rebase with master azurechat branch

.gitignore

@@ -26,6 +26,7 @@ yarn-error.log*
 
 # local env files
 .env*.local
+.env
 
 # typescript
 *.tsbuildinfo

README.md

@@ -1,4 +1,4 @@
-# Unleash the Power of Azure Open AI
+# Unleash the Power of Azure OpenAI
 
 1. [Introduction](#introduction)
 1. [Solution Overview](/docs/1-introduction.md)
@@ -14,11 +14,11 @@
 
 # Introduction
 
-_Azure Chat Solution Accelerator powered by Azure Open AI Service_
+_Azure Chat Solution Accelerator powered by Azure OpenAI Service_
 
 ![](/docs/images/intro.png)
 
-_Azure Chat Solution Accelerator powered by Azure Open AI Service_ is a solution accelerator that allows organisations to deploy a private chat tenant in their Azure Subscription, with a familiar user experience and the added capabilities of chatting over your data and files.
+_Azure Chat Solution Accelerator powered by Azure OpenAI Service_ is a solution accelerator that allows organisations to deploy a private chat tenant in their Azure Subscription, with a familiar user experience and the added capabilities of chatting over your data and files.
 
 Benefits are:
 

docs/8-extensions.md

@@ -47,6 +47,9 @@ As an example you can create an extension that calls Bing Search API to search f
 
 In the example below only the `query` is required as Bing does not require a body parameter.
 
+> [!NOTE]
+> As header values specified for an extension often contain secrets (e.g. API keys) Azure Chat stores those values securely in Azure Key Vault. If you are deploying the solution to Azure using azd or the bicep templates the required Key Vault role assignment is automatically created. If you are running the solution locally you will need to manually add the "Key Vault Secrets Officer" role to identy that is running the solution (wh8ch will typically be the user logged into the Azure CLI)
+
 # Bing Search Extension
 
 1.  **Name**: `Bing Search`

docs/migration.md

@@ -1,15 +1,19 @@
-# Migration
+# Migration 2.1
+
+The new changes merges GPT-4 and GPT-4 Vision models into a single GPT-4o model. This allows multi-modal inputs and generates text as an output. The new model is available within the following [regions](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-preview-model-availability).
+
+# Migration 2.0
 
 The following changes and services are required to migrate from the old version to the new version.
 
 Refer the `.env.example` file for the latest environment variable changes.
 
 If you previously had Azure Chat running and have pulled the v2 version you will need at minimum to make the following changes:
 
-* Change the "OPENAI_API_KEY" environment setting to "AZURE_OPENAI_API_KEY"
-* Add an additional container to your Cosmos DB database called "config" with a partition key of "/userId"
-* Add the "AZURE_KEY_VAULT_NAME" environment setting with the name of your Azure Key Vault
-* Add the "New Azure Services" settings below if you wish to use these features
+- Change the "OPENAI_API_KEY" environment setting to "AZURE_OPENAI_API_KEY"
+- Add an additional container to your Cosmos DB database called "config" with a partition key of "/userId"
+- Add the "AZURE_KEY_VAULT_NAME" environment setting with the name of your Azure Key Vault
+- Add the "New Azure Services" settings below if you wish to use these features
 
 ## New Azure Services
 

infra/main.bicep

@@ -9,9 +9,9 @@ param name string
 @description('Primary location for all resources')
 param location string
 
-// azure open ai -- only regions supporting gpt-35-turbo v1106
+// azure open ai -- regions currently support gpt-4o global-standard
 @description('Location for the OpenAI resource group')
-@allowed(['australiaeast', 'canadaeast', 'francecentral', 'southindia', 'uksouth', 'swedencentral', 'westus'])
+@allowed(['australiaeast', 'brazilsouth', 'canadaeast', 'eastus', 'eastus2', 'francecentral', 'germanywestcentral', 'japaneast', 'koreacentral', 'northcentralus', 'norwayeast', 'polandcentral', 'spaincentral', 'southafricanorth', 'southcentralus', 'southindia', 'swedencentral', 'switzerlandnorth', 'uksouth', 'westeurope', 'westus', 'westus3'])
 @metadata({
   azd: {
     type: 'location'
@@ -20,37 +20,26 @@ param location string
 param openAILocation string
 
 param openAISku string = 'S0'
-param openAIApiVersion string = '2023-12-01-preview'
+param openAIApiVersion string ='2024-08-01-preview'
 
-param chatGptDeploymentCapacity int = 120
-param chatGptDeploymentName string = 'chat-gpt-35-turbo'
-param chatGptModelName string = 'gpt-35-turbo'
-param chatGptModelVersion string = '1106'
+param chatGptDeploymentCapacity int = 30
+param chatGptDeploymentName string = 'gpt-4o'
+param chatGptModelName string = 'gpt-4o'
+param chatGptModelVersion string = '2024-05-13'
 param embeddingDeploymentName string = 'embedding'
 param embeddingDeploymentCapacity int = 120
 param embeddingModelName string = 'text-embedding-ada-002'
 
-// DALL-E v3 only supported in Sweden Central for now
+// DALL-E v3 only supported in limited regions for now
 @description('Location for the OpenAI DALL-E 3 instance resource group')
-@allowed(['swedencentral'])
+@allowed(['swedencentral', 'eastus', 'australiaeast'])
 param dalleLocation string
 
 param dalleDeploymentCapacity int = 1
 param dalleDeploymentName string = 'dall-e-3'
 param dalleModelName string = 'dall-e-3'
 param dalleApiVersion string = '2023-12-01-preview'
 
-// DALL-E v3 only supported in Sweden Central for now
-@description('Location for the GPT vision instance resource')
-@allowed(['swedencentral','westus',])
-param gptvisionLocation string
-
-param gptvisionDeploymentCapacity int = 1
-param gptvisionDeploymentName string = 'gpt-4-vision'
-param gptvisionModelName string = 'gpt-4'
-param gptvisionApiVersion string = '2023-12-01-preview'
-param gptvisionModelVersion string = 'vision-preview'
-
 param formRecognizerSkuName string = 'S0'
 param searchServiceIndexName string = 'azure-chat'
 param searchServiceSkuName string = 'standard'
@@ -93,12 +82,6 @@ module resources 'resources.bicep' = {
     dalleDeploymentName: dalleDeploymentName
     dalleModelName: dalleModelName
     dalleApiVersion: dalleApiVersion
-    gptvisionLocation: gptvisionLocation
-    gptvisionApiVersion: gptvisionApiVersion
-    gptvisionDeploymentCapacity: gptvisionDeploymentCapacity
-    gptvisionDeploymentName: gptvisionDeploymentName
-    gptvisionModelName: gptvisionModelName
-    gptvisionModelVersion: gptvisionModelVersion
     formRecognizerSkuName: formRecognizerSkuName
     searchServiceIndexName: searchServiceIndexName
     searchServiceSkuName: searchServiceSkuName