diff --git a/Deployment/quota_check_params.sh b/Deployment/quota_check_params.sh index 8ef95bd2..28b78981 100644 --- a/Deployment/quota_check_params.sh +++ b/Deployment/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-mini:100,text-embedding-3-large:100" +DEFAULT_MODEL_CAPACITY="gpt4.1-mini:150,text-embedding-3-large:100" # Convert the comma-separated string into an array IFS=',' read -r -a MODEL_CAPACITY_PAIRS <<< "$DEFAULT_MODEL_CAPACITY" diff --git a/docs/QuotaCheck.md b/docs/QuotaCheck.md index d830bc7c..ca0f5e01 100644 --- a/docs/QuotaCheck.md +++ b/docs/QuotaCheck.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-mini - increase the capacity to at least 150K tokens for optimal performance.** +> **For Global Standard | gpt4.1-mini - increase the capacity to at least 150K tokens for optimal performance.** ### Login if you have not done so already ``` @@ -11,7 +11,7 @@ azd auth login ### 📌 Default Models & Capacities: ``` -gpt-4o-mini:100, text-embedding-3-large:100 +gpt4.1-mini:150, text-embedding-3-large:100 ``` ### 📌 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-mini:100,text-embedding-3-large:100 + ./quota_check_params.sh --models gpt4.1-mini:150,text-embedding-3-large:100 ``` ✔️ Check default models in specific region(s): ``` @@ -45,11 +45,11 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc ``` ✔️ Passing Both models and regions: ``` - ./quota_check_params.sh --models gpt-4o-mini:100 --regions eastus,westus2 + ./quota_check_params.sh --models gpt4.1-mini:150 --regions eastus,westus2 ``` ✔️ All parameters combined: ``` - ./quota_check_params.sh --models gpt-4o-mini:100,text-embedding-3-large:100 --regions eastus,westus --verbose + ./quota_check_params.sh --models gpt4.1-mini:150,text-embedding-3-large:100 --regions eastus,westus --verbose ``` ### **Sample Output** diff --git a/infra/main.bicep b/infra/main.bicep index ab42becf..7fb16a4d 100644 --- a/infra/main.bicep +++ b/infra/main.bicep @@ -426,7 +426,7 @@ module avmContainerRegistry './modules/container-registry.bicep' = { roleAssignments: [ { principalId: managedCluster.outputs.systemAssignedMIPrincipalId - roleDefinitionIdOrName: 'AcrPull' + roleDefinitionIdOrName: '7f951dda-4ed3-4680-a7ca-43fe172d538d' // AcrPull principalType: 'ServicePrincipal' } ] @@ -523,7 +523,7 @@ module avmAppConfig 'br/public:avm/res/app-configuration/configuration-store:0.9 roleAssignments: [ { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'App Configuration Data Reader' + roleDefinitionIdOrName: '516239f1-63e1-4d78-a4de-a74fb236a071' // App Configuration Data Reader principalType: 'ServicePrincipal' } ] @@ -687,7 +687,7 @@ module avmStorageAccount 'br/public:avm/res/storage/storage-account:0.32.0' = { roleAssignments: [ { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'Storage Blob Data Contributor' + roleDefinitionIdOrName: 'ba92f5b4-2d11-453d-a403-e96b0029c9fe' // Storage Blob Data Contributor principalType: 'ServicePrincipal' } ] @@ -773,12 +773,12 @@ module avmSearchSearchServicesUpdate 'br/public:avm/res/search/search-service:0. partitionCount: 1 roleAssignments: [ { - roleDefinitionIdOrName: 'Search Index Data Contributor' // Cognitive Search Contributor + roleDefinitionIdOrName: '8ebe5a00-799e-43f5-93ac-243d3dce84a7' // Search Index Data Contributor principalId: userAssignedIdentity.outputs.principalId principalType: 'ServicePrincipal' } { - roleDefinitionIdOrName: 'Search Index Data Reader' //'5e0bd9bd-7b93-4f28-af87-19fc36ad61bd'// Cognitive Services OpenAI User + roleDefinitionIdOrName: '1407120a-92aa-4202-b7e9-c0e197c71c8f' // Search Index Data Reader principalId: userAssignedIdentity.outputs.principalId principalType: 'ServicePrincipal' } @@ -840,12 +840,12 @@ module avmOpenAi 'br/public:avm/res/cognitive-services/account:0.14.2' = { roleAssignments: [ { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'Cognitive Services OpenAI Contributor' + roleDefinitionIdOrName: 'a001fd3d-188f-4b5d-821b-7da978bf7442' // Cognitive Services OpenAI Contributor principalType: 'ServicePrincipal' } { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'Cognitive Services OpenAI User' + roleDefinitionIdOrName: '5e0bd9bd-7b93-4f28-af87-19fc36ad61bd' // Cognitive Services OpenAI User principalType: 'ServicePrincipal' } ] @@ -917,7 +917,7 @@ module documentIntelligence 'br/public:avm/res/cognitive-services/account:0.14.2 roleAssignments: [ { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'Cognitive Services User' + roleDefinitionIdOrName: 'a97b65f3-24c7-4388-baec-2e87135dc908' // Cognitive Services User principalType: 'ServicePrincipal' } ] @@ -1038,7 +1038,7 @@ module managedCluster 'br/public:avm/res/container-service/managed-cluster:0.13. roleAssignments: [ { principalId: userAssignedIdentity.outputs.principalId - roleDefinitionIdOrName: 'Contributor' + roleDefinitionIdOrName: 'b24988ac-6180-42a0-ab88-20f7382dd24c' // Contributor principalType: 'ServicePrincipal' } ] diff --git a/infra/main.json b/infra/main.json index 9f48c8e4..df6a00d0 100644 --- a/infra/main.json +++ b/infra/main.json @@ -6,7 +6,7 @@ "_generator": { "name": "bicep", "version": "0.43.8.12551", - "templateHash": "1044709840990635274" + "templateHash": "9930092765515882543" } }, "parameters": { @@ -21062,7 +21062,7 @@ "value": [ { "principalId": "[reference('managedCluster').outputs.systemAssignedMIPrincipalId.value]", - "roleDefinitionIdOrName": "AcrPull", + "roleDefinitionIdOrName": "7f951dda-4ed3-4680-a7ca-43fe172d538d", "principalType": "ServicePrincipal" } ] @@ -31099,7 +31099,7 @@ "value": [ { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "App Configuration Data Reader", + "roleDefinitionIdOrName": "516239f1-63e1-4d78-a4de-a74fb236a071", "principalType": "ServicePrincipal" } ] @@ -35679,7 +35679,7 @@ "value": [ { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "Storage Blob Data Contributor", + "roleDefinitionIdOrName": "ba92f5b4-2d11-453d-a403-e96b0029c9fe", "principalType": "ServicePrincipal" } ] @@ -43863,12 +43863,12 @@ "roleAssignments": { "value": [ { - "roleDefinitionIdOrName": "Search Index Data Contributor", + "roleDefinitionIdOrName": "8ebe5a00-799e-43f5-93ac-243d3dce84a7", "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", "principalType": "ServicePrincipal" }, { - "roleDefinitionIdOrName": "Search Index Data Reader", + "roleDefinitionIdOrName": "1407120a-92aa-4202-b7e9-c0e197c71c8f", "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", "principalType": "ServicePrincipal" } @@ -45973,12 +45973,12 @@ "value": [ { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "Cognitive Services OpenAI Contributor", + "roleDefinitionIdOrName": "a001fd3d-188f-4b5d-821b-7da978bf7442", "principalType": "ServicePrincipal" }, { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "Cognitive Services OpenAI User", + "roleDefinitionIdOrName": "5e0bd9bd-7b93-4f28-af87-19fc36ad61bd", "principalType": "ServicePrincipal" } ] @@ -49166,7 +49166,7 @@ "value": [ { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "Cognitive Services User", + "roleDefinitionIdOrName": "a97b65f3-24c7-4388-baec-2e87135dc908", "principalType": "ServicePrincipal" } ] @@ -52398,7 +52398,7 @@ "value": [ { "principalId": "[reference('userAssignedIdentity').outputs.principalId.value]", - "roleDefinitionIdOrName": "Contributor", + "roleDefinitionIdOrName": "b24988ac-6180-42a0-ab88-20f7382dd24c", "principalType": "ServicePrincipal" } ]