diff --git a/.devcontainer/setup_env.sh b/.devcontainer/setup_env.sh index b2d7806a9..c3a31369d 100755 --- a/.devcontainer/setup_env.sh +++ b/.devcontainer/setup_env.sh @@ -5,6 +5,7 @@ git pull # provide execute permission to quotacheck script sudo chmod +x ./infra/scripts/checkquota.sh +sudo chmod +x ./infra/scripts/quota_check_params.sh # Add the path to ~/.bashrc for persistence if ! grep -q '/opt/mssql-tools18/bin' ~/.bashrc; then diff --git a/.github/workflows/CAdeploy.yml b/.github/workflows/CAdeploy.yml index 03ab12f99..7865b05d4 100644 --- a/.github/workflows/CAdeploy.yml +++ b/.github/workflows/CAdeploy.yml @@ -115,7 +115,7 @@ jobs: az deployment group create \ --resource-group ${{ env.RESOURCE_GROUP_NAME }} \ --template-file infra/main.bicep \ - --parameters AZURE_ENV_OPENAI_LOCATION=${{ env.AZURE_LOCATION }} + --parameters AzureOpenAILocation=${{ env.AZURE_LOCATION }} - name: List KeyVaults and Store in Array id: list_keyvaults diff --git a/docs/DeploymentGuide.md b/docs/DeploymentGuide.md index fc6a69a88..a580e3ed9 100644 --- a/docs/DeploymentGuide.md +++ b/docs/DeploymentGuide.md @@ -24,7 +24,7 @@ Here are some example regions where the services are available: East US, East US ### [Optional] Quota Recommendations By default, the **Gpt-4o-mini model capacity** in deployment is set to **30k tokens**, so we recommend -> **For Global Standard | GPT-4o-mini - the capacity to at least 100k tokens post-deployment for optimal performance.** +> **For Global Standard | GPT-4o-mini - increase the capacity to at least 150k tokens post-deployment for optimal performance.** To adjust quota settings, follow these [steps](AzureGPTQuotaSettings.md) @@ -80,7 +80,7 @@ If you're not using one of the above options for opening the project, then you'l 1. Make sure the following tools are installed: - [PowerShell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell?view=powershell-7.5) (v7.0+) - available for Windows, macOS, and Linux. - [Azure Developer CLI (azd)](https://aka.ms/install-azd) - - [Python 3.9+](https://www.python.org/downloads/) + - [Python 3.9 to 3.11](https://www.python.org/downloads/) - [Docker Desktop](https://www.docker.com/products/docker-desktop/) - [Git](https://git-scm.com/downloads) - [Microsoft ODBC Driver 18 for SQL Server](https://learn.microsoft.com/en-us/sql/connect/odbc/download-odbc-driver-for-sql-server?view=sql-server-ver16) diff --git a/docs/FabricDeployment.md b/docs/FabricDeployment.md index 6e527bcd2..2ec187e72 100644 --- a/docs/FabricDeployment.md +++ b/docs/FabricDeployment.md @@ -47,7 +47,9 @@ 2. Select Fabric Workspace 3. Click `Select` 4. After publish is complete, navigate to Fabric Workspace -5. Click `...` next to the Semantic model for Power BI report +5. You will find the report in the Fabric Workspace under the name **WealthAdvisor-Client360Report**. +6. Use the report's filtering options to analyze client data. + -## Step 5: Update the Power BI URL in Azure App Service configuration + diff --git a/docs/quota_check.md b/docs/quota_check.md index f8345074d..b0b3639a5 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-mini - the capacity to at least 100K tokens for optimal performance.** +> **For Global Standard | GPT-4o-mini - increase the capacity to at least 150K tokens for optimal performance.** ### Login if you have not done so already ``` diff --git a/infra/main.bicep b/infra/main.bicep index bb55275b5..54acda493 100644 --- a/infra/main.bicep +++ b/infra/main.bicep @@ -21,7 +21,6 @@ param deploymentType string = 'GlobalStandard' @description('Name of the GPT model to deploy:') @allowed([ 'gpt-4o-mini' - 'gpt-4o' ]) param gptModelName string = 'gpt-4o-mini' @@ -50,7 +49,7 @@ param embeddingDeploymentCapacity int = 80 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','norwayeast','southindia', 'swedencentral','uksouth', 'westus', 'westus3']) +@allowed(['australiaeast','eastus', 'eastus2','francecentral','japaneast','swedencentral','uksouth', 'westus', 'westus3']) @description('Azure OpenAI Location') param AzureOpenAILocation string = 'eastus2' diff --git a/infra/scripts/quota_check_params.sh b/infra/scripts/quota_check_params.sh index 893dc7e82..a373ad1cb 100644 --- a/infra/scripts/quota_check_params.sh +++ b/infra/scripts/quota_check_params.sh @@ -93,7 +93,7 @@ az account set --subscription "$AZURE_SUBSCRIPTION_ID" echo "🎯 Active Subscription: $(az account show --query '[name, id]' --output tsv)" # Default Regions to check (Comma-separated, now configurable) -DEFAULT_REGIONS="eastus,uksouth,eastus2,northcentralus,westus,westus2,southcentralus,canadacentral,australiaeast,swedencentral" +DEFAULT_REGIONS="australiaeast,eastus,eastus2,francecentral,japaneast,swedencentral,uksouth,westus,westus3" IFS=',' read -r -a DEFAULT_REGION_ARRAY <<< "$DEFAULT_REGIONS" # Read parameters (if any)