diff --git a/docs/CustomizingAzdParameters.md b/docs/CustomizingAzdParameters.md index d573e3240..1fc24810c 100644 --- a/docs/CustomizingAzdParameters.md +++ b/docs/CustomizingAzdParameters.md @@ -12,12 +12,20 @@ By default this template will use the environment name as the prefix to prevent | `AZURE_LOCATION` | string | `` | Location of the Azure resources. Controls where the infrastructure will be deployed. | | `AZURE_ENV_OPENAI_LOCATION` | string | `` | Specifies the region for OpenAI resource deployment. | | `AZURE_ENV_MODEL_DEPLOYMENT_TYPE` | string | `GlobalStandard` | Defines the deployment type for the AI model (e.g., Standard, GlobalStandard). | -| `AZURE_ENV_MODEL_NAME` | string | `gpt-4o` | Specifies the name of the GPT model to be deployed. | -| `AZURE_EXISTING_AI_PROJECT_RESOURCE_ID` | string | `` | Set this if you want to reuse an AI Foundry Project instead of creating a new one. | -| `AZURE_ENV_MODEL_VERSION` | string | `2024-08-06` | Version of the GPT model to be used for deployment. | -| `AZURE_ENV_MODEL_CAPACITY` | int | `150` | Sets the GPT model capacity. | -| `AZURE_ENV_IMAGETAG` | string | `latest` | Docker image tag used for container deployments. | +| `AZURE_ENV_MODEL_NAME` | string | `gpt-4.1-mini` | Specifies the name of the GPT model to be deployed. | +| `AZURE_ENV_MODEL_VERSION` | string | `2025-04-14` | Version of the GPT model to be used for deployment. | +| `AZURE_ENV_MODEL_CAPACITY` | int | `50` | Sets the GPT model capacity. | +| `AZURE_ENV_MODEL_4_1_DEPLOYMENT_TYPE` | string | `GlobalStandard` | Defines the deployment type for the AI model (e.g., Standard, GlobalStandard). | +| `AZURE_ENV_MODEL_4_1_NAME` | string | `gpt-4.1` | Specifies the name of the GPT model to be deployed. | +| `AZURE_ENV_MODEL_4_1_VERSION` | string | `2025-04-14` | Version of the GPT model to be used for deployment. | +| `AZURE_ENV_MODEL_4_1_CAPACITY` | int | `150` | Sets the GPT model capacity. | +| `AZURE_ENV_REASONING_MODEL_DEPLOYMENT_TYPE` | string | `GlobalStandard` | Defines the deployment type for the AI model (e.g., Standard, GlobalStandard). | +| `AZURE_ENV_REASONING_MODEL_NAME` | string | `o4-mini` | Specifies the name of the reasoning GPT model to be deployed. | +| `AZURE_ENV_REASONING_MODEL_VERSION` | string | `2025-04-16` | Version of the reasoning GPT model to be used for deployment. | +| `AZURE_ENV_REASONING_MODEL_CAPACITY` | int | `50` | Sets the reasoning GPT model capacity. | +| `AZURE_ENV_IMAGETAG` | string | `latest_v3` | Docker image tag used for container deployments. | | `AZURE_ENV_ENABLE_TELEMETRY` | bool | `true` | Enables telemetry for monitoring and diagnostics. | +| `AZURE_EXISTING_AI_PROJECT_RESOURCE_ID` | string | `` | Set this if you want to reuse an AI Foundry Project instead of creating a new one. | | `AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID` | string | Guide to get your [Existing Workspace ID](/docs/re-use-log-analytics.md) | Set this if you want to reuse an existing Log Analytics Workspace instead of creating a new one. | | `AZURE_ENV_VM_ADMIN_USERNAME` | string | `take(newGuid(), 20)` | The administrator username for the virtual machine. | | `AZURE_ENV_VM_ADMIN_PASSWORD` | string | `newGuid()` | The administrator password for the virtual machine. | diff --git a/docs/DeploymentGuide.md b/docs/DeploymentGuide.md index 3bed9496a..168d84922 100644 --- a/docs/DeploymentGuide.md +++ b/docs/DeploymentGuide.md @@ -185,19 +185,6 @@ Consider the following settings during your deployment to modify specific settin When you start the deployment, most parameters will have **default values**, but you can update the following settings [here](../docs/CustomizingAzdParameters.md): -| **Setting** | **Description** | **Default value** | -| ------------------------------ | ------------------------------------------------------------------------------------ | ----------------- | -| **Environment Name** | Used as a prefix for all resource names to ensure uniqueness across environments. | macae | -| **Azure Region** | Location of the Azure resources. Controls where the infrastructure will be deployed. | swedencentral | -| **OpenAI Deployment Location** | Specifies the region for OpenAI resource deployment. | swedencentral | -| **Model Deployment Type** | Defines the deployment type for the AI model (e.g., Standard, GlobalStandard). | GlobalStandard | -| **GPT Model Name** | Specifies the name of the GPT model to be deployed. | gpt-4o | -| **GPT Model Version** | Version of the GPT model to be used for deployment. | 2024-08-06 | -| **GPT Model Capacity** | Sets the GPT model capacity. | 150 | -| **Image Tag** | Docker image tag used for container deployments. | latest | -| **Enable Telemetry** | Enables telemetry for monitoring and diagnostics. | true | -| **Existing Log Analytics Workspace** | To reuse an existing Log Analytics Workspace ID instead of creating a new one. | *(none)* | -| **Existing Azure AI Foundry Project** | To reuse an existing Azure AI Foundry Project ID instead of creating a new one. | *(none)* | diff --git a/infra/main.parameters.json b/infra/main.parameters.json index c6cf3c72f..3bf39983c 100644 --- a/infra/main.parameters.json +++ b/infra/main.parameters.json @@ -23,9 +23,30 @@ "gptModelCapacity": { "value": "${AZURE_ENV_MODEL_CAPACITY}" }, + "gpt4_1ModelDeploymentType": { + "value": "${AZURE_ENV_MODEL_4_1_DEPLOYMENT_TYPE}" + }, + "gpt4_1ModelName": { + "value": "${AZURE_ENV_MODEL_4_1_NAME}" + }, + "gpt4_1ModelVersion": { + "value": "${AZURE_ENV_MODEL_4_1_VERSION}" + }, "gpt4_1ModelCapacity": { "value": "${AZURE_ENV_MODEL_4_1_CAPACITY}" }, + "gptReasoningModelDeploymentType": { + "value": "${AZURE_ENV_REASONING_MODEL_DEPLOYMENT_TYPE}" + }, + "gptReasoningModelName": { + "value": "${AZURE_ENV_REASONING_MODEL_NAME}" + }, + "gptReasoningModelVersion": { + "value": "${AZURE_ENV_REASONING_MODEL_VERSION}" + }, + "gptReasoningModelCapacity": { + "value": "${AZURE_ENV_REASONING_MODEL_CAPACITY}" + }, "backendContainerImageTag": { "value": "${AZURE_ENV_IMAGE_TAG=latest_v3}" }, diff --git a/infra/main.waf.parameters.json b/infra/main.waf.parameters.json index 51d451d53..b6bf190a3 100644 --- a/infra/main.waf.parameters.json +++ b/infra/main.waf.parameters.json @@ -23,6 +23,30 @@ "gptModelCapacity": { "value": "${AZURE_ENV_MODEL_CAPACITY}" }, + "gpt4_1ModelDeploymentType": { + "value": "${AZURE_ENV_MODEL_4_1_DEPLOYMENT_TYPE}" + }, + "gpt4_1ModelName": { + "value": "${AZURE_ENV_MODEL_4_1_NAME}" + }, + "gpt4_1ModelVersion": { + "value": "${AZURE_ENV_MODEL_4_1_VERSION}" + }, + "gpt4_1ModelCapacity": { + "value": "${AZURE_ENV_MODEL_4_1_CAPACITY}" + }, + "gptReasoningModelDeploymentType": { + "value": "${AZURE_ENV_REASONING_MODEL_DEPLOYMENT_TYPE}" + }, + "gptReasoningModelName": { + "value": "${AZURE_ENV_REASONING_MODEL_NAME}" + }, + "gptReasoningModelVersion": { + "value": "${AZURE_ENV_REASONING_MODEL_VERSION}" + }, + "gptReasoningModelCapacity": { + "value": "${AZURE_ENV_REASONING_MODEL_CAPACITY}" + }, "backendContainerImageTag": { "value": "${AZURE_ENV_IMAGE_TAG=latest_v3}" },