644 --- a/docs/AzureGPTQuotaSettings.md +++ b/docs/AzureGPTQuotaSettings.md @@ -7,6 +7,6 @@ Please follow [quota check instructions guide](./Quota_Check.md) to check quota 3. **Go to** the `Management Center` from the bottom-left navigation menu. 4. Select `Quota` - Click on the `GlobalStandard` dropdown. - - Select the required **GPT model** (`GPT-4o`). + - Select the required **GPT model** (`GPT-4.1`). - Choose the **region** where the deployment is hosted. 5. Request More Quota or delete any unused model deployments as needed. \ No newline at end of file diff --git a/docs/CustomizingAzdParameters.md b/docs/CustomizingAzdParameters.md index d16f28ab..2ad0ff49 100644 --- a/docs/CustomizingAzdParameters.md +++ b/docs/CustomizingAzdParameters.md @@ -13,8 +13,8 @@ By default this template will use the environment name as the prefix to prevent | `AZURE_ENV_SECONDARY_LOCATION` | string | `eastus2` | Specifies a secondary Azure region. | | `AZURE_ENV_CU_LOCATION` | string | `WestUS` | Sets the location for the Azure Content Understanding service. | | `AZURE_ENV_MODEL_DEPLOYMENT_TYPE` | string | `GlobalStandard` | Defines the model deployment type (allowed values: `Standard`, `GlobalStandard`). | -| `AZURE_ENV_MODEL_NAME` | string | `gpt-4o` | Specifies the GPT model name (allowed values: `gpt-4o`). -| `AZURE_ENV_MODEL_VERSION` | string | `2024-08-06` | Specifies the GPT model version (allowed values: `2024-08-06`). | +| `AZURE_ENV_MODEL_NAME` | string | `gpt-4.1` | Specifies the GPT model name (allowed values: `gpt-4.1`). +| `AZURE_ENV_MODEL_VERSION` | string | `2025-04-14` | Specifies the GPT model version (allowed values: `2025-04-14`). | | `AZURE_ENV_MODEL_CAPACITY` | integer | `30` | Sets the model capacity (choose based on your subscription's available GPT capacity). | | `USE_LOCAL_BUILD` | boolean | `false` | Indicates whether to use a local container build for deployment. | | `AZURE_ENV_IMAGETAG` | boolean | `latest` | Set the Image tag Like (allowed values: latest, dev, hotfix) | diff --git a/docs/DeploymentGuide.md b/docs/DeploymentGuide.md index 0735575f..43d4498d 100644 --- a/docs/DeploymentGuide.md +++ b/docs/DeploymentGuide.md @@ -118,8 +118,8 @@ When you start the deployment, most parameters will have **default values**, but | **Azure AI Content Understanding Location** | Location for the **Content Understanding** service. | Sweden Central | | **Secondary Location** | A **less busy** region for **Azure Cosmos DB**, useful in case of availability constraints. | eastus2 | | **Deployment Type** | Select from a drop-down list. | GlobalStandard | -| **GPT Model** | Choose from **gpt-4o**. | gpt-4o | -| **GPT Model Version** | GPT model version used in the deployment. | 2024-08-06 | +| **GPT Model** | Choose from **gpt-4.1**. | gpt-4.1 | +| **GPT Model Version** | GPT model version used in the deployment. | 2025-04-14 | | **GPT Model Deployment Capacity** | Configure capacity for **GPT models**. | 30k | | **Use Local Build** | Boolean flag to determine if local container builds should be used. | false | | **Image Tag** | Image version for deployment (allowed values: `latest`, `dev`, `hotfix`). | latest | diff --git a/docs/ProcessingPipelineApproach.md b/docs/ProcessingPipelineApproach.md index 89c9e813..7fb43916 100644 --- a/docs/ProcessingPipelineApproach.md +++ b/docs/ProcessingPipelineApproach.md @@ -23,13 +23,13 @@ At the application level, when a file is processed a number of steps take place Uses Azure AI Content Understanding Service to detect and extract text from images and PDFs. This service also retrieves the coordinates of each piece of text, along with confidence scores, by leveraging built-in (pretrained) models. -2. **Map Pipeline** – Mapping Extracted Text with Azure OpenAI Service GPT-4o +2. **Map Pipeline** – Mapping Extracted Text with Azure OpenAI Service GPT-4.1 - Takes the extracted text (as context) and the associated document images, then applies GPT-4o’s vision capabilities to interpret the content. It maps the recognized text to a predefined entity schema, providing structured data fields and confidence scores derived from model log probabilities. + Takes the extracted text (as context) and the associated document images, then applies GPT-4.1’s vision capabilities to interpret the content. It maps the recognized text to a predefined entity schema, providing structured data fields and confidence scores derived from model log probabilities. 3. **Evaluate Pipeline** – Merging and Evaluating Extraction Results - Combines confidence scores from both the Extract pipeline (Azure AI Content Understanding) and the Map pipeline (GPT-4o). It then calculates an overall confidence level by merging and comparing these scores, ensuring accuracy and consistency in the final extracted data. + Combines confidence scores from both the Extract pipeline (Azure AI Content Understanding) and the Map pipeline (GPT-4.1). It then calculates an overall confidence level by merging and comparing these scores, ensuring accuracy and consistency in the final extracted data. 4. **Save Pipeline** – Storing Results in Azure Blob Storage and Azure Cosmos DB diff --git a/docs/TechnicalArchitecture.md b/docs/TechnicalArchitecture.md index cfc0e92f..61851dff 100644 --- a/docs/TechnicalArchitecture.md +++ b/docs/TechnicalArchitecture.md @@ -30,7 +30,7 @@ Using Azure Storage Queue, pipeline work steps and processing jobs are added to Used to detect and extract text from images and PDFs. This service also retrieves the coordinates of each piece of text, along with confidence scores, by leveraging built-in (pretrained) models. This utilizes the prebuild-layout 2024-12-01-preview for extraction. ### Azure OpenAI Service -Using Azure OpenAI Service, a deployment of the GPT-4o 2024-10-01-preview model is used during the content processing pipeline to extract content. GPT Vision is used for extraction and validation functions during processing. This model can be changed to a different Azure OpenAI Service model if desired, but this has not been thoroughly tested and may be affected by the output token limits. +Using Azure OpenAI Service, a deployment of the GPT-4.1 2025-04-14 model is used during the content processing pipeline to extract content. GPT Vision is used for extraction and validation functions during processing. This model can be changed to a different Azure OpenAI Service model if desired, but this has not been thoroughly tested and may be affected by the output token limits. ### Blob Storage Using Azure Blob Storage, schema .py files, source files for processing, and final output JSON files are stored in blob storage. diff --git a/docs/quota_check.md b/docs/quota_check.md index 594812ef..ae2b53d8 100644 --- a/docs/quota_check.md +++ b/docs/quota_check.md @@ -1,7 +1,7 @@ ## Check Quota Availability Before Deployment Before deploying the accelerator, **ensure sufficient quota availability** for the required model. -> **For Global Standard | GPT-4o - the capacity to at least 30K tokens for optimal performance.** +> **For Global Standard | GPT-4.1 - the capacity to at least 30K tokens for optimal performance.** ### Login if you have not done so already ``` @@ -11,7 +11,7 @@ azd auth login ### 📌 Default Models & Capacities: ``` -gpt-4o:30 +gpt4.1:30 ``` ### 📌 Default Regions: ``` @@ -37,7 +37,7 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc ``` ✔️ Check specific model(s) in default regions: ``` - ./quota_check_params.sh --models gpt-4o:30 + ./quota_check_params.sh --models gpt4.1:30 ``` ✔️ Check default models in specific region(s): ``` @@ -45,7 +45,7 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc ``` ✔️ Passing Both models and regions: ``` - ./quota_check_params.sh --models gpt-4o:30 --regions eastus,westus2 + ./quota_check_params.sh --models gpt4.1:30 --regions eastus,westus2 ``` ✔️ All parameters combined: ``` diff --git a/infra/main.bicep b/infra/main.bicep index 99a5b016..b341476b 100644 --- a/infra/main.bicep +++ b/infra/main.bicep @@ -31,10 +31,10 @@ param contentUnderstandingLocation string param deploymentType string = 'GlobalStandard' @description('Name of the GPT model to deploy:') -param gptModelName string = 'gpt-4o' +param gptModelName string = 'gpt-4.1' @description('Version of the GPT model to deploy:') -param gptModelVersion string = '2024-08-06' +param gptModelVersion string = '2025-04-14' //var gptModelVersion = '2024-02-15-preview' diff --git a/infra/main.bicepparam b/infra/main.bicepparam index b6a15d71..0a18581c 100644 --- a/infra/main.bicepparam +++ b/infra/main.bicepparam @@ -4,8 +4,8 @@ param environmentName = readEnvironmentVariable('AZURE_ENV_NAME', 'cps') param secondaryLocation = readEnvironmentVariable('AZURE_ENV_SECONDARY_LOCATION', 'EastUs2') param contentUnderstandingLocation = readEnvironmentVariable('AZURE_ENV_CU_LOCATION', 'WestUS') param deploymentType = readEnvironmentVariable('AZURE_ENV_MODEL_DEPLOYMENT_TYPE', 'GlobalStandard') -param gptModelName = readEnvironmentVariable('AZURE_ENV_MODEL_NAME', 'gpt-4o') -param gptModelVersion = readEnvironmentVariable('AZURE_ENV_MODEL_VERSION', '2024-08-06') +param gptModelName = readEnvironmentVariable('AZURE_ENV_MODEL_NAME', 'gpt-4.1') +param gptModelVersion = readEnvironmentVariable('AZURE_ENV_MODEL_VERSION', '2025-04-14') param gptDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_MODEL_CAPACITY', '30')) param useLocalBuild = readEnvironmentVariable('USE_LOCAL_BUILD', 'false') param imageTag = readEnvironmentVariable('AZURE_ENV_IMAGETAG', 'latest') diff --git a/infra/main.json b/infra/main.json index 4f5351e4..100bb459 100644 --- a/infra/main.json +++ b/infra/main.json @@ -4,8 +4,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "15234454470886032390" + "version": "0.36.1.42791", + "templateHash": "12817067577745543929" } }, "parameters": { @@ -53,14 +53,14 @@ }, "gptModelName": { "type": "string", - "defaultValue": "gpt-4o", + "defaultValue": "gpt-4.1", "metadata": { "description": "Name of the GPT model to deploy:" } }, "gptModelVersion": { "type": "string", - "defaultValue": "2024-08-06", + "defaultValue": "2025-04-14", "metadata": { "description": "Version of the GPT model to deploy:" } @@ -128,6 +128,10 @@ "metadata": { "description": "Optional: Existing Log Analytics Workspace Resource ID" } + }, + "imageTag": { + "type": "string", + "defaultValue": "latest" } }, "variables": { @@ -393,8 +397,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "3237931210750164965" + "version": "0.36.1.42791", + "templateHash": "17040083292589011391" } }, "parameters": { @@ -479,8 +483,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "1503106947863889964" + "version": "0.36.1.42791", + "templateHash": "11049431112452456133" } }, "parameters": { @@ -588,8 +592,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "4417744862326794406" + "version": "0.36.1.42791", + "templateHash": "1305630352036876197" } }, "parameters": { @@ -606,6 +610,7 @@ }, "variables": { "useExisting": "[not(empty(parameters('existingLogAnalyticsWorkspaceId')))]", + "existingLawSubscriptionId": "[if(variables('useExisting'), split(parameters('existingLogAnalyticsWorkspaceId'), '/')[2], '')]", "existingLawResourceGroup": "[if(variables('useExisting'), split(parameters('existingLogAnalyticsWorkspaceId'), '/')[4], '')]", "existingLawName": "[if(variables('useExisting'), split(parameters('existingLogAnalyticsWorkspaceId'), '/')[8], '')]" }, @@ -643,7 +648,7 @@ "publicNetworkAccessForIngestion": "Enabled", "publicNetworkAccessForQuery": "Disabled", "Request_Source": "rest", - "WorkspaceResourceId": "[if(variables('useExisting'), extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', subscription().subscriptionId, variables('existingLawResourceGroup')), 'Microsoft.OperationalInsights/workspaces', variables('existingLawName')), resourceId('Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')))]" + "WorkspaceResourceId": "[if(variables('useExisting'), extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', variables('existingLawSubscriptionId'), variables('existingLawResourceGroup')), 'Microsoft.OperationalInsights/workspaces', variables('existingLawName')), resourceId('Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')))]" }, "dependsOn": [ "[resourceId('Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName'))]" @@ -659,6 +664,10 @@ "type": "string", "value": "[if(variables('useExisting'), variables('existingLawName'), parameters('logAnalyticsWorkspaceName'))]" }, + "logAnalyticsWorkspaceSubscription": { + "type": "string", + "value": "[if(variables('useExisting'), variables('existingLawSubscriptionId'), split(subscription().id, '/')[2])]" + }, "logAnalyticsWorkspaceResourceGroup": { "type": "string", "value": "[if(variables('useExisting'), variables('existingLawResourceGroup'), resourceGroup().name)]" @@ -687,8 +696,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "12870101648257851199" + "version": "0.36.1.42791", + "templateHash": "6955709595359352278" } }, "parameters": { @@ -773,8 +782,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "8070899038568610427" + "version": "0.36.1.42791", + "templateHash": "3200993772301267162" } }, "parameters": { @@ -931,8 +940,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "13810365425953827110" + "version": "0.36.1.42791", + "templateHash": "9667477416787926279" } }, "parameters": { @@ -1487,6 +1496,9 @@ }, "logAnalyticsWorkspaceResourceGroup": { "value": "[reference(resourceId('Microsoft.Resources/deployments', 'deploy_app_insights'), '2022-09-01').outputs.logAnalyticsWorkspaceResourceGroup.value]" + }, + "logAnalyticsWorkspaceSubscription": { + "value": "[reference(resourceId('Microsoft.Resources/deployments', 'deploy_app_insights'), '2022-09-01').outputs.logAnalyticsWorkspaceSubscription.value]" } }, "template": { @@ -1495,8 +1507,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "12849612969576340024" + "version": "0.36.1.42791", + "templateHash": "17443204944330265380" } }, "parameters": { @@ -1514,6 +1526,9 @@ }, "logAnalyticsWorkspaceResourceGroup": { "type": "string" + }, + "logAnalyticsWorkspaceSubscription": { + "type": "string" } }, "resources": [ @@ -1536,8 +1551,8 @@ "appLogsConfiguration": { "destination": "log-analytics", "logAnalyticsConfiguration": { - "customerId": "[reference(extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', subscription().subscriptionId, parameters('logAnalyticsWorkspaceResourceGroup')), 'Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')), '2023-09-01').customerId]", - "sharedKey": "[listKeys(extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', subscription().subscriptionId, parameters('logAnalyticsWorkspaceResourceGroup')), 'Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')), '2023-09-01').primarySharedKey]" + "customerId": "[reference(extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', parameters('logAnalyticsWorkspaceSubscription'), parameters('logAnalyticsWorkspaceResourceGroup')), 'Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')), '2023-09-01').customerId]", + "sharedKey": "[listKeys(extensionResourceId(format('/subscriptions/{0}/resourceGroups/{1}', parameters('logAnalyticsWorkspaceSubscription'), parameters('logAnalyticsWorkspaceResourceGroup')), 'Microsoft.OperationalInsights/workspaces', parameters('logAnalyticsWorkspaceName')), '2023-09-01').primarySharedKey]" } }, "zoneRedundant": false, @@ -1625,6 +1640,9 @@ }, "useLocalBuild": { "value": "false" + }, + "imageTag": { + "value": "latest" } }, "template": { @@ -1633,8 +1651,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "6288181929674095968" + "version": "0.36.1.42791", + "templateHash": "2659069563004380992" } }, "parameters": { @@ -1710,6 +1728,9 @@ "useLocalBuild": { "type": "string", "defaultValue": "false" + }, + "imageTag": { + "type": "string" } }, "variables": { @@ -2004,7 +2025,7 @@ "value": "contentprocessor" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -2036,8 +2057,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { @@ -2179,7 +2200,7 @@ "value": "contentprocessorapi" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -2216,8 +2237,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { @@ -2359,7 +2380,7 @@ "value": "contentprocessorweb" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -2408,8 +2429,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { @@ -2592,8 +2613,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "18013369407849007542" + "version": "0.36.1.42791", + "templateHash": "3850312828243192450" } }, "parameters": { @@ -2700,8 +2721,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "12698338841871546352" + "version": "0.36.1.42791", + "templateHash": "10346977865586942127" } }, "parameters": { @@ -2945,8 +2966,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "6748924733076412812" + "version": "0.36.1.42791", + "templateHash": "4418232655579357592" } }, "parameters": { @@ -3148,6 +3169,9 @@ }, "useLocalBuild": { "value": "[variables('useLocalBuildLower')]" + }, + "imageTag": { + "value": "[parameters('imageTag')]" } }, "template": { @@ -3156,8 +3180,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "6288181929674095968" + "version": "0.36.1.42791", + "templateHash": "2659069563004380992" } }, "parameters": { @@ -3233,6 +3257,9 @@ "useLocalBuild": { "type": "string", "defaultValue": "false" + }, + "imageTag": { + "type": "string" } }, "variables": { @@ -3527,7 +3554,7 @@ "value": "contentprocessor" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -3559,8 +3586,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { @@ -3702,7 +3729,7 @@ "value": "contentprocessorapi" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -3739,8 +3766,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { @@ -3882,7 +3909,7 @@ "value": "contentprocessorweb" }, "azureContainerRegistryImageTag": { - "value": "latest" + "value": "[parameters('imageTag')]" }, "managedIdentityId": { "value": "[parameters('containerRegistryReaderId')]" @@ -3931,8 +3958,8 @@ "metadata": { "_generator": { "name": "bicep", - "version": "0.35.1.17967", - "templateHash": "17874244636612129409" + "version": "0.36.1.42791", + "templateHash": "13562163699289922411" } }, "parameters": { diff --git a/infra/scripts/checkquota.sh b/infra/scripts/checkquota.sh index e4aab3df..eb11255e 100644 --- a/infra/scripts/checkquota.sh +++ b/infra/scripts/checkquota.sh @@ -31,7 +31,7 @@ echo "✅ Azure subscription set successfully." # Define models and their minimum required capacities declare -A MIN_CAPACITY=( - ["OpenAI.Standard.gpt-4o"]=$GPT_MIN_CAPACITY + ["OpenAI.GlobalStandard.gpt4.1"]=$GPT_MIN_CAPACITY ) VALID_REGION="" diff --git a/infra/scripts/quota_check_params.sh b/infra/scripts/quota_check_params.sh index 7e562c56..61ca4e5e 100644 --- a/infra/scripts/quota_check_params.sh +++ b/infra/scripts/quota_check_params.sh @@ -47,7 +47,7 @@ log_verbose() { } # Default Models and Capacities (Comma-separated in "model:capacity" format) -DEFAULT_MODEL_CAPACITY="gpt-4o:30" +DEFAULT_MODEL_CAPACITY="gpt4.1:30" # Convert the comma-separated string into an array IFS=',' read -r -a MODEL_CAPACITY_PAIRS <<< "$DEFAULT_MODEL_CAPACITY" @@ -92,7 +92,8 @@ az account set --subscription "$AZURE_SUBSCRIPTION_ID" echo "🎯 Active Subscription: $(az account show --query '[name, id]' --output tsv)" # Default Regions to check (Comma-separated, now configurable) -DEFAULT_REGIONS="eastus,uksouth,eastus2,northcentralus,swedencentral,westus,westus2,southcentralus,canadacentral" +DEFAULT_REGIONS="australiaeast,eastus,uksouth,eastus2,northcentralus,swedencentral,westus,southcentralus" + IFS=',' read -r -a DEFAULT_REGION_ARRAY <<< "$DEFAULT_REGIONS" # Read parameters (if any)