Merge branch 'dev' of https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator into dev

Author: TravisHilbert

azure.yaml

@@ -1,24 +1,2 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/Azure/azure-dev/main/schemas/v1.0/azure.yaml.json
-environment:
-  name: multi-agent-custom-automation-engine-solution-accelerator
-  location: eastus
 name: multi-agent-custom-automation-engine-solution-accelerator
-metadata:
-    template: [email protected]
-parameters:
-  azureOpenAILocation:
-    type: string
-    default: eastus2
-  prefix:
-    type: string
-    default: ma-azdtest
-  baseUrl:
-    type: string
-    default: 'https://raw.githubusercontent.com/microsoft/multi-agent-custom-automation-engine-solution-accelerator'
-deployment:
-  mode: Incremental
-  template: ./infra/main.bicep  # Path to the main.bicep file inside the 'deployment' folder
-  prameters:
-    azureOpenAILocation: ${{ parameters.AiLocation }}
-    prefix: ${{ parameters.ResourcePrefix }}
-    baseUrl: ${{ parameters.baseUrl }}

documentation/CustomizeSolution.md

@@ -614,4 +614,4 @@ This application orchestrates a group of AI agents to accomplish user-defined ta
 
 Understanding the flow of data through the endpoints, agents, and persistent storage is key to grasping the logic of the application. Each component plays a specific role in ensuring tasks are planned, executed, and adjusted based on feedback, providing a robust and interactive system.
 
-For instructions to setup a local development environment for the solution, please see [local deployment guide](./LocalDeployment.md).
+For instructions to setup a local development environment for the solution, please see [deployment guide](./DeploymentGuide.md).

documentation/CustomizingAzdParameters.md

@@ -108,7 +108,7 @@ When you start the deployment, most parameters will have **default values**, but
 | **Secondary Location**            | A **less busy** region for **Azure Cosmos DB**, useful in case of availability constraints. | eastus2           |
 | **Deployment Type**               | Select from a drop-down list.                                                               | GlobalStandard    |
 | **GPT Model**                     | Choose from **gpt-4, gpt-4o, gpt-4o-mini**.                                                 | gpt-4o            |
-| **GPT Model Deployment Capacity** | Configure capacity for **GPT models**.                                                      | 100k              |
+| **GPT Model Deployment Capacity** | Configure capacity for **GPT models**.                                                      | 140k              |
 
 </details>
 
@@ -117,8 +117,6 @@ When you start the deployment, most parameters will have **default values**, but
 
 By default, the **GPT model capacity** in deployment is set to **140k tokens**.
 
-> **We recommend increasing the capacity to 100k tokens for optimal performance.**
-
 To adjust quota settings, follow these [steps](./AzureGPTQuotaSettings.md).
 
 **⚠️ Warning:** Insufficient quota can cause deployment errors. Please ensure you have the recommended capacity or request additional capacity before deploying this solution.

documentation/DeploymentGuide.md

@@ -1,17 +1,18 @@
-## Document Generation Solution Accelerator: Responsible AI FAQ
-- ### What is Build your own copilot - Generic Solution Accelerator?
-    This solution accelerator is an open-source GitHub Repository to help create AI assistants using Azure OpenAI Service and Azure AI Search. This can be used by anyone looking for reusable architecture and code snippets to build AI assistants with their own enterprise data. The repository showcases a generic scenario of a user who wants to generate a document template based on a sample set of data.
+## Multi Agent Custom Automation Engine Solution Accelerator: Responsible AI FAQ
+- ### What is Multi Agent Custom Automation Engine?
+    This solution accelerator is designed to help businesses leverage AI agents for automating complex organizational tasks. This accelerator provides a foundation for building AI-driven orchestration systems that can coordinate multiple specialized agents to accomplish various business processes.
 
-- ### What can Document Generation Solution Accelerator do? 
-    The sample solution included focuses on a generic use case - chat with your own data, generate a document template using your own data, and exporting the document in a docx format. The sample data is sourced from generic AI-generated promissory notes. The documents are intended for use as sample data only. The sample solution takes user input in text format and returns LLM responses in text format up to 800 tokens. It uses prompt flow to search data from AI search vector store, summarize the retrieved documents with Azure OpenAI.
+- ### What can Multi Agent Custom Automation Engine do? 
+    The Multi-Agent Custom Automation Engine solution accelerator allows users to specify tasks and have them automatically processed by a group of AI agents, each specialized in different aspects of the business. This automation not only saves time but also ensures accuracy and consistency in task execution.
 
-- ### What is/are Document Generation Solution Accelerator’s intended use(s)?  
-    This repository is to be used only as a solution accelerator following the open-source license terms listed in the GitHub repository. The example scenario’s intended purpose is to help users generate a document template to perform their work more efficiently.
+- ### What is/are Multi Agent Custom Automation Engine’s intended use(s)?  
+    This repository is to be used only as a solution accelerator following the open-source license terms listed in the GitHub repository. The example scenario’s intended purpose is to help users understand how the multi-agent pattern can be applied to various business scenarios.
 
-- ### How was Document Generation Solution Accelerator evaluated? What metrics are used to measure performance?
+- ### How was Multi Agent Custom Automation Engine evaluated? What metrics are used to measure performance?
     We have used AI Foundry Prompt flow evaluation SDK to test for harmful content, groundedness, and potential security risks. 
 
-- ### What are the limitations of Document Generation Solution Accelerator? How can users minimize the impact of Document Generation Solution Accelerator’s limitations when using the system?
-    This solution accelerator can only be used as a sample to accelerate the creation of AI assistants. The repository showcases a sample scenario of a user generating a document template. Users should review the system prompts provided and update as per their organizational guidance. Users should run their own evaluation flow either using the guidance provided in the GitHub repository or their choice of evaluation methods. AI-generated content may be inaccurate and should be manually reviewed. Currently, the sample repo is available in English only.  
-- ### What operational factors and settings allow for effective and responsible use of Document Generation Solution Accelerator?
-    Users can try different values for some parameters like system prompt, temperature, max tokens etc. shared as configurable environment variables while running run evaluations for AI assistants. Please note that these parameters are only provided as guidance to start the configuration but not as a complete available list to adjust the system behavior. Please always refer to the latest product documentation for these details or reach out to your Microsoft account team if you need assistance.
+- ### What are the limitations of Multi Agent Custom Automation Engine? How can users minimize the impact of Multi Agent Custom Automation Engine’s limitations when using the system?
+    This solution accelerator can only be used as a sample to accelerate the creation of a multi-agent solution. The repository showcases a sample scenarios using multiple agents to solve tasks. Users should review the system prompts provided and update as per their organizational guidance. Users should run their own evaluation flow either using the guidance provided in the GitHub repository or their choice of evaluation methods. AI-generated content may be inaccurate and should be manually reviewed. Currently, the sample repo is available in English only.  
+
+- ### What operational factors and settings allow for effective and responsible use of Multi Agent Custom Automation Engine?
+    Users can try different values for some parameters like system prompt, temperature, max tokens etc. shared as configurable environment variables while running run evaluations for AI agents. Users can also provide their own agent implementation using functional tools designed for those specific agents.  Please note that these parameters are only provided as guidance to start the configuration but not as a complete available list to adjust the system behavior. Please always refer to the latest product documentation for these details or reach out to your Microsoft account team if you need assistance.

documentation/TRANSPARENCY_FAQ.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 - the capacity to at least 50k tokens for optimal performance.**
+> **For Global Standard | GPT-4o - the capacity to at least 140k tokens for optimal performance.**
 
 ### Login if you have not done so already
 ```
@@ -11,7 +11,7 @@ azd auth login
 
 ### 📌 Default Models & Capacities:
 ```
-gpt-4o:50
+gpt-4o:140
 ```
 ### 📌 Default Regions:
 ```
@@ -37,19 +37,19 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc
    ```
 ✔️ Check specific model(s) in default regions:
   ```
-  ./quota_check_params.sh --models gpt-4o:50
+  ./quota_check_params.sh --models gpt-4o:140
   ```
 ✔️ Check default models in specific region(s):
   ```
 ./quota_check_params.sh --regions eastus,westus
   ```
 ✔️ Passing Both models and regions:  
   ```
-  ./quota_check_params.sh --models gpt-4o:50 --regions eastus,westus2
+  ./quota_check_params.sh --models gpt-4o:140 --regions eastus,westus2
   ```
 ✔️ All parameters combined:
   ```
- ./quota_check_params.sh --models gpt-4o:50 --regions eastus,westus --verbose
+ ./quota_check_params.sh --models gpt-4o:140 --regions eastus,westus --verbose
   ```
 
 ### **Sample Output**

documentation/quota_check.md

@@ -32,8 +32,11 @@ param azureOpenAILocation string //= 'eastus2' // The location used for all depl
 
 @minLength(3)
 @maxLength(20)
-@description('Prefix for all resources created by this template.  This prefix will be used to create unique names for all resources.  The prefix must be unique within the resource group.')
-param prefix string //= 'macae'
+@description('A unique prefix for all resources in this deployment. This should be 3-20 characters long:')
+param environmentName string
+ 
+var uniqueId = toLower(uniqueString(subscription().id, environmentName, resourceGroup().location))
+var solutionPrefix = 'ma${padLeft(take(uniqueId, 12), 12, '0')}'
 
 @description('Tags to apply to all deployed resources')
 param tags object = {}
@@ -60,7 +63,7 @@ param capacity int = 140
 
 var location = resourceGroup().location
 var modelVersion = '2024-08-06'
-var aiServicesName = '${prefix}-aiservices'
+var aiServicesName = '${solutionPrefix}-aiservices'
 var deploymentType = 'GlobalStandard'
 var gptModelVersion = 'gpt-4o'
 var appVersion = 'fnd01'
@@ -71,7 +74,7 @@ var dockerRegistryUrl = 'https://${resgistryName}.azurecr.io'
 var backendDockerImageURL = '${resgistryName}.azurecr.io/macaebackend:${appVersion}'
 var frontendDockerImageURL = '${resgistryName}.azurecr.io/macaefrontend:${appVersion}'
 
-var uniqueNameFormat = '${prefix}-{0}-${uniqueString(resourceGroup().id, prefix)}'
+var uniqueNameFormat = '${solutionPrefix}-{0}-${uniqueString(resourceGroup().id, solutionPrefix)}'
 var aoaiApiVersion = '2025-01-01-preview'
 var imageName = frontendDockerImageURL
 resource logAnalytics 'Microsoft.OperationalInsights/workspaces@2023-09-01' = {
@@ -121,7 +124,7 @@ resource aiServices 'Microsoft.CognitiveServices/accounts@2024-04-01-preview' =
     apiProperties: {
       //statisticsEnabled: false
     }
-    disableLocalAuth: true
+    //disableLocalAuth: true
   }
 }
 
@@ -147,7 +150,7 @@ resource aiServicesDeployments 'Microsoft.CognitiveServices/accounts/deployments
 module kvault 'deploy_keyvault.bicep' = {
   name: 'deploy_keyvault'
   params: {
-    solutionName: prefix
+    solutionName: solutionPrefix
     solutionLocation: location
     managedIdentityObjectId: managedIdentityModule.outputs.managedIdentityOutput.objectId
   }
@@ -161,7 +164,7 @@ module kvault 'deploy_keyvault.bicep' = {
 module aifoundry 'deploy_ai_foundry.bicep' = {
   name: 'deploy_ai_foundry'
   params: {
-    solutionName: prefix
+    solutionName: solutionPrefix
     solutionLocation: azureOpenAILocation
     keyVaultName: kvault.outputs.keyvaultName
     gptModelName: gptModelVersion
@@ -203,7 +206,7 @@ resource cosmos 'Microsoft.DocumentDB/databaseAccounts@2024-05-15' = {
       }
     ]
     capabilities: [{ name: 'EnableServerless' }]
-    disableLocalAuth: true
+    //disableLocalAuth: true
   }
 
   resource contributorRoleDefinition 'sqlRoleDefinitions' existing = {
@@ -277,7 +280,7 @@ resource acaCosomsRoleAssignment 'Microsoft.DocumentDB/databaseAccounts/sqlRoleA
 
 @description('')
 resource containerApp 'Microsoft.App/containerApps@2024-03-01' = {
-  name: '${prefix}-backend'
+  name: '${solutionPrefix}-backend'
   location: location
   tags: tags
   identity: {
@@ -446,7 +449,7 @@ resource frontendAppService 'Microsoft.Web/sites@2021-02-01' = {
 }
 
 resource aiHubProject 'Microsoft.MachineLearningServices/workspaces@2024-01-01-preview' existing = {
-  name: '${prefix}-aiproject' // aiProjectName must be calculated - available at main start.
+  name: '${solutionPrefix}-aiproject' // aiProjectName must be calculated - available at main start.
 }
 
 resource aiDeveloper 'Microsoft.Authorization/roleDefinitions@2022-04-01' existing = {
@@ -467,7 +470,7 @@ var cosmosAssignCli = 'az cosmosdb sql role assignment create --resource-group "
 module managedIdentityModule 'deploy_managed_identity.bicep' = {
   name: 'deploy_managed_identity'
   params: {
-    solutionName: prefix
+    solutionName: solutionPrefix
     //solutionLocation: location
     managedIdentityId: pullIdentity.id
     managedIdentityPropPrin: pullIdentity.properties.principalId