fix: merging dev changes to main

code/backend/batch/utilities/helpers/env_helper.py

@@ -186,7 +186,7 @@ def __load_config(self, **kwargs) -> None:
                 "AZURE_OPENAI_MODEL_NAME", "gpt-4.1"
             )
 
-        self.AZURE_OPENAI_VISION_MODEL = os.getenv("AZURE_OPENAI_VISION_MODEL", "gpt-4")
+        self.AZURE_OPENAI_VISION_MODEL = os.getenv("AZURE_OPENAI_VISION_MODEL", "gpt-4.1")
         self.AZURE_OPENAI_TEMPERATURE = os.getenv("AZURE_OPENAI_TEMPERATURE", "0")
         self.AZURE_OPENAI_TOP_P = os.getenv("AZURE_OPENAI_TOP_P", "1.0")
         self.AZURE_OPENAI_MAX_TOKENS = os.getenv("AZURE_OPENAI_MAX_TOKENS", "1000")

code/tests/utilities/helpers/test_push_embedder.py

@@ -192,7 +192,7 @@ def test_embed_file_advanced_image_processing_uses_vision_model_for_captioning(
 ):
     # given
     env_helper_mock = MagicMock()
-    env_helper_mock.AZURE_OPENAI_VISION_MODEL = "gpt-4"
+    env_helper_mock.AZURE_OPENAI_VISION_MODEL = "gpt-4.1"
     push_embedder = PushEmbedder(MagicMock(), env_helper_mock)
     source_url = "http://localhost:8080/some-file-name.jpg"
 

docs/LOCAL_DEPLOYMENT.md

@@ -21,6 +21,8 @@ The easiest way to run this accelerator is in a VS Code Dev Containers, which wi
     * **Important**: Beware that the resources created by this command will incur immediate costs, primarily from the AI Search resource. These resources may accrue costs even if you interrupt the command before it is fully executed. You can run `azd down` or delete the resources manually to avoid unnecessary spending.
     * You will be prompted to select a subscription, and a location. That location list is based on the [OpenAI model availability table](https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models#model-summary-table-and-region-availability) and may become outdated as availability changes.
     * If you do, accidentally, chose the wrong location; you will have to ensure that you use `azd down` or delete the Resource Group as the deployment bases the location from this Resource Group.
+    > **Note:** If you deployed with `enableRedundancy=true` and Log Analytics workspace replication is enabled, you must first disable replication before running `azd down` else resource group delete will fail. Follow the steps in [Handling Log Analytics Workspace Deletion with Replication Enabled](./LogAnalyticsReplicationDisable.md), wait until replication returns `false`, then run `azd down`.
+
 1. After the application has been successfully deployed you will see a URL printed to the console.  Click that URL to interact with the application in your browser.
 
 > NOTE: It may take up to an hour for the application to be fully deployed. If you see a "Python Developer" welcome screen or an error page, then wait a bit and refresh the page.

docs/LogAnalyticsReplicationDisable.md

@@ -0,0 +1,26 @@
+# 🛠 Handling Log Analytics Workspace Deletion with Replication Enabled
+
+If redundancy (replication) is enabled for your Log Analytics workspace, you must disable it before deleting the workspace or resource group. Otherwise, deletion will fail.
+
+## ✅ Steps to Disable Replication Before Deletion
+Run the following Azure CLI command. Note: This operation may take about 5 minutes to complete.
+
+```bash
+az resource update --ids "/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.OperationalInsights/workspaces/{logAnalyticsName}" --set properties.replication.enabled=false
+```
+
+Replace:
+- `{subscriptionId}` → Your Azure subscription ID
+- `{resourceGroupName}` → The name of your resource group
+- `{logAnalyticsName}` → The name of your Log Analytics workspace
+
+Optional: Verify replication disabled (should output `false`):
+```bash
+az resource show --ids "/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.OperationalInsights/workspaces/{logAnalyticsName}" --query properties.replication.enabled -o tsv
+```
+
+## ✅ After Disabling Replication
+You can safely delete:
+- The Log Analytics workspace (manual)
+- The resource group (manual), or
+- All provisioned resources via `azd down`

docs/model_configuration.md

@@ -27,9 +27,9 @@ This document outlines the necessary steps and configurations required for setti
 - `AZURE_OPENAI_VISION_MODEL`: The Azure OpenAI Model Deployment Name
     - example: `my-gpt-4`
 - `AZURE_OPENAI_VISION_MODEL_NAME`: The Azure OpenAI Model Name
-    - example: `gpt-4`
+    - example: `gpt-4.1`
 - `AZURE_OPENAI_VISION_MODEL_VERSION`: The Azure OpenAI Model Version
-    - example: `turbo-2024-04-09`
+    - example: `2025-04-14`
 - `AZURE_OPENAI_VISION_MODEL_CAPACITY`: The Tokens per Minute Rate Limit (thousands)
     - example: `10`
 

infra/main.bicep

@@ -151,13 +151,13 @@ param useAdvancedImageProcessing bool = false
 param advancedImageProcessingMaxImages int = 1
 
 @description('Optional. Azure OpenAI Vision Model Deployment Name.')
-param azureOpenAIVisionModel string = 'gpt-4'
+param azureOpenAIVisionModel string = 'gpt-4.1'
 
 @description('Optional. Azure OpenAI Vision Model Name.')
-param azureOpenAIVisionModelName string = 'gpt-4'
+param azureOpenAIVisionModelName string = 'gpt-4.1'
 
 @description('Optional. Azure OpenAI Vision Model Version.')
-param azureOpenAIVisionModelVersion string = 'turbo-2024-04-09'
+param azureOpenAIVisionModelVersion string = '2025-04-14'
 
 @description('Optional. Azure OpenAI Vision Model Capacity - See here for more info  https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/quota.')
 param azureOpenAIVisionModelCapacity int = 10
@@ -963,26 +963,6 @@ var defaultOpenAiDeployments = [
   }
 ]
 
-var openAiDeployments = concat(
-  defaultOpenAiDeployments,
-  useAdvancedImageProcessing
-    ? [
-        {
-          name: azureOpenAIVisionModel
-          model: {
-            format: 'OpenAI'
-            name: azureOpenAIVisionModelName
-            version: azureOpenAIVisionModelVersion
-          }
-          sku: {
-            name: 'GlobalStandard'
-            capacity: azureOpenAIVisionModelCapacity
-          }
-        }
-      ]
-    : []
-)
-
 module openai 'modules/core/ai/cognitiveservices.bicep' = {
   name: azureOpenAIResourceName
   scope: resourceGroup()
@@ -992,7 +972,7 @@ module openai 'modules/core/ai/cognitiveservices.bicep' = {
     tags: allTags
     kind: 'OpenAI'
     sku: azureOpenAISkuName
-    deployments: openAiDeployments
+    deployments: defaultOpenAiDeployments
     userAssignedResourceId: managedIdentityModule.outputs.resourceId
     restrictOutboundNetworkAccess: true
     allowedFqdnList: concat(