The quota check has failed, and the pipeline cannot proceed.
Build URL: ${RUN_URL}
Please take necessary action.
Best regards,
Your Automation Team
We would like to inform you that the Multi-Agent-Custom-Automation-Engine-Solution-Accelerator Automation process has encountered an issue and has failed to complete successfully.
Build URL: ${RUN_URL}
${OUTPUT}
Please investigate the matter at your earliest convenience.
Best regards,
Your Automation Team
The quota check has failed, and the pipeline cannot proceed.
Build URL: ${RUN_URL}
Please take necessary action.
Best regards,
Your Automation Team
We would like to inform you that the Multi-Agent-Custom-Automation-Engine-Solution-Accelerator Automation process has encountered an issue and has failed to complete successfully.
Build URL: ${RUN_URL}
${OUTPUT}
Please investigate the matter at your earliest convenience.
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} deployment has failed due to insufficient quota in the requested regions.
Issue Details:
âĸ Quota check failed for GPT model
âĸ Required GPT Capacity: ${{ env.GPT_MIN_CAPACITY }}
âĸ Checked Regions: ${{ vars.AZURE_REGIONS }}
Run URL: ${RUN_URL}
Please resolve the quota issue and retry the deployment.
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} deployment process has encountered an issue and has failed to complete successfully.
Deployment Details:
âĸ Resource Group: ${RESOURCE_GROUP}
âĸ WAF Enabled: ${{ env.WAF_ENABLED }}
âĸ EXP Enabled: ${{ env.EXP }}
Run URL: ${RUN_URL}
Please investigate the deployment failure at your earliest convenience.
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} deployment has completed successfully.
Deployment Details:
âĸ Resource Group: ${RESOURCE_GROUP}
âĸ Web App URL: ${WEBAPP_URL}
âĸ E2E Tests: Skipped (as configured)
Configuration:
âĸ WAF Enabled: ${{ env.WAF_ENABLED }}
âĸ EXP Enabled: ${{ env.EXP }}
Run URL: ${RUN_URL}
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} deployment and testing process has completed successfully.
Deployment Details:
âĸ Resource Group: ${RESOURCE_GROUP}
âĸ Web App URL: ${WEBAPP_URL}
âĸ E2E Tests: Passed â
âĸ Test Suite: ${TEST_SUITE_NAME}
âĸ Test Report: View Report
Configuration:
âĸ WAF Enabled: ${{ env.WAF_ENABLED }}
âĸ EXP Enabled: ${{ env.EXP }}
Run URL: ${RUN_URL}
Best regards,
Your Automation Team
We would like to inform you that ${{ env.accelerator_name }} accelerator test automation process has encountered issues and failed to complete successfully.
Deployment Details:
âĸ Resource Group: ${RESOURCE_GROUP}
âĸ Web App URL: ${WEBAPP_URL}
âĸ Deployment Status: â
Success
âĸ E2E Tests: â Failed
âĸ Test Suite: ${TEST_SUITE_NAME}
Test Details:
âĸ Test Report: View Report
Run URL: ${RUN_URL}
Please investigate the matter at your earliest convenience.
Best regards,
Your Automation Team
The ${{ env.accelerator_name }} pipeline executed against the specified target URL and testing process has completed successfully.
Test Results:
âĸ Status: â
Passed
âĸ Test Suite: ${TEST_SUITE_NAME}
${TEST_REPORT_URL:+âĸ Test Report: View Report}
âĸ Target URL: ${EXISTING_URL}
Deployment: Skipped
Run URL: ${RUN_URL}
Best regards,
Your Automation Team
The ${{ env.accelerator_name }} pipeline executed against the specified target URL and the test automation has encountered issues and failed to complete successfully.
Failure Details:
âĸ Target URL: ${EXISTING_URL}
${TEST_REPORT_URL:+âĸ Test Report: View Report}
âĸ Test Suite: ${TEST_SUITE_NAME}
âĸ Deployment: Skipped
Run URL: ${RUN_URL}
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} Test Automation process has completed successfully.
Run URL: ${RUN_URL}
Test Report: ${REPORT_URL}
Best regards,
Your Automation Team
We would like to inform you that the ${{ env.accelerator_name }} Test Automation process has encountered an issue and has failed to complete successfully.
Run URL: ${RUN_URL}
Test Report: ${REPORT_URL}
Please investigate the matter at your earliest convenience.
Best regards,
Your Automation Team
-
-User story
-
-
-### Overview
-
-Problem:
-Agentic AI systems are set to transform the way businesses operate, however it can be fairly complex to build an initial MVP to demonstrate this value.
-
-Solution:
-The Multi-Agent -Custom Automation Engine Solution Accelerator provides a ready to go application to use as the base of the MVP, or as a reference, allowing you to hit the ground running.
+When dealing with complex organizational tasks, users often face significant challenges, including coordinating across multiple departments, maintaining consistency in processes, and ensuring efficient resource utilization.
-### Technology Note
-This accelerator uses the AutoGen framework from Microsoft Research. This is an open source project that is maintained by [Microsoft Researchâs AI Frontiers Lab](https://www.microsoft.com/research/lab/ai-frontiers/). Please see this [blog post](https://devblogs.microsoft.com/autogen/microsofts-agentic-frameworks-autogen-and-semantic-kernel/) for the latest information on using the AutoGen framework in production solutions.
+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.
-### Use cases / scenarios
-The multi-agent approach allows users to utilize multiple AI agents simultaneously for repeatable tasks, ensuring consistency and efficiency.
-The agents collaborate with a manager on various assignments for onboarding a new employee , such as HR and tech support AI working together to set up software accounts, configure hardware, schedule onboarding meetings, register employees for benefits, and send welcome emails. Additionally, these agents can handle tasks like procurement and drafting press releases.
+-### Business value -Multi-agent systems represent the next wave of Generative AI use cases, offering entirely new opportunities to drive efficiencies in your business. The Multi-Agent -Custom Automation Engine Solution Accelerator demonstrates several key benefits: +
+
+[**SOLUTION OVERVIEW**](#solution-overview) \| [**QUICK DEPLOY**](#quick-deploy) \| [**BUSINESS SCENARIO**](#business-scenario) \| [**SUPPORTING DOCUMENTATION**](#supporting-documentation)
-- **Allows people to focus on what matters:** by doing the heavy lifting involved with coordinating activities across an organization, peoplesâ time is freed up to focus on their specializations.
-- **Enabling GenAI to scale:** by not needing to build one application after another, organizations are able to reduce the friction of adopting GenAI across their entire organization. One capability can unlock almost unlimited use cases.
-- **Applicable to most industries:** these are common challenges that most organizations face, across most industries.
+
+-Whilst still an emerging area, investing in agentic use cases, digitatization and developing tools will be key to ensuring you are able to leverage these new technologies and seize the GenAI moment. +**Note:** With any AI solutions you create using these templates, you are responsible for assessing all associated risks and for complying with all applicable laws and safety standards. Learn more in the transparency documents for [Agent Service](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/agents/transparency-note) and [Agent Framework](https://github.com/microsoft/agent-framework/blob/main/TRANSPARENCY_FAQ.md). +
-### Technical key features +
+Solution overview
+
-This application is an AI-driven orchestration system that manages a group of AI agents to accomplish tasks based on user input. It uses a FastAPI backend to handle HTTP requests, processes them through various specialized agents, and stores stateful information using Azure Cosmos DB. The system is designed to:
+The solution leverages Azure OpenAI Service, Azure Container Apps, Azure Cosmos DB, and Azure Container Registry to create an intelligent automation pipeline. It uses a multi-agent approach where specialized AI agents work together to plan, execute, and validate tasks based on user input.
-- Receive input tasks from users.
-- Generate a detailed plan to accomplish the task using a Planner agent.
-- Execute the plan by delegating steps to specialized agents (e.g., HR, Procurement, Marketing).
-- Incorporate human feedback into the workflow.
-- Maintain state across sessions with persistent storage.
+### Solution architecture
+||
+|---|
-This system is intended for developing and deploying custom AI solutions for specific customers. This code has not been tested as an end-to-end, reliable production application- it is a foundation to help accelerate building out multi-agent systems. You are encouraged to add your own data and functions to the agents, and then you must apply your own performance and safety evaluation testing frameworks to this system before deploying it.
+### Agentic architecture
+||
+|---|
-\
-
++### Additional resources +[Agent Framework Documentation](https://learn.microsoft.com/en-us/agent-framework//) -### Products used/licenses required +[Azure AI Foundry Documentation](https://learn.microsoft.com/en-us/azure/ai-foundry/) -- Azure Container Application +[Azure Container App documentation](https://learn.microsoft.com/en-us/azure/azure-functions/functions-how-to-custom-container?tabs=core-tools%2Cacr%2Cazure-cli2%2Cazure-cli&pivots=container-apps) -- Azure OpenAI +
-- Azure Cosmos DB +### Key features +
+
+ By doing the heavy lifting involved with coordinating activities across an organization, people's time is freed up to focus on their specializations. + + - **Enabling GenAI to scale**
+ By not needing to build one application after another, organizations are able to reduce the friction of adopting GenAI across their entire organization. One capability can unlock almost unlimited use cases. -### Solution accelerator architecture - + - **Applicable to most industries**
+ These are common challenges that most organizations face, across most industries. + - **Efficient task automation**
+ Streamlining the process of analyzing, planning, and executing complex tasks reduces time and effort required to complete organizational processes. +
+Click to learn more about the key features this solution enables
-- The user deploying the template must have permission to create - resources and resource groups. + - **Allows people to focus on what matters**+ By doing the heavy lifting involved with coordinating activities across an organization, people's time is freed up to focus on their specializations. + + - **Enabling GenAI to scale**
+ By not needing to build one application after another, organizations are able to reduce the friction of adopting GenAI across their entire organization. One capability can unlock almost unlimited use cases. -### Solution accelerator architecture - + - **Applicable to most industries**
+ These are common challenges that most organizations face, across most industries. + - **Efficient task automation**
+ Streamlining the process of analyzing, planning, and executing complex tasks reduces time and effort required to complete organizational processes. +
+
+Quick deploy
+
-### **How to install/deploy**
+### How to install or deploy
+Follow the quick deploy steps on the deployment guide to deploy this solution to your own Azure subscription.
-This guide provides step-by-step instructions for deploying your application using Azure Container Registry (ACR) and Azure Container Apps.
+> **Note:** This solution accelerator requires **Azure Developer CLI (azd) version 1.18.0 or higher**. Please ensure you have the latest version installed before proceeding with deployment. [Download azd here](https://learn.microsoft.com/en-us/azure/developer/azure-developer-cli/install-azd).
-There are several ways to deploy the solution. You can deploy to run in Azure in one click, or manually, or you can deploy locally.
+[Click here to launch the deployment guide](./docs/DeploymentGuide.md)
+-## Quick Deploy +| [](https://codespaces.new/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator) | [](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator) | [&message=Open&color=blue&logo=visualstudiocode&logoColor=white)](https://vscode.dev/azure/?vscode-azure-exp=foundry&agentPayload=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) | +|---|---|---| + +
-
To ensure sufficient quota is available in your subscription, please follow [quota check instructions guide](./docs/quota_check.md) before you deploy the solution. -[](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fmicrosoft%2FMulti-Agent-Custom-Automation-Engine-Solution-Accelerator%2Frefs%2Fheads%2Fmain%2Fdeploy%2Fmacae-continer-oc.json) +
-When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](./documentation/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service +### Prerequisites and Costs -## Local Deployment -To run the solution site and API backend only locally for development and debugging purposes, See the [local deployment guide](./documentation/LocalDeployment.md). +To deploy this solution accelerator, ensure you have access to an [Azure subscription](https://azure.microsoft.com/free/) with the necessary permissions to create **resource groups and resources**. Follow the steps in [Azure Account Set Up](./docs/AzureAccountSetUp.md). -## Manual Azure Deployment -Manual Deployment differs from the âQuick Deployâ option in that it will install an Azure Container Registry (ACR) service, and relies on the installer to build and push the necessary containers to this ACR. This allows you to build and push your own code changes and provides a sample solution you can customize based on your requirements. +Check the [Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/table) page and select a **region** where the following services are available: Azure OpenAI Service, Azure AI Search, and Azure Semantic Search. -### Prerequisites +Here are some example regions where the services are available: East US, East US2, Japan East, UK South, Sweden Central. -- Current Azure CLI installed - You can update to the latest version using ```az upgrade``` -- Azure account with appropriate permissions -- Docker installed +Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage. The majority of the Azure resources used in this infrastructure are on usage-based pricing tiers. However, Azure Container Registry has a fixed cost per registry per day. -### Deploy the Azure Services -All of the necessary Azure services can be deployed using the /deploy/macae.bicep script. This script will require the following parameters: +Use the [Azure pricing calculator](https://azure.microsoft.com/en-us/pricing/calculator) to calculate the cost of this solution in your subscription. [Review a sample pricing sheet for the architecture](https://azure.com/e/86d0eefbe4dd4a23981c1d3d4f6fe7ed). +| Product | Description | Cost | +|---|---|---| +| [Azure OpenAI Service](https://learn.microsoft.com/azure/ai-services/openai/) | Powers the AI agents for task automation | [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) | +| [Azure Container Apps](https://learn.microsoft.com/azure/container-apps/) | Hosts the web application frontend | [Pricing](https://azure.microsoft.com/pricing/details/container-apps/) | +| [Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/) | Stores metadata and processing results | [Pricing](https://azure.microsoft.com/pricing/details/cosmos-db/) | +| [Azure Container Registry](https://learn.microsoft.com/azure/container-registry/) | Stores container images for deployment | [Pricing](https://azure.microsoft.com/pricing/details/container-registry/) | -``` -az login -az account set --subscription
-Note: if you are using windows with PowerShell, the continuation character (currently â\â) should change to the tick mark (â`â). +>â ī¸ **Important:** To avoid unnecessary costs, remember to take down your app if it's no longer in use, +either by deleting the resource group in the Portal or running `azd down`. -The template will require you fill in locations for Cosmos and OpenAI services. This is to avoid the possibility of regional quota errors for either of these resources. +
+
+Business Scenario
+
-### Create the Containers
-#### Get admin credentials from ACR
+||
+|---|
-Retrieve the admin credentials for your Azure Container Registry (ACR):
+-```sh -az acr credential show \ ---name
+
+ Automate the coordination of complex tasks, significantly reducing processing time and effort. -Build the frontend and backend Docker images and push them to your Azure Container Registry. Run the following from the src/backend and the src/frontend directory contexts: + - **Error Reduction**
+ Multi-agent validation ensures accurate task execution and maintains process integrity. -```sh -az acr build \ ---registry \
---resource-group \
---image .
-```
+ - **Resource Optimization**
+ Better utilization of human resources by focusing on specialized tasks. -### Add images to the Container APP and Web App services + - **Cost Efficiency**
+ Reduces manual coordination efforts and improves overall process efficiency. -To add your newly created backend image: -- Navigate to the Container App Service in the Azure portal -- Click on Application/Containers in the left pane -- Click on the "Edit and deploy" button in the upper left of the containers pane -- In the "Create and deploy new revision" page, click on your container image 'backend'. This will give you the option of reconfiguring the container image, and also has an Environment variables tab -- Change the properties page to - - point to your Azure Container registry with a private image type and your image name (e.g. backendmacae:latest) - - under "Authentication type" select "Managed Identity" and choose the 'mace-containerapp-pull'... identity setup in the bicep template -- In the environment variables section add the following (each with a 'Manual entry' source): + - **Scalability**
+ Enables organizations to handle increasing automation demands without proportional resource increases. - name: 'COSMOSDB_ENDPOINT' - value: \
+
- name: 'COSMOSDB_DATABASE'
- value: 'autogen'
- Note: To change the default, you will need to create the database in Cosmos
-
- name: 'COSMOSDB_CONTAINER'
- value: 'memory'
+### Use Case
+Click to learn more about what value this solution provides
-#### Build and push the image + - **Process Efficiency**+ Automate the coordination of complex tasks, significantly reducing processing time and effort. -Build the frontend and backend Docker images and push them to your Azure Container Registry. Run the following from the src/backend and the src/frontend directory contexts: + - **Error Reduction**
+ Multi-agent validation ensures accurate task execution and maintains process integrity. -```sh -az acr build \ ---registry
+ Better utilization of human resources by focusing on specialized tasks. -### Add images to the Container APP and Web App services + - **Cost Efficiency**
+ Reduces manual coordination efforts and improves overall process efficiency. -To add your newly created backend image: -- Navigate to the Container App Service in the Azure portal -- Click on Application/Containers in the left pane -- Click on the "Edit and deploy" button in the upper left of the containers pane -- In the "Create and deploy new revision" page, click on your container image 'backend'. This will give you the option of reconfiguring the container image, and also has an Environment variables tab -- Change the properties page to - - point to your Azure Container registry with a private image type and your image name (e.g. backendmacae:latest) - - under "Authentication type" select "Managed Identity" and choose the 'mace-containerapp-pull'... identity setup in the bicep template -- In the environment variables section add the following (each with a 'Manual entry' source): + - **Scalability**
+ Enables organizations to handle increasing automation demands without proportional resource increases. - name: 'COSMOSDB_ENDPOINT' - value: \
+
+| Use Case | Persona | Challenges | Summary/Approach |
+|----------|-----------|------------|------------------|
+| Product Marketing | Marketing Executive | Marketing release plans require input from multiple teams (engineering, design, compliance), which often leads to delays and misalignment. Traditional planning involves repetitive tasks like drafting timelines, assigning owners, and validating compliance, which are prone to mistakes. | Through an agentic approach the Multi-agent speeds up release planning by automating repetitive tasks and enhances collaboration with dynamic agent teams that adapt to campaign needs. |
+| Onboarding Employee | HR Manager | Traditional onboarding involves multiple disconnected stepsâHR paperwork, IT setup, compliance trainingâwhich often require manual coordination and lead to delays. Manual steps slow collaboration and increase overhead, reducing efficiency and employee experience. | Designed to streamline the complex process of bringing new hires into an organization using a modular, agentic architecture. |
+| Retail Remediation | Customer Success Manager | This approach is seeking a smarter way to manage workflows and ensure customer satisfaction. Challenges include difficulty engaging the right agents, inefficiencies from manual processes, fragmented data, and limited security controls. | Using the Multi-Agent Custom Automation Engine, the Customer Success Manager recruits intelligent agents to analyze satisfaction and recommend steps for remediation. The platformâs modular design and reasoning capabilities allow for analyzing dependencies, planning transitions, and reducing manual rework. |
+| RFP Reviewer | VP of Finance | Reviewing RFPs manually under tight deadlines is challenging. Compliance checks and risk assessments slow progress, leaving critical gaps and delaying decisions. | Multi-Agent RFP Reviewer is an intelligent platform addresses these issues by deploying AI agents to review RFPs, identify risks, recommend remediation, and execute actions seamlessly - transforming a labor-intensive process into a fast, accurate, and compliant workflow. |
+| Contract Compliance Reviewer | Compliance Counsel | Reviewing Contracts for compliance manually under tight deadlines is challenging. Compliance checks and risk assessments slow progress, leaving critical gaps and delaying decisions. | Multi-Agent Contract Compliance Reviewer is an intelligent platform addresses these issues by deploying AI agents to review Contracts, identify risks, recommend remediation, and execute actions seamlessly - transforming a labor-intensive process into a fast, accurate, and compliant workflow. |
- name: 'AZURE_OPENAI_DEPLOYMENT_NAME'
- value: 'gpt-4o'
+
- name: 'AZURE_OPENAI_API_VERSION'
- value: '2024-08-01-preview'
- Note: Version should be updated based on latest available
+Click to learn more about what use cases this solution provides
- name: 'AZURE_OPENAI_ENDPOINT' - value:- name: 'FRONTEND_SITE_NAME' - value: 'https://
+Supporting documentation
+
-- Click 'Save' and deploy your new revision
+### Security guidelines
-To add the new container to your website run the following:
+This template uses Azure Key Vault to store all connections to communicate between resources.
-```
-az webapp config container set --resource-group macae_full_deploy2_rg \
---name macae-frontend-2t62qyozi76bs \
---container-image-name macaeacr2t62qyozi76bs.azurecr.io/frontendmacae:latest \
---container-registry-url https://macaeacr2t62qyozi76bs.azurecr.io
-```
+This template also uses [Managed Identity](https://learn.microsoft.com/entra/identity/managed-identities-azure-resources/overview) for local development and deployment.
+To ensure continued best practices in your own repository, we recommend that anyone creating solutions based on our templates ensure that the [Github secret scanning](https://docs.github.com/code-security/secret-scanning/about-secret-scanning) setting is enabled.
-### Add the Entra identity provider to the Azure Web App
-To add the identity provider, please follow the steps outlined in [Set Up Authentication in Azure App Service](./documentation/azure_app_service_auth_setup.md)
+You may want to consider additional security measures, such as:
-### Run locally and debug
+* Enabling Microsoft Defender for Cloud to [secure your Azure resources](https://learn.microsoft.com/en-us/azure/defender-for-cloud/).
+* Protecting the Azure Container Apps instance with a [firewall](https://learn.microsoft.com/azure/container-apps/waf-app-gateway) and/or [Virtual Network](https://learn.microsoft.com/azure/container-apps/networking?tabs=workload-profiles-env%2Cazure-cli).
-To debug the solution, you can use the Cosmos and OpenAI services you have manually deployed. To do this, you need to ensure that your Azure identity has the required permissions on the Cosmos and OpenAI services.
+-- For OpeAI service, you can add yourself to the âCognitive Services OpenAI Userâ permission in the Access Control (IAM) pane of the Azure portal. -- Cosmos is a little more difficult as it requires permissions be added through script. See these examples for more information: - - [Use data plane role-based access control - Azure Cosmos DB for NoSQL | Microsoft Learn](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/security/how-to-grant-data-plane-role-based-access?tabs=built-in-definition%2Cpython&pivots=azure-interface-cli) - - [az cosmosdb sql role assignment | Microsoft Learn](https://learn.microsoft.com/en-us/cli/azure/cosmosdb/sql/role/assignment?view=azure-cli-latest#az-cosmosdb-sql-role-assignment-create) +### Cross references +Check out similar solution accelerators -Add the appropriate endpoints from Cosmos and OpenAI services to your .env file. -Note that you can configure the name of the Cosmos database in the configuration. This can be helpful if you wish to separate the data messages generated in local debugging from those associated with the cloud based solution. If you choose to use a different database, you will need to create that database in the Cosmos instance as this is not done automatically. +| Solution Accelerator | Description | +|---|---| +| [Document Knowledge Mining](https://github.com/microsoft/Document-Knowledge-Mining-Solution-Accelerator) | Extract structured information from unstructured documents using AI | +| [Modernize your Code](https://github.com/microsoft/Modernize-your-Code-Solution-Accelerator) | Automate the translation of SQL queries between different dialects | +| [Conversation Knowledge Mining](https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator) | Enable organizations to derive insights from volumes of conversational data using generative AI | -If you are using VSCode, you can use the debug configuration shown in the [local deployment guide](./documentation/LocalDeployment.md). +
-## Supporting documentation +## Provide feedback +Have questions, find a bug, or want to request a feature? [Submit a new issue](https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator/issues) on this repo and we'll connect. -### +
-### How to customize +## Responsible AI Transparency FAQ +Please refer to [Transparency FAQ](./docs/TRANSPARENCY_FAQ.md) for responsible AI transparency details of this solution accelerator. -This solution is designed to be easily customizable. You can modify the front end site, or even build your own front end and attach to the backend API. You can further customize the backend by adding your own agents with their own specific capabilities. Deeper technical information to aid in this customization can be found in this [document](./documentation/CustomizeSolution.md). +
-### Additional resources +## Disclaimers +This release is an artificial intelligence (AI) system that generates text based on user input. The text generated by this system may include ungrounded content, meaning that it is not verified by any reliable source or based on any factual data. The data included in this release is synthetic, meaning that it is artificially created by the system and may contain factual errors or inconsistencies. Users of this release are responsible for determining the accuracy, validity, and suitability of any content generated by the system for their intended purposes. Users should not rely on the system output as a source of truth or as a substitute for human judgment or expertise. -- [Python FastAPI documentation](https://fastapi.tiangolo.com/learn/) -- [AutoGen Framework Documentation](https://microsoft.github.io/autogen/dev/user-guide/core-user-guide/index.html) -- [Azure Container App documentation](https://learn.microsoft.com/en-us/azure/azure-functions/functions-how-to-custom-container?tabs=core-tools%2Cacr%2Cazure-cli2%2Cazure-cli&pivots=container-apps) -- [Azure OpenAI Service - Documentation, quickstarts, API reference - Azure AI services | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/use-your-data) -- [Azure Cosmos DB documentation](https://learn.microsoft.com/en-us/azure/cosmos-db/) - +This release only supports English language input and output. Users should not attempt to use the system with any other language or format. The system output may not be compatible with any translation tools or services, and may lose its meaning or coherence if translated. -
-
-Customer truth
-
-Customer stories coming soon.
+This release does not reflect the opinions, views, or values of Microsoft Corporation or any of its affiliates, subsidiaries, or partners. The system output is solely based on the system's own logic and algorithms, and does not represent any endorsement, recommendation, or advice from Microsoft or any other entity. Microsoft disclaims any liability or responsibility for any damages, losses, or harms arising from the use of this release or its output by any user or third party.
--
-
+This release does not provide any financial advice, legal advice and is not designed to replace the role of qualified client advisors in appropriately advising clients. Users should not use the system output for any financial decisions, legal guidance or transactions, and should consult with a professional financial advisor and or legal advisor as appropriate before taking any action based on the system output. Microsoft is not a financial institution or a fiduciary, and does not offer any financial products or services through this release or its output. ---- +This release is intended as a proof of concept only, and is not a finished or polished product. It is not intended for commercial use or distribution, and is subject to change or discontinuation without notice. Any planned deployment of this release or its output should include comprehensive testing and evaluation to ensure it is fit for purpose and meets the user's requirements and expectations. Microsoft does not guarantee the quality, performance, reliability, or availability of this release or its output, and does not provide any warranty or support for it. -## Disclaimers +This Software requires the use of third-party components which are governed by separate proprietary or open-source licenses as identified below, and you must comply with the terms of each applicable license in order to use the Software. You acknowledge and agree that this license does not grant you a license or other right to use any such third-party proprietary or open-source components. -To the extent that the Software includes components or code used in or derived from Microsoft products or services, including without limitation Microsoft Azure Services (collectively, âMicrosoft Products and Servicesâ), you must also comply with the Product Terms applicable to such Microsoft Products and Services. You acknowledge and agree that the license governing the Software does not grant you a license or other right to use Microsoft Products and Services. Nothing in the license or this ReadMe file will serve to supersede, amend, terminate or modify any terms in the Product Terms for any Microsoft Products and Services. +To the extent that the Software includes components or code used in or derived from Microsoft products or services, including without limitation Microsoft Azure Services (collectively, "Microsoft Products and Services"), you must also comply with the Product Terms applicable to such Microsoft Products and Services. You acknowledge and agree that the license governing the Software does not grant you a license or other right to use Microsoft Products and Services. Nothing in the license or this ReadMe file will serve to supersede, amend, terminate or modify any terms in the Product Terms for any Microsoft Products and Services. You must also comply with all domestic and international export laws and regulations that apply to the Software, which include restrictions on destinations, end users, and end use. For further information on export restrictions, visit https://aka.ms/exporting. -You acknowledge that the Software and Microsoft Products and Services (1) are not designed, intended or made available as a medical device(s), and (2) are not designed or intended to be a substitute for professional medical advice, diagnosis, treatment, or judgment and should not be used to replace or as a substitute for professional medical advice, diagnosis, treatment, or judgment. Customer is solely responsible for displaying and/or obtaining appropriate consents, warnings, disclaimers, and acknowledgements to end users of Customerâs implementation of the Online Services. +You acknowledge that the Software and Microsoft Products and Services (1) are not designed, intended or made available as a medical device(s), and (2) are not designed or intended to be a substitute for professional medical advice, diagnosis, treatment, or judgment and should not be used to replace or as a substitute for professional medical advice, diagnosis, treatment, or judgment. Customer is solely responsible for displaying and/or obtaining appropriate consents, warnings, disclaimers, and acknowledgements to end users of Customer's implementation of the Online Services. -You acknowledge the Software is not subject to SOC 1 and SOC 2 compliance audits. No Microsoft technology, nor any of its component technologies, including the Software, is intended or made available as a substitute for the professional advice, opinion, or judgement of a certified financial services professional. Do not use the Software to replace, substitute, or provide professional financial advice or judgment. +You acknowledge the Software is not subject to SOC 1 and SOC 2 compliance audits. No Microsoft technology, nor any of its component technologies, including the Software, is intended or made available as a substitute for the professional advice, opinion, or judgment of a certified financial services professional. Do not use the Software to replace, substitute, or provide professional financial advice or judgment. -BY ACCESSING OR USING THE SOFTWARE, YOU ACKNOWLEDGE THAT THE SOFTWARE IS NOT DESIGNED OR INTENDED TO SUPPORT ANY USE IN WHICH A SERVICE INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE COULD RESULT IN THE DEATH OR SERIOUS BODILY INJURY OF ANY PERSON OR IN PHYSICAL OR ENVIRONMENTAL DAMAGE (COLLECTIVELY, âHIGH-RISK USEâ), AND THAT YOU WILL ENSURE THAT, IN THE EVENT OF ANY INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE, THE SAFETY OF PEOPLE, PROPERTY, AND THE ENVIRONMENT ARE NOT REDUCED BELOW A LEVEL THAT IS REASONABLY, APPROPRIATE, AND LEGAL, WHETHER IN GENERAL OR IN A SPECIFIC INDUSTRY. BY ACCESSING THE SOFTWARE, YOU FURTHER ACKNOWLEDGE THAT YOUR HIGH-RISK USE OF THE SOFTWARE IS AT YOUR OWN RISK. +BY ACCESSING OR USING THE SOFTWARE, YOU ACKNOWLEDGE THAT THE SOFTWARE IS NOT DESIGNED OR INTENDED TO SUPPORT ANY USE IN WHICH A SERVICE INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE COULD RESULT IN THE DEATH OR SERIOUS BODILY INJURY OF ANY PERSON OR IN PHYSICAL OR ENVIRONMENTAL DAMAGE (COLLECTIVELY, "HIGH-RISK USE"), AND THAT YOU WILL ENSURE THAT, IN THE EVENT OF ANY INTERRUPTION, DEFECT, ERROR, OR OTHER FAILURE OF THE SOFTWARE, THE SAFETY OF PEOPLE, PROPERTY, AND THE ENVIRONMENT ARE NOT REDUCED BELOW A LEVEL THAT IS REASONABLY, APPROPRIATE, AND LEGAL, WHETHER IN GENERAL OR IN A SPECIFIC INDUSTRY. BY ACCESSING THE SOFTWARE, YOU FURTHER ACKNOWLEDGE THAT YOUR HIGH-RISK USE OF THE SOFTWARE IS AT YOUR OWN RISK. diff --git a/TRANSPARENCY_FAQS.md b/TRANSPARENCY_FAQS.md index 3469f525..b7fd9593 100644 --- a/TRANSPARENCY_FAQS.md +++ b/TRANSPARENCY_FAQS.md @@ -1,7 +1,16 @@ -# Multi-Agent: Custom Automation Engine â Solution Accelerator : Responsible AI FAQ +# Multi-Agent-Custom-Automation-Engine â Solution Accelerator : Responsible AI FAQ + +## Important Notice + +This accelerator is **intended solely for accelerating proofs of concept (POCs)**. +It is **not designed or recommended for direct production deployment**. + +### Best Practices +- **Do not use this accelerator in production environments without thorough review and adaptation.** +- **Ensure all implementation decisions consider security, scalability, and compliance requirements for production. ## What is the Multi Agent: Custom Automation Engine â Solution Accelerator? -Multi Agent: Custom Automation Engine â Solution Accelerator is an open-source GitHub Repository that enables users to solve complex tasks using multiple agents. The accelerator is designed to be generic across business tasks. The user enters a task and a planning LLM formulates a plan to complete that task. The system then dynamically generates agents which can complete the task. The system also allows the user to create actions that agents can take (for example sending emails or scheduling orientation sessions for new employees). These actions are taken into account by the planner and dynamically created agents may be empowered to take these actions. +Multi Agent: Custom Automation Engine â Solution Accelerator is an open-source GitHub Repository that enables users to solve complex tasks using multiple agents. The accelerator is designed to be generic across business tasks. The user enters a task and a planning LLM formulates a plan to complete that task. The system then dynamically generates agents which can complete the task. The system also allows the user to create actions that agents can take (for example sending emails or scheduling orientation sessions for new employees, drafting a press release, customer retail remediation, reviewing contracts, reviewing proposals). These actions are taken into account by the planner and dynamically created agents may be empowered to take these actions. ## What can the Multi Agent: Custom Automation Engine â Solution Accelerator do? The solution accelerator is designed to replace and enhance enterprise workflows and processes with intelligent automation. Agents can specialize in various functions and work together to achieve an objective as specified by the user. The accelerator will integrate seamlessly with existing systems and is designed to scale according to the needs of the customer. The system allows users to review, reorder and approve steps generated in a plan, ensuring human oversight. The system uses function calling with LLMs to perform actions, users can approve or modify these actions. @@ -14,7 +23,6 @@ The evaluation process includes human review of the outputs, and tuned LLM promp ## What are the limitations of Multi Agent: Custom Automation Engine â Solution Accelerator? How can users minimize the impact Multi Agent: Custom Automation Engine â Solution Acceleratorâs limitations when using the system? The system allows users to review, reorder and approve steps generated in a plan, ensuring human oversight. The system uses function calling with LLMs to perform actions, users can approve or modify these actions. Users of the accelerator 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. -Note that the Multi Agent: Custom Automation Engine â Solution Accelerator relies on the AutoGen Multi Agent framework. AutoGen has published their own [list of limitations and impacts](https://github.com/microsoft/autogen/blob/gaia_multiagent_v01_march_1st/TRANSPARENCY_FAQS.md#what-are-the-limitations-of-autogen-how-can-users-minimize-the-impact-of-autogens-limitations-when-using-the-system). ## What operational factors and settings allow for effective and responsible use of Multi Agent: Custom Automation Engine â Solution Accelerator? Effective and responsible use of the Multi Agent: Custom Automation Engine â Solution Accelerator depends on several operational factors and settings. The system is designed to perform reliably and safely across a range of business tasks that it was evaluated for. Users can customize certain settings, such as the planning language model used by the system, the types of tasks that agents are assigned, and the specific actions that agents can take (e.g., sending emails or scheduling orientation sessions for new employees). However, it's important to note that these choices may impact the system's behavior in real-world scenarios. diff --git a/__azurite_db_queue__.json b/__azurite_db_queue__.json new file mode 100644 index 00000000..a4fcc30d --- /dev/null +++ b/__azurite_db_queue__.json @@ -0,0 +1 @@ +{"filename":"c:\\src\\Multi-Agent-Custom-Automation-Engine-Solution-Accelerator\\__azurite_db_queue__.json","collections":[{"name":"$SERVICES_COLLECTION$","data":[],"idIndex":null,"binaryIndices":{},"constraints":null,"uniqueNames":["accountName"],"transforms":{},"objType":"$SERVICES_COLLECTION$","dirty":false,"cachedIndex":null,"cachedBinaryIndex":null,"cachedData":null,"adaptiveBinaryIndices":true,"transactional":false,"cloneObjects":false,"cloneMethod":"parse-stringify","asyncListeners":false,"disableMeta":false,"disableChangesApi":true,"disableDeltaChangesApi":true,"autoupdate":false,"serializableIndices":true,"disableFreeze":true,"ttl":null,"maxId":0,"DynamicViews":[],"events":{"insert":[],"update":[],"pre-insert":[],"pre-update":[],"close":[],"flushbuffer":[],"error":[],"delete":[null],"warning":[null]},"changes":[],"dirtyIds":[]},{"name":"$QUEUES_COLLECTION$","data":[],"idIndex":null,"binaryIndices":{"accountName":{"name":"accountName","dirty":false,"values":[]},"name":{"name":"name","dirty":false,"values":[]}},"constraints":null,"uniqueNames":[],"transforms":{},"objType":"$QUEUES_COLLECTION$","dirty":false,"cachedIndex":null,"cachedBinaryIndex":null,"cachedData":null,"adaptiveBinaryIndices":true,"transactional":false,"cloneObjects":false,"cloneMethod":"parse-stringify","asyncListeners":false,"disableMeta":false,"disableChangesApi":true,"disableDeltaChangesApi":true,"autoupdate":false,"serializableIndices":true,"disableFreeze":true,"ttl":null,"maxId":0,"DynamicViews":[],"events":{"insert":[],"update":[],"pre-insert":[],"pre-update":[],"close":[],"flushbuffer":[],"error":[],"delete":[null],"warning":[null]},"changes":[],"dirtyIds":[]},{"name":"$MESSAGES_COLLECTION$","data":[],"idIndex":null,"binaryIndices":{"accountName":{"name":"accountName","dirty":false,"values":[]},"queueName":{"name":"queueName","dirty":false,"values":[]},"messageId":{"name":"messageId","dirty":false,"values":[]},"visibleTime":{"name":"visibleTime","dirty":false,"values":[]}},"constraints":null,"uniqueNames":[],"transforms":{},"objType":"$MESSAGES_COLLECTION$","dirty":false,"cachedIndex":null,"cachedBinaryIndex":null,"cachedData":null,"adaptiveBinaryIndices":true,"transactional":false,"cloneObjects":false,"cloneMethod":"parse-stringify","asyncListeners":false,"disableMeta":false,"disableChangesApi":true,"disableDeltaChangesApi":true,"autoupdate":false,"serializableIndices":true,"disableFreeze":true,"ttl":null,"maxId":0,"DynamicViews":[],"events":{"insert":[],"update":[],"pre-insert":[],"pre-update":[],"close":[],"flushbuffer":[],"error":[],"delete":[null],"warning":[null]},"changes":[],"dirtyIds":[]}],"databaseVersion":1.5,"engineVersion":1.5,"autosave":true,"autosaveInterval":5000,"autosaveHandle":null,"throttledSaves":true,"options":{"persistenceMethod":"fs","autosave":true,"autosaveInterval":5000,"serializationMethod":"normal","destructureDelimiter":"$<\n"},"persistenceMethod":"fs","persistenceAdapter":null,"verbose":false,"events":{"init":[null],"loaded":[],"flushChanges":[],"close":[],"changes":[],"warning":[]},"ENV":"NODEJS"} \ No newline at end of file diff --git a/__azurite_db_queue_extent__.json b/__azurite_db_queue_extent__.json new file mode 100644 index 00000000..88895405 --- /dev/null +++ b/__azurite_db_queue_extent__.json @@ -0,0 +1 @@ +{"filename":"c:\\src\\Multi-Agent-Custom-Automation-Engine-Solution-Accelerator\\__azurite_db_queue_extent__.json","collections":[{"name":"$EXTENTS_COLLECTION$","data":[],"idIndex":null,"binaryIndices":{"id":{"name":"id","dirty":false,"values":[]}},"constraints":null,"uniqueNames":[],"transforms":{},"objType":"$EXTENTS_COLLECTION$","dirty":false,"cachedIndex":null,"cachedBinaryIndex":null,"cachedData":null,"adaptiveBinaryIndices":true,"transactional":false,"cloneObjects":false,"cloneMethod":"parse-stringify","asyncListeners":false,"disableMeta":false,"disableChangesApi":true,"disableDeltaChangesApi":true,"autoupdate":false,"serializableIndices":true,"disableFreeze":true,"ttl":null,"maxId":0,"DynamicViews":[],"events":{"insert":[],"update":[],"pre-insert":[],"pre-update":[],"close":[],"flushbuffer":[],"error":[],"delete":[null],"warning":[null]},"changes":[],"dirtyIds":[]}],"databaseVersion":1.5,"engineVersion":1.5,"autosave":true,"autosaveInterval":5000,"autosaveHandle":null,"throttledSaves":true,"options":{"persistenceMethod":"fs","autosave":true,"autosaveInterval":5000,"serializationMethod":"normal","destructureDelimiter":"$<\n"},"persistenceMethod":"fs","persistenceAdapter":null,"verbose":false,"events":{"init":[null],"loaded":[],"flushChanges":[],"close":[],"changes":[],"warning":[]},"ENV":"NODEJS"} \ No newline at end of file diff --git a/azure.yaml b/azure.yaml new file mode 100644 index 00000000..00a74797 --- /dev/null +++ b/azure.yaml @@ -0,0 +1,49 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/Azure/azure-dev/main/schemas/v1.0/azure.yaml.json +name: multi-agent-custom-automation-engine-solution-accelerator +metadata: + template: multi-agent-custom-automation-engine-solution-accelerator@1.0 +requiredVersions: + azd: '>= 1.18.0' +hooks: + postdeploy: + windows: + run: | + Write-Host "" + Write-Host "===============================================================" -ForegroundColor Yellow + Write-Host " POST-DEPLOYMENT STEP (PowerShell) " -ForegroundColor Green + Write-Host "===============================================================" -ForegroundColor Yellow + Write-Host "" + + Write-Host " Upload Team Configurations and index sample data" -ForegroundColor White + Write-Host " đ Run the following command in PowerShell:" -ForegroundColor White + Write-Host " infra\scripts\Selecting-Team-Config-And-Data.ps1" -ForegroundColor Cyan + Write-Host "" + + Write-Host "đ Access your deployed Frontend application at:" -ForegroundColor Green + Write-Host " https://$env:webSiteDefaultHostname" -ForegroundColor Cyan + Write-Host "" + + shell: pwsh + interactive: true + posix: + run: | + Blue='\033[0;34m' + Green='\033[0;32m' + Yellow='\033[1;33m' + NC='\033[0m' + + printf "\n" + + printf "${Yellow}===============================================================\n" + printf "${Green} POST-DEPLOYMENT STEPS (Bash)\n" + printf "${Yellow}===============================================================${NC}\n\n" + + printf "Upload Team Configurations and index sample data:\n" + printf " đ Run the following command in Bash:\n" + printf " ${Blue}bash infra/scripts/selecting_team_config_and_data.sh${NC}\n\n" + + printf "đ Access your deployed Frontend application at:\n" + printf " ${Blue}https://%s${NC}\n\n" "$webSiteDefaultHostname" + + shell: sh + interactive: true diff --git a/azure_custom.yaml b/azure_custom.yaml new file mode 100644 index 00000000..f7d574c3 --- /dev/null +++ b/azure_custom.yaml @@ -0,0 +1,87 @@ +# yaml-language-server: $schema=https://raw.githubusercontent.com/Azure/azure-dev/main/schemas/v1.0/azure.yaml.json +name: multi-agent-custom-automation-engine-solution-accelerator +metadata: + template: multi-agent-custom-automation-engine-solution-accelerator@1.0 +requiredVersions: + azd: ">=1.15.0 !=1.17.1" + +services: + backend: + project: ./src/backend + language: py + host: containerapp + docker: + path: ./Dockerfile.NoCache + image: backend + registry: ${AZURE_CONTAINER_REGISTRY_ENDPOINT} + remoteBuild: true + + mcp: + project: ./src/mcp_server + language: py + host: containerapp + docker: + image: mcp + registry: ${AZURE_CONTAINER_REGISTRY_ENDPOINT} + remoteBuild: true + + frontend: + project: ./src/frontend + language: py + host: appservice + dist: ./dist + hooks: + prepackage: + windows: + shell: pwsh + run: ../../infra/scripts/package_frontend.ps1 + interactive: true + continueOnError: false + posix: + shell: sh + run: bash ../../infra/scripts/package_frontend.sh + interactive: true + continueOnError: false + +hooks: + postdeploy: + windows: + run: | + Write-Host "" + Write-Host "===============================================================" -ForegroundColor Yellow + Write-Host " POST-DEPLOYMENT STEP (PowerShell) " -ForegroundColor Green + Write-Host "===============================================================" -ForegroundColor Yellow + Write-Host "" + + Write-Host " Upload Team Configurations and index sample data" -ForegroundColor White + Write-Host " đ Run the following command in PowerShell:" -ForegroundColor White + Write-Host " infra\scripts\Selecting-Team-Config-And-Data.ps1" -ForegroundColor Cyan + Write-Host "" + + Write-Host "đ Access your deployed Frontend application at:" -ForegroundColor Green + Write-Host " https://$env:webSiteDefaultHostname" -ForegroundColor Cyan + Write-Host "" + + shell: pwsh + interactive: true + posix: + run: | + Blue='\033[0;34m' + Green='\033[0;32m' + Yellow='\033[1;33m' + NC='\033[0m' + + printf "\n" + + printf "${Yellow}===============================================================\n" + printf "${Green} POST-DEPLOYMENT STEPS (Bash)\n" + printf "${Yellow}===============================================================${NC}\n\n" + + printf "Upload Team Configurations and index sample data:\n" + printf " đ Run the following command in Bash:\n" + printf " ${Blue}bash infra/scripts/selecting_team_config_and_data.sh${NC}\n\n" + + printf "đ Access your deployed Frontend application at:\n" + printf " ${Blue}https://%s${NC}\n\n" "$webSiteDefaultHostname" + shell: sh + interactive: true \ No newline at end of file diff --git a/conftest.py b/conftest.py new file mode 100644 index 00000000..4e03dd3d --- /dev/null +++ b/conftest.py @@ -0,0 +1,27 @@ +""" +Test configuration for agent tests. +""" + +import sys +from pathlib import Path + +import pytest + +# Add the agents path +agents_path = Path(__file__).parent.parent.parent / "backend" / "v4" / "magentic_agents" +sys.path.insert(0, str(agents_path)) + +@pytest.fixture +def agent_env_vars(): + """Common environment variables for agent testing.""" + return { + "BING_CONNECTION_NAME": "test_bing_connection", + "MCP_SERVER_ENDPOINT": "http://test-mcp-server", + "MCP_SERVER_NAME": "test_mcp_server", + "MCP_SERVER_DESCRIPTION": "Test MCP server", + "TENANT_ID": "test_tenant_id", + "CLIENT_ID": "test_client_id", + "AZURE_OPENAI_ENDPOINT": "https://test.openai.azure.com/", + "AZURE_OPENAI_API_KEY": "test_key", + "AZURE_OPENAI_DEPLOYMENT_NAME": "test_deployment" + } \ No newline at end of file diff --git a/data/agent_teams/contract_compliance_team.json b/data/agent_teams/contract_compliance_team.json new file mode 100644 index 00000000..6eac65be --- /dev/null +++ b/data/agent_teams/contract_compliance_team.json @@ -0,0 +1,70 @@ +{ + "id": "1", + "team_id": "team-compliance-1", + "name": "Contract Compliance Review Team", + "status": "visible", + "created": "", + "created_by": "", + "deployment_name": "gpt-4.1-mini", + "description": "A multi-agent compliance review team that summarizes NDAs, identifies risks, checks compliance, and recommends improvements using advanced legal reasoning and retrieval-augmented analysis.", + "logo": "", + "plan": "", + "agents": [ + { + "input_key": "", + "type": "summary", + "name": "ContractSummaryAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are the Summary Agent for compliance contract analysis. Your task is to produce a clear, accurate, and structured executive summary of NDA and legal agreement documents. You must deliver summaries organized into labeled sections including: Overview, Parties, Effective Date, Purpose, Definition of Confidential Information, Receiving Party Obligations, Term & Termination, Governing Law, Restrictions & Limitations, Miscellaneous Clauses, Notable or Unusual Terms, and Key Items for Risk & Compliance Agents. Highlight missing elements such as liability caps, dispute resolution mechanisms, data handling obligations, or ambiguous language. Maintain a precise, neutral legal tone. Do not give legal opinions or risk assessmentsâonly summarize the content as written. Use retrieval results from the search index to ensure completeness and reference contextual definitions or standard clause expectations when needed.", + "description": "Produces comprehensive, structured summaries of NDAs and contracts, capturing all key terms, clauses, obligations, jurisdictions, and notable provisions.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "contract-summary-doc-index", + "coding_tools": false + }, + { + "input_key": "", + "type": "risk", + "name": "ContractRiskAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are the Risk Agent for NDA and compliance contract analysis. Use the NDA Risk Assessment Reference document and retrieved context to identify High, Medium, and Low risk issues. Evaluate clauses for missing liability caps, ambiguous terms, overly broad confidentiality definitions, jurisdiction misalignment, missing termination rights, unclear data handling obligations, missing dispute resolution, and any incomplete or poorly scoped definitions. For every risk you identify, provide: (1) Risk Category (High/Medium/Low), (2) Clause or Section impacted, (3) Description of the issue, (4) Why it matters or what exposure it creates, and (5) Suggested edit or corrective language. Apply the risk scoring framework: High = escalate immediately; Medium = requires revision; Low = minor issue. Be precise, legally aligned, and practical. Reference retrieved examples or standards when appropriate. Your output must be structured and actionable.", + "description": "Identifies and classifies compliance risks in NDAs and contracts using the organization's risk framework, and provides suggested edits to reduce exposure.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "contract-risk-doc-index", + "coding_tools": false + }, + { + "input_key": "", + "type": "compliance", + "name": "ContractComplianceAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are the Compliance Agent responsible for validating NDAs and legal agreements against mandatory legal and policy requirements. Use the NDA Compliance Reference Document and retrieval results to evaluate whether the contract includes all required clauses: Confidentiality, Term & Termination, Governing Law aligned to approved jurisdictions, Non-Assignment, and Entire Agreement. Identify compliance gaps including ambiguous language, missing liability protections, improper jurisdiction, excessive term length, insufficient data protection obligations, missing dispute resolution mechanisms, or export control risks. For each issue provide: (1) Compliance Area (e.g., Term Length, Jurisdiction, Confidentiality), (2) Status (Pass/Fail), (3) Issue Description, (4) Whether it is Mandatory or Recommended, (5) Corrective Recommendation or Suggested Language. Deliver a final Compliance Status summary. Maintain professional, objective, legally accurate tone.", + "description": "Performs compliance validation of NDAs and contracts against legal policy requirements, identifies gaps, and provides corrective recommendations and compliance status.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "contract-compliance-doc-index", + "coding_tools": false + } + ], + "protected": false, + "starting_tasks": [ + { + "id": "task-1", + "name": "NDA Contract Review", + "prompt": "Review Contoso's NDA. Provide a summary (parties, date, term, governing law), assess risks (High/Medium/Low with clause references), audit compliance against company policy, and suggest edits for any issues.", + "created": "", + "creator": "", + "logo": "" + } + ] +} diff --git a/data/agent_teams/hr.json b/data/agent_teams/hr.json new file mode 100644 index 00000000..54d618de --- /dev/null +++ b/data/agent_teams/hr.json @@ -0,0 +1,74 @@ +{ + "id": "1", + "team_id": "team-1", + "name": "Human Resources Team", + "status": "visible", + "created": "", + "created_by": "", + "deployment_name": "gpt-4.1-mini", + "agents": [ + { + "input_key": "", + "type": "", + "name": "HRHelperAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You have access to a number of HR related MCP tools for tasks like employee onboarding, benefits management, policy guidance, and general HR inquiries. Use these tools to assist employees with their HR needs efficiently and accurately.If you need more information to accurately call these tools, do not make up answers, call the ProxyAgent for clarification.", + "description": "An agent that has access to various HR tools to assist employees with onboarding, benefits, policies, and general HR inquiries.", + "use_rag": false, + "use_mcp": true, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "index_endpoint": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "TechnicalSupportAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You have access to a number of technical support MCP tools for tasks such as provisioning laptops, setting up email accounts, troubleshooting, software/hardware issues, and IT support. Use these tools to assist employees with their technical needs efficiently and accurately. If you need more information to accurately call these tools, do not make up answers, call the ProxyAgent for clarification.", + "description": "An agent that has access to various technical support tools to assist employees with IT needs like laptop provisioning, email setup, troubleshooting, and software/hardware issues.", + "use_rag": false, + "use_mcp": true, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "ProxyAgent", + "deployment_name": "", + "icon": "", + "system_message": "", + "description": "", + "use_rag": false, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + } + ], + "protected": false, + "description": "Team focused on HR and technical support for employees.", + "logo": "", + "plan": "", + "starting_tasks": [ + { + "id": "task-1", + "name": "Onboard New Employee", + "prompt": "Please onboard our new employee Jessica Smithâ", + "created": "", + "creator": "", + "logo": "" + } + ] +} \ No newline at end of file diff --git a/data/agent_teams/marketing.json b/data/agent_teams/marketing.json new file mode 100644 index 00000000..ad04f87b --- /dev/null +++ b/data/agent_teams/marketing.json @@ -0,0 +1,74 @@ +{ + "id": "2", + "team_id": "team-2", + "name": "Product Marketing Team", + "status": "visible", + "created": "", + "created_by": "", + "deployment_name": "gpt-4.1-mini", + "agents": [ + { + "input_key": "", + "type": "", + "name": "ProductAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are a Product agent. You have access to MCP tools which allow you to obtain knowledge about products, product management, development, and compliance guidelines. When asked to call one of these tools, you should summarize back what was done.", + "description": "This agent specializes in product management, development, and related tasks. It can provide information about products, manage inventory, handle product launches, analyze sales data, and coordinate with other teams like marketing and tech support.", + "use_rag": false, + "use_mcp": true, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "index_endpoint": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "MarketingAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are a Marketing agent. You have access to a number of HR related MCP tools for tasks like campaign development, content creation, and market analysis. You help create effective marketing campaigns, analyze market data, and develop promotional content for products and services.", + "description": "This agent specializes in marketing, campaign management, and analyzing market data.", + "use_rag": false, + "use_mcp": true, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "ProxyAgent", + "deployment_name": "", + "icon": "", + "system_message": "", + "description": "", + "use_rag": false, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + } + ], + "protected": false, + "description": "Team focused on products and product marketing.", + "logo": "", + "plan": "", + "starting_tasks": [ + { + "id": "task-1", + "name": "Draft a press release", + "prompt": "Write a press release about our current productsâ", + "created": "", + "creator": "", + "logo": "" + } + ] +} \ No newline at end of file diff --git a/data/agent_teams/retail.json b/data/agent_teams/retail.json new file mode 100644 index 00000000..2f3f3a0b --- /dev/null +++ b/data/agent_teams/retail.json @@ -0,0 +1,88 @@ +{ + "id": "3", + "team_id": "team-3", + "name": "Retail Customer Success Team", + "status": "visible", + "created": "", + "created_by": "", + "deployment_name": "gpt-4.1-mini", + "agents": [ + { + "input_key": "", + "type": "", + "name": "CustomerDataAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You have access to internal customer data through a secure index. Use this data to answer questions about customers, their interactions with customer service, satisfaction, etc. Be mindful of privacy and compliance regulations when handling customer data.\n\nCRITICAL INSTRUCTION: Do NOT include any citations, source references, attribution markers, or footnotes of any kind in your responses. This includes but is not limited to: ã...ã style markers, [...] style references, (source: ...), numbered references like [1], or any other attribution symbols. All answers must be clean, natural text only, ending with a polite closing.", + "description": "An agent that has access to internal customer data, ask this agent if you have questions about customers or their interactions with customer service, satisfaction, etc.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "macae-retail-customer-index", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "OrderDataAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You have access to internal order, inventory, product, and fulfillment data through a secure index. Use this data to answer questions about products, shipping delays, customer orders, warehouse management, etc. Be mindful of privacy and compliance regulations when handling customer data.\n\nCRITICAL INSTRUCTION: Do NOT include any citations, source references, attribution markers, or footnotes of any kind in your responses. This includes but is not limited to: ã...ã style markers, [...] style references, (source: ...), numbered references like [1], or any other attribution symbols. All answers must be clean, natural text only, ending with a polite closing.", + "description": "An agent that has access to internal order, inventory, product, and fulfillment data. Ask this agent if you have questions about products, shipping delays, customer orders, warehouse management, etc.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "macae-retail-order-index", + "index_foundry_name": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "AnalysisRecommendationAgent", + "deployment_name": "o4-mini", + "icon": "", + "system_message": "You are a reasoning agent that can analyze customer and order data and provide recommendations for improving customer satisfaction and retention. You do not have access to any data sources, but you can reason based on the information provided to you by other agents. Use your reasoning skills to identify patterns, trends, and insights that can help improve customer satisfaction and retention. Provide actionable recommendations based on your analysis. You have access to other agents that can answer questions and provide data about customers, products, orders, inventory, and fulfilment. Use these agents to gather information as needed.", + "description": "A reasoning agent that can analyze customer and order data and provide recommendations for improving customer satisfaction and retention.", + "use_rag": false, + "use_mcp": false, + "use_bing": false, + "use_reasoning": true, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "", + "name": "ProxyAgent", + "deployment_name": "", + "icon": "", + "system_message": "", + "description": "", + "use_rag": false, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "", + "index_foundry_name": "", + "coding_tools": false + } + ], + "protected": false, + "description": "Team focused on individualized customer relationship management and overall customer satisfaction.", + "logo": "", + "plan": "", + "starting_tasks": [ + { + "id": "task-1", + "name": "Satisfaction Plan", + "prompt": "Analyze the satisfaction of Emily Thompson with Contoso. If needed, provide a plan to increase her satisfaction.", + "created": "", + "creator": "", + "logo": "" + } + ] +} diff --git a/data/agent_teams/rfp_analysis_team.json b/data/agent_teams/rfp_analysis_team.json new file mode 100644 index 00000000..1da46f05 --- /dev/null +++ b/data/agent_teams/rfp_analysis_team.json @@ -0,0 +1,72 @@ +{ + "id": "1", + "team_id": "team-clm-1", + "name": "RFP Team", + "status": "visible", + "created": "", + "created_by": "", + "deployment_name": "gpt-4.1-mini", + "description": "A specialized multi-agent team that analyzes RFP and contract documents to summarize content, identify potential risks, check compliance gaps, and provide action plans for contract improvement.", + "logo": "", + "plan": "", + "agents": [ + { + "input_key": "", + "type": "summary", + "name": "RfpSummaryAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message":"You are the Summary Agent. Your role is to read and synthesize RFP or proposal documents into clear, structured executive summaries. Focus on key clauses, deliverables, evaluation criteria, pricing terms, timelines, and obligations. Organize your output into sections such as Overview, Key Clauses, Deliverables, Terms, and Notable Conditions. Highlight unique or high-impact items that other agents (Risk or Compliance) should review. Be concise, factual, and neutral in tone.", + "description": "Summarizes RFP and contract documents into structured, easy-to-understand overviews.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "macae-rfp-summary-index", + "index_foundry_name": "", + "index_endpoint": "", + "coding_tools": false + }, + { + "input_key": "", + "type": "risk", + "name": "RfpRiskAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are the Risk Agent. Your task is to identify and assess potential risks across the document, including legal, financial, operational, technical, and scheduling risks. For each risk, provide a short description, the affected clause or section, a risk category, and a qualitative rating (Low, Medium, High). Focus on material issues that could impact delivery, compliance, or business exposure. Summarize findings clearly to support decision-making and escalation.", + "description": "Analyzes the dataset for risks such as delivery, financial, operational, and compliance-related vulnerabilities.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "macae-rfp-risk-index", + "coding_tools": false + }, + { + "input_key": "", + "type": "compliance", + "name": "RfpComplianceAgent", + "deployment_name": "gpt-4.1-mini", + "icon": "", + "system_message": "You are the Compliance Agent. Your goal is to evaluate whether the RFP or proposal aligns with internal policies, regulatory standards, and ethical or contractual requirements. Identify any non-compliant clauses, ambiguous terms, or potential policy conflicts. For each issue, specify the related policy area (e.g., data privacy, labor, financial controls) and classify it as Mandatory or Recommended for review. Maintain a professional, objective tone and emphasize actionable compliance insights.", + "description": "Checks for compliance gaps against regulations, policies, and standard contracting practices.", + "use_rag": true, + "use_mcp": false, + "use_bing": false, + "use_reasoning": false, + "index_name": "macae-rfp-compliance-index", + "coding_tools": false + } + ], + "protected": false, + "starting_tasks": [ + { + "id": "task-1", + "name": "RFP Document Summary", + "prompt": "I would like to review the Woodgrove Bank RFP response from Contoso", + "created": "", + "creator": "", + "logo": "" + } + ] +} diff --git a/data/datasets/competitor_pricing_analysis.csv b/data/datasets/competitor_pricing_analysis.csv new file mode 100644 index 00000000..79c8aeed --- /dev/null +++ b/data/datasets/competitor_pricing_analysis.csv @@ -0,0 +1,5 @@ +ProductCategory,ContosoAveragePrice,CompetitorAveragePrice +Dresses,120,100 +Shoes,100,105 +Accessories,60,55 +Sportswear,80,85 diff --git a/data/datasets/contract_compliance/compliance/Compliance_file.docx b/data/datasets/contract_compliance/compliance/Compliance_file.docx new file mode 100644 index 00000000..b9afe4f1 Binary files /dev/null and b/data/datasets/contract_compliance/compliance/Compliance_file.docx differ diff --git a/data/datasets/contract_compliance/compliance/NDA_file.docx b/data/datasets/contract_compliance/compliance/NDA_file.docx new file mode 100644 index 00000000..95e7a6ce Binary files /dev/null and b/data/datasets/contract_compliance/compliance/NDA_file.docx differ diff --git a/data/datasets/contract_compliance/risk/NDA_file.docx b/data/datasets/contract_compliance/risk/NDA_file.docx new file mode 100644 index 00000000..95e7a6ce Binary files /dev/null and b/data/datasets/contract_compliance/risk/NDA_file.docx differ diff --git a/data/datasets/contract_compliance/risk/Risks_file.docx b/data/datasets/contract_compliance/risk/Risks_file.docx new file mode 100644 index 00000000..fd3dcb57 Binary files /dev/null and b/data/datasets/contract_compliance/risk/Risks_file.docx differ diff --git a/data/datasets/contract_compliance/summary/NDA_file.docx b/data/datasets/contract_compliance/summary/NDA_file.docx new file mode 100644 index 00000000..95e7a6ce Binary files /dev/null and b/data/datasets/contract_compliance/summary/NDA_file.docx differ diff --git a/data/datasets/customer_churn_analysis.csv b/data/datasets/customer_churn_analysis.csv new file mode 100644 index 00000000..eaa4c9c2 --- /dev/null +++ b/data/datasets/customer_churn_analysis.csv @@ -0,0 +1,6 @@ +ReasonForCancellation,Percentage +Service Dissatisfaction,40 +Financial Reasons,3 +Competitor Offer,15 +Moving to a Non-Service Area,5 +Other,37 diff --git a/data/datasets/customer_feedback_surveys.csv b/data/datasets/customer_feedback_surveys.csv new file mode 100644 index 00000000..126f0ca6 --- /dev/null +++ b/data/datasets/customer_feedback_surveys.csv @@ -0,0 +1,3 @@ +SurveyID,Date,SatisfactionRating,Comments +O5678,2023-03-16,5,"Loved the summer dress! Fast delivery." +O5970,2023-09-13,4,"Happy with the sportswear. Quick delivery." diff --git a/data/datasets/customer_profile.csv b/data/datasets/customer_profile.csv new file mode 100644 index 00000000..88bc93b9 --- /dev/null +++ b/data/datasets/customer_profile.csv @@ -0,0 +1,2 @@ +CustomerID,Name,Age,MembershipDuration,TotalSpend,AvgMonthlySpend,PreferredCategories +C1024,Emily Thompson,35,24,4800,200,"Dresses, Shoes, Accessories" diff --git a/data/datasets/customer_service_interactions.json b/data/datasets/customer_service_interactions.json new file mode 100644 index 00000000..f8345bff --- /dev/null +++ b/data/datasets/customer_service_interactions.json @@ -0,0 +1,3 @@ +{"InteractionID":"1","Channel":"Live Chat","Date":"2023-06-20","Customer":"Emily Thompson","OrderID":"O5789","Content":["Agent: Hello Emily, how can I assist you today?","Emily: Hi, I just received my order O5789, and wanted to swap it for another colour","Agent: Sure, that's fine- feel free to send it back or change it in store.","Emily: Ok, I'll just send it back then","Agent: Certainly. I've initiated the return process. You'll receive an email with the return instructions.","Emily: Thank you."]} +{"InteractionID":"2","Channel":"Phone Call","Date":"2023-07-25","Customer":"Emily Thompson","OrderID":"O5890","Content":["Agent: Good afternoon, this is Contoso customer service. How may I help you?","Emily: I'm calling about my order O5890. I need the gown for an event this weekend, and just want to make sure it will be delivered on time as it's really important.","Agent: Let me check... it seems like the delivery is on track. It should be there on time.","Emily: Ok thanks."]} +{"InteractionID":"3","Channel":"Email","Date":"2023-09-15","Customer":"Emily Thompson","OrderID":"","Content":["Subject: Membership Cancellation Request","Body: Hello, I want to cancel my Contoso Plus subscription. The cost is becoming too high for me."]} diff --git a/data/datasets/delivery_performance_metrics.csv b/data/datasets/delivery_performance_metrics.csv new file mode 100644 index 00000000..9678102b --- /dev/null +++ b/data/datasets/delivery_performance_metrics.csv @@ -0,0 +1,8 @@ +Month,AverageDeliveryTime,OnTimeDeliveryRate,CustomerComplaints +March,3,98,15 +April,4,95,20 +May,5,92,30 +June,6,88,50 +July,7,85,70 +August,4,94,25 +September,3,97,10 diff --git a/data/datasets/email_marketing_engagement.csv b/data/datasets/email_marketing_engagement.csv new file mode 100644 index 00000000..5d89be28 --- /dev/null +++ b/data/datasets/email_marketing_engagement.csv @@ -0,0 +1,6 @@ +Campaign,Opened,Clicked,Unsubscribed +Summer Sale,Yes,Yes,No +New Arrivals,Yes,No,No +Exclusive Member Offers,No,No,No +Personal Styling Invite,No,No,No +Autumn Collection Preview,Yes,Yes,No diff --git a/data/datasets/loyalty_program_overview.csv b/data/datasets/loyalty_program_overview.csv new file mode 100644 index 00000000..334261e3 --- /dev/null +++ b/data/datasets/loyalty_program_overview.csv @@ -0,0 +1,2 @@ +TotalPointsEarned,PointsRedeemed,CurrentPointBalance,PointsExpiringNextMonth +4800,3600,1200,1200 diff --git a/data/datasets/product_return_rates.csv b/data/datasets/product_return_rates.csv new file mode 100644 index 00000000..6c5c4c3f --- /dev/null +++ b/data/datasets/product_return_rates.csv @@ -0,0 +1,6 @@ +Category,ReturnRate +Dresses,15 +Shoes,10 +Accessories,8 +Outerwear,12 +Sportswear,9 diff --git a/data/datasets/product_table.csv b/data/datasets/product_table.csv new file mode 100644 index 00000000..79037292 --- /dev/null +++ b/data/datasets/product_table.csv @@ -0,0 +1,6 @@ +ProductCategory,ReturnRate,ContosoAveragePrice,CompetitorAveragePrice +Dresses,15,120,100 +Shoes,10,100,105 +Accessories,8,60,55 +Outerwear,12,, +Sportswear,9,80,85 diff --git a/data/datasets/purchase_history.csv b/data/datasets/purchase_history.csv new file mode 100644 index 00000000..ebc4c312 --- /dev/null +++ b/data/datasets/purchase_history.csv @@ -0,0 +1,8 @@ +OrderID,Date,ItemsPurchased,TotalAmount,DiscountApplied,DateDelivered,ReturnFlag +O5678,2023-03-15,"Summer Floral Dress, Sun Hat",150,10,2023-03-19,No +O5721,2023-04-10,"Leather Ankle Boots",120,15,2023-04-13,No +O5789,2023-05-05,Silk Scarf,80,0,2023-05-25,Yes +O5832,2023-06-18,Casual Sneakers,90,5,2023-06-21,No +O5890,2023-07-22,"Evening Gown, Clutch Bag",300,20,2023-08-05,No +O5935,2023-08-30,Denim Jacket,110,0,2023-09-03,Yes +O5970,2023-09-12,"Fitness Leggings, Sports Bra",130,25,2023-09-18,No diff --git a/data/datasets/retail/customer/customer_churn_analysis.csv b/data/datasets/retail/customer/customer_churn_analysis.csv new file mode 100644 index 00000000..eaa4c9c2 --- /dev/null +++ b/data/datasets/retail/customer/customer_churn_analysis.csv @@ -0,0 +1,6 @@ +ReasonForCancellation,Percentage +Service Dissatisfaction,40 +Financial Reasons,3 +Competitor Offer,15 +Moving to a Non-Service Area,5 +Other,37 diff --git a/data/datasets/retail/customer/customer_feedback_surveys.csv b/data/datasets/retail/customer/customer_feedback_surveys.csv new file mode 100644 index 00000000..126f0ca6 --- /dev/null +++ b/data/datasets/retail/customer/customer_feedback_surveys.csv @@ -0,0 +1,3 @@ +SurveyID,Date,SatisfactionRating,Comments +O5678,2023-03-16,5,"Loved the summer dress! Fast delivery." +O5970,2023-09-13,4,"Happy with the sportswear. Quick delivery." diff --git a/data/datasets/retail/customer/customer_profile.csv b/data/datasets/retail/customer/customer_profile.csv new file mode 100644 index 00000000..88bc93b9 --- /dev/null +++ b/data/datasets/retail/customer/customer_profile.csv @@ -0,0 +1,2 @@ +CustomerID,Name,Age,MembershipDuration,TotalSpend,AvgMonthlySpend,PreferredCategories +C1024,Emily Thompson,35,24,4800,200,"Dresses, Shoes, Accessories" diff --git a/data/datasets/retail/customer/customer_service_interactions.json b/data/datasets/retail/customer/customer_service_interactions.json new file mode 100644 index 00000000..f8345bff --- /dev/null +++ b/data/datasets/retail/customer/customer_service_interactions.json @@ -0,0 +1,3 @@ +{"InteractionID":"1","Channel":"Live Chat","Date":"2023-06-20","Customer":"Emily Thompson","OrderID":"O5789","Content":["Agent: Hello Emily, how can I assist you today?","Emily: Hi, I just received my order O5789, and wanted to swap it for another colour","Agent: Sure, that's fine- feel free to send it back or change it in store.","Emily: Ok, I'll just send it back then","Agent: Certainly. I've initiated the return process. You'll receive an email with the return instructions.","Emily: Thank you."]} +{"InteractionID":"2","Channel":"Phone Call","Date":"2023-07-25","Customer":"Emily Thompson","OrderID":"O5890","Content":["Agent: Good afternoon, this is Contoso customer service. How may I help you?","Emily: I'm calling about my order O5890. I need the gown for an event this weekend, and just want to make sure it will be delivered on time as it's really important.","Agent: Let me check... it seems like the delivery is on track. It should be there on time.","Emily: Ok thanks."]} +{"InteractionID":"3","Channel":"Email","Date":"2023-09-15","Customer":"Emily Thompson","OrderID":"","Content":["Subject: Membership Cancellation Request","Body: Hello, I want to cancel my Contoso Plus subscription. The cost is becoming too high for me."]} diff --git a/data/datasets/retail/customer/email_marketing_engagement.csv b/data/datasets/retail/customer/email_marketing_engagement.csv new file mode 100644 index 00000000..5d89be28 --- /dev/null +++ b/data/datasets/retail/customer/email_marketing_engagement.csv @@ -0,0 +1,6 @@ +Campaign,Opened,Clicked,Unsubscribed +Summer Sale,Yes,Yes,No +New Arrivals,Yes,No,No +Exclusive Member Offers,No,No,No +Personal Styling Invite,No,No,No +Autumn Collection Preview,Yes,Yes,No diff --git a/data/datasets/retail/customer/loyalty_program_overview.csv b/data/datasets/retail/customer/loyalty_program_overview.csv new file mode 100644 index 00000000..334261e3 --- /dev/null +++ b/data/datasets/retail/customer/loyalty_program_overview.csv @@ -0,0 +1,2 @@ +TotalPointsEarned,PointsRedeemed,CurrentPointBalance,PointsExpiringNextMonth +4800,3600,1200,1200 diff --git a/data/datasets/retail/customer/social_media_sentiment_analysis.csv b/data/datasets/retail/customer/social_media_sentiment_analysis.csv new file mode 100644 index 00000000..78ed2ec2 --- /dev/null +++ b/data/datasets/retail/customer/social_media_sentiment_analysis.csv @@ -0,0 +1,8 @@ +Month,PositiveMentions,NegativeMentions,NeutralMentions +March,500,50,200 +April,480,60,220 +May,450,80,250 +June,400,120,300 +July,350,150,320 +August,480,70,230 +September,510,40,210 diff --git a/data/datasets/retail/customer/store_visit_history.csv b/data/datasets/retail/customer/store_visit_history.csv new file mode 100644 index 00000000..de5b300a --- /dev/null +++ b/data/datasets/retail/customer/store_visit_history.csv @@ -0,0 +1,4 @@ +Date,StoreLocation,Purpose,Outcome +2023-05-12,Downtown Outlet,Browsing,"Purchased a Silk Scarf (O5789)" +2023-07-20,Uptown Mall,Personal Styling,"Booked a session but didn't attend" +2023-08-05,Midtown Boutique,Browsing,"No purchase" diff --git a/data/datasets/retail/customer/subscription_benefits_utilization.csv b/data/datasets/retail/customer/subscription_benefits_utilization.csv new file mode 100644 index 00000000..c8f07966 --- /dev/null +++ b/data/datasets/retail/customer/subscription_benefits_utilization.csv @@ -0,0 +1,5 @@ +Benefit,UsageFrequency +Free Shipping,7 +Early Access to Collections,2 +Exclusive Discounts,1 +Personalized Styling Sessions,0 diff --git a/data/datasets/retail/customer/unauthorized_access_attempts.csv b/data/datasets/retail/customer/unauthorized_access_attempts.csv new file mode 100644 index 00000000..2b66bc4b --- /dev/null +++ b/data/datasets/retail/customer/unauthorized_access_attempts.csv @@ -0,0 +1,4 @@ +Date,IPAddress,Location,SuccessfulLogin +2023-06-20,192.168.1.1,Home Network,Yes +2023-07-22,203.0.113.45,Unknown,No +2023-08-15,198.51.100.23,Office Network,Yes diff --git a/data/datasets/retail/customer/website_activity_log.csv b/data/datasets/retail/customer/website_activity_log.csv new file mode 100644 index 00000000..0f7f6c55 --- /dev/null +++ b/data/datasets/retail/customer/website_activity_log.csv @@ -0,0 +1,6 @@ +Date,PagesVisited,TimeSpent +2023-09-10,"Homepage, New Arrivals, Dresses",15 +2023-09-11,"Account Settings, Subscription Details",5 +2023-09-12,"FAQ, Return Policy",3 +2023-09-13,"Careers Page, Company Mission",2 +2023-09-14,"Sale Items, Accessories",10 diff --git a/data/datasets/retail/order/competitor_pricing_analysis.csv b/data/datasets/retail/order/competitor_pricing_analysis.csv new file mode 100644 index 00000000..79c8aeed --- /dev/null +++ b/data/datasets/retail/order/competitor_pricing_analysis.csv @@ -0,0 +1,5 @@ +ProductCategory,ContosoAveragePrice,CompetitorAveragePrice +Dresses,120,100 +Shoes,100,105 +Accessories,60,55 +Sportswear,80,85 diff --git a/data/datasets/retail/order/delivery_performance_metrics.csv b/data/datasets/retail/order/delivery_performance_metrics.csv new file mode 100644 index 00000000..9678102b --- /dev/null +++ b/data/datasets/retail/order/delivery_performance_metrics.csv @@ -0,0 +1,8 @@ +Month,AverageDeliveryTime,OnTimeDeliveryRate,CustomerComplaints +March,3,98,15 +April,4,95,20 +May,5,92,30 +June,6,88,50 +July,7,85,70 +August,4,94,25 +September,3,97,10 diff --git a/data/datasets/retail/order/product_return_rates.csv b/data/datasets/retail/order/product_return_rates.csv new file mode 100644 index 00000000..6c5c4c3f --- /dev/null +++ b/data/datasets/retail/order/product_return_rates.csv @@ -0,0 +1,6 @@ +Category,ReturnRate +Dresses,15 +Shoes,10 +Accessories,8 +Outerwear,12 +Sportswear,9 diff --git a/data/datasets/retail/order/product_table.csv b/data/datasets/retail/order/product_table.csv new file mode 100644 index 00000000..79037292 --- /dev/null +++ b/data/datasets/retail/order/product_table.csv @@ -0,0 +1,6 @@ +ProductCategory,ReturnRate,ContosoAveragePrice,CompetitorAveragePrice +Dresses,15,120,100 +Shoes,10,100,105 +Accessories,8,60,55 +Outerwear,12,, +Sportswear,9,80,85 diff --git a/data/datasets/retail/order/purchase_history.csv b/data/datasets/retail/order/purchase_history.csv new file mode 100644 index 00000000..bf4cbdcc --- /dev/null +++ b/data/datasets/retail/order/purchase_history.csv @@ -0,0 +1,8 @@ +OrderID,Name,Date,ItemsPurchased,TotalAmount,DiscountApplied,DateDelivered,ReturnFlag +O5678,Emily Thompson,2023-03-15,"Summer Floral Dress, Sun Hat",150,10,2023-03-19,No +O5721,Emily Thompson,2023-04-10,"Leather Ankle Boots",120,15,2023-04-13,No +O5789,Emily Thompson,2023-05-05,Silk Scarf,80,0,2023-05-25,Yes +O5832,Emily Thompson,2023-06-18,Casual Sneakers,90,5,2023-06-21,No +O5890,Emily Thompson,2023-07-22,"Evening Gown, Clutch Bag",300,20,2023-08-05,No +O5935,Emily Thompson,2023-08-30,Denim Jacket,110,0,2023-09-03,Yes +O5970,Emily Thompson,2023-09-12,"Fitness Leggings, Sports Bra",130,25,2023-09-18,No diff --git a/data/datasets/retail/order/warehouse_incident_reports.csv b/data/datasets/retail/order/warehouse_incident_reports.csv new file mode 100644 index 00000000..e7440fcb --- /dev/null +++ b/data/datasets/retail/order/warehouse_incident_reports.csv @@ -0,0 +1,4 @@ +Date,IncidentDescription,AffectedOrders +2023-06-15,Inventory system outage,100 +2023-07-18,Logistics partner strike,250 +2023-08-25,Warehouse flooding due to heavy rain,150 diff --git a/data/datasets/rfp/compliance/rfp_compliance_guidelines.pdf b/data/datasets/rfp/compliance/rfp_compliance_guidelines.pdf new file mode 100644 index 00000000..53e89678 Binary files /dev/null and b/data/datasets/rfp/compliance/rfp_compliance_guidelines.pdf differ diff --git a/data/datasets/rfp/compliance/woodgrove_bank_rfp_response_contoso_ltd.pdf b/data/datasets/rfp/compliance/woodgrove_bank_rfp_response_contoso_ltd.pdf new file mode 100644 index 00000000..46ab9b4b Binary files /dev/null and b/data/datasets/rfp/compliance/woodgrove_bank_rfp_response_contoso_ltd.pdf differ diff --git a/data/datasets/rfp/risk/rfp_security_risk_guidelines.pdf b/data/datasets/rfp/risk/rfp_security_risk_guidelines.pdf new file mode 100644 index 00000000..e1534a45 Binary files /dev/null and b/data/datasets/rfp/risk/rfp_security_risk_guidelines.pdf differ diff --git a/data/datasets/rfp/risk/woodgrove_bank_rfp_response_contoso_ltd.pdf b/data/datasets/rfp/risk/woodgrove_bank_rfp_response_contoso_ltd.pdf new file mode 100644 index 00000000..46ab9b4b Binary files /dev/null and b/data/datasets/rfp/risk/woodgrove_bank_rfp_response_contoso_ltd.pdf differ diff --git a/data/datasets/rfp/summary/woodgrove_bank_rfp_response_contoso_ltd.pdf b/data/datasets/rfp/summary/woodgrove_bank_rfp_response_contoso_ltd.pdf new file mode 100644 index 00000000..46ab9b4b Binary files /dev/null and b/data/datasets/rfp/summary/woodgrove_bank_rfp_response_contoso_ltd.pdf differ diff --git a/data/datasets/social_media_sentiment_analysis.csv b/data/datasets/social_media_sentiment_analysis.csv new file mode 100644 index 00000000..78ed2ec2 --- /dev/null +++ b/data/datasets/social_media_sentiment_analysis.csv @@ -0,0 +1,8 @@ +Month,PositiveMentions,NegativeMentions,NeutralMentions +March,500,50,200 +April,480,60,220 +May,450,80,250 +June,400,120,300 +July,350,150,320 +August,480,70,230 +September,510,40,210 diff --git a/data/datasets/store_visit_history.csv b/data/datasets/store_visit_history.csv new file mode 100644 index 00000000..de5b300a --- /dev/null +++ b/data/datasets/store_visit_history.csv @@ -0,0 +1,4 @@ +Date,StoreLocation,Purpose,Outcome +2023-05-12,Downtown Outlet,Browsing,"Purchased a Silk Scarf (O5789)" +2023-07-20,Uptown Mall,Personal Styling,"Booked a session but didn't attend" +2023-08-05,Midtown Boutique,Browsing,"No purchase" diff --git a/data/datasets/subscription_benefits_utilization.csv b/data/datasets/subscription_benefits_utilization.csv new file mode 100644 index 00000000..c8f07966 --- /dev/null +++ b/data/datasets/subscription_benefits_utilization.csv @@ -0,0 +1,5 @@ +Benefit,UsageFrequency +Free Shipping,7 +Early Access to Collections,2 +Exclusive Discounts,1 +Personalized Styling Sessions,0 diff --git a/data/datasets/unauthorized_access_attempts.csv b/data/datasets/unauthorized_access_attempts.csv new file mode 100644 index 00000000..2b66bc4b --- /dev/null +++ b/data/datasets/unauthorized_access_attempts.csv @@ -0,0 +1,4 @@ +Date,IPAddress,Location,SuccessfulLogin +2023-06-20,192.168.1.1,Home Network,Yes +2023-07-22,203.0.113.45,Unknown,No +2023-08-15,198.51.100.23,Office Network,Yes diff --git a/data/datasets/warehouse_incident_reports.csv b/data/datasets/warehouse_incident_reports.csv new file mode 100644 index 00000000..e7440fcb --- /dev/null +++ b/data/datasets/warehouse_incident_reports.csv @@ -0,0 +1,4 @@ +Date,IncidentDescription,AffectedOrders +2023-06-15,Inventory system outage,100 +2023-07-18,Logistics partner strike,250 +2023-08-25,Warehouse flooding due to heavy rain,150 diff --git a/data/datasets/website_activity_log.csv b/data/datasets/website_activity_log.csv new file mode 100644 index 00000000..0f7f6c55 --- /dev/null +++ b/data/datasets/website_activity_log.csv @@ -0,0 +1,6 @@ +Date,PagesVisited,TimeSpent +2023-09-10,"Homepage, New Arrivals, Dresses",15 +2023-09-11,"Account Settings, Subscription Details",5 +2023-09-12,"FAQ, Return Policy",3 +2023-09-13,"Careers Page, Company Mission",2 +2023-09-14,"Sale Items, Accessories",10 diff --git a/deploy/macae-continer.bicep b/deploy/macae-continer.bicep deleted file mode 100644 index b4d8aa44..00000000 --- a/deploy/macae-continer.bicep +++ /dev/null @@ -1,344 +0,0 @@ -@description('Location for all resources.') -param location string = 'EastUS2' //Fixed for model availability, change back to resourceGroup().location - -@description('Location for OpenAI resources.') -param azureOpenAILocation string = 'EastUS' //Fixed for model availability - - - -@description('A prefix to add to the start of all resource names. Note: A "unique" suffix will also be added') -param prefix string = 'macae' - -@description('Tags to apply to all deployed resources') -param tags object = {} - -@description('The size of the resources to deploy, defaults to a mini size') -param resourceSize { - gpt4oCapacity: int - cosmosThroughput: int - containerAppSize: { - cpu: string - memory: string - minReplicas: int - maxReplicas: int - } -} = { - gpt4oCapacity: 50 - cosmosThroughput: 1000 - containerAppSize: { - cpu: '2.0' - memory: '4.0Gi' - minReplicas: 1 - maxReplicas: 1 - } -} - - -var appVersion = 'latest' -var resgistryName = 'biabcontainerreg' -var dockerRegistryUrl = 'https://${resgistryName}.azurecr.io' - -@description('URL for frontend docker image') -var backendDockerImageURL = '${resgistryName}.azurecr.io/macaebackend:${appVersion}' -var frontendDockerImageURL = '${resgistryName}.azurecr.io/macaefrontend:${appVersion}' - -var uniqueNameFormat = '${prefix}-{0}-${uniqueString(resourceGroup().id, prefix)}' -var aoaiApiVersion = '2024-08-01-preview' - - -resource logAnalytics 'Microsoft.OperationalInsights/workspaces@2023-09-01' = { - name: format(uniqueNameFormat, 'logs') - location: location - tags: tags - properties: { - retentionInDays: 30 - sku: { - name: 'PerGB2018' - } - } -} - -resource appInsights 'Microsoft.Insights/components@2020-02-02-preview' = { - name: format(uniqueNameFormat, 'appins') - location: location - kind: 'web' - properties: { - Application_Type: 'web' - WorkspaceResourceId: logAnalytics.id - } -} - -resource openai 'Microsoft.CognitiveServices/accounts@2023-10-01-preview' = { - name: format(uniqueNameFormat, 'openai') - location: azureOpenAILocation - tags: tags - kind: 'OpenAI' - sku: { - name: 'S0' - } - properties: { - customSubDomainName: format(uniqueNameFormat, 'openai') - } - resource gpt4o 'deployments' = { - name: 'gpt-4o' - sku: { - name: 'GlobalStandard' - capacity: resourceSize.gpt4oCapacity - } - properties: { - model: { - format: 'OpenAI' - name: 'gpt-4o' - version: '2024-08-06' - } - versionUpgradeOption: 'NoAutoUpgrade' - } - } -} - -resource aoaiUserRoleDefinition 'Microsoft.Authorization/roleDefinitions@2022-05-01-preview' existing = { - name: '5e0bd9bd-7b93-4f28-af87-19fc36ad61bd' //'Cognitive Services OpenAI User' -} - -resource acaAoaiRoleAssignment 'Microsoft.Authorization/roleAssignments@2022-04-01' = { - name: guid(containerApp.id, openai.id, aoaiUserRoleDefinition.id) - scope: openai - properties: { - principalId: containerApp.identity.principalId - roleDefinitionId: aoaiUserRoleDefinition.id - principalType: 'ServicePrincipal' - } -} - -resource cosmos 'Microsoft.DocumentDB/databaseAccounts@2024-05-15' = { - name: format(uniqueNameFormat, 'cosmos') - location: location - tags: tags - kind: 'GlobalDocumentDB' - properties: { - databaseAccountOfferType: 'Standard' - enableFreeTier: false - locations: [ - { - failoverPriority: 0 - locationName: location - } - ] - } - - resource contributorRoleDefinition 'sqlRoleDefinitions' existing = { - name: '00000000-0000-0000-0000-000000000002' - } - - resource autogenDb 'sqlDatabases' = { - name: 'autogen' - properties: { - resource: { - id: 'autogen' - createMode: 'Default' - } - options: { - throughput: resourceSize.cosmosThroughput - } - } - - resource memoryContainer 'containers' = { - name: 'memory' - properties: { - resource: { - id: 'memory' - partitionKey: { - kind: 'Hash' - version: 2 - paths: [ - '/session_id' - ] - } - } - } - } - } -} -// Define existing ACR resource - - -resource pullIdentity 'Microsoft.ManagedIdentity/userAssignedIdentities@2023-07-31-preview' = { - name: format(uniqueNameFormat, 'containerapp-pull') - location: location -} - - - -resource containerAppEnv 'Microsoft.App/managedEnvironments@2024-03-01' = { - name: format(uniqueNameFormat, 'containerapp') - location: location - tags: tags - properties: { - daprAIConnectionString: appInsights.properties.ConnectionString - appLogsConfiguration: { - destination: 'log-analytics' - logAnalyticsConfiguration: { - customerId: logAnalytics.properties.customerId - sharedKey: logAnalytics.listKeys().primarySharedKey - } - } - } - resource aspireDashboard 'dotNetComponents@2024-02-02-preview' = { - name: 'aspire-dashboard' - properties: { - componentType: 'AspireDashboard' - } - } -} - -resource acaCosomsRoleAssignment 'Microsoft.DocumentDB/databaseAccounts/sqlRoleAssignments@2024-05-15' = { - name: guid(containerApp.id, cosmos::contributorRoleDefinition.id) - parent: cosmos - properties: { - principalId: containerApp.identity.principalId - roleDefinitionId: cosmos::contributorRoleDefinition.id - scope: cosmos.id - } -} - -@description('') -resource containerApp 'Microsoft.App/containerApps@2024-03-01' = { - name: '${prefix}-backend' - location: location - tags: tags - identity: { - type: 'SystemAssigned, UserAssigned' - userAssignedIdentities: { - '${pullIdentity.id}': {} - } - } - properties: { - managedEnvironmentId: containerAppEnv.id - configuration: { - ingress: { - targetPort: 8000 - external: true - corsPolicy: { - allowedOrigins: [ - 'https://${format(uniqueNameFormat, 'frontend')}.azurewebsites.net' - 'http://${format(uniqueNameFormat, 'frontend')}.azurewebsites.net' - ] - } - } - activeRevisionsMode: 'Single' - } - template: { - scale: { - minReplicas: resourceSize.containerAppSize.minReplicas - maxReplicas: resourceSize.containerAppSize.maxReplicas - rules: [ - { - name: 'http-scaler' - http: { - metadata: { - concurrentRequests: '100' - } - } - } - ] - } - containers: [ - { - name: 'backend' - image: backendDockerImageURL - resources: { - cpu: json(resourceSize.containerAppSize.cpu) - memory: resourceSize.containerAppSize.memory - } - env: [ - { - name: 'COSMOSDB_ENDPOINT' - value: cosmos.properties.documentEndpoint - } - { - name: 'COSMOSDB_DATABASE' - value: cosmos::autogenDb.name - } - { - name: 'COSMOSDB_CONTAINER' - value: cosmos::autogenDb::memoryContainer.name - } - { - name: 'AZURE_OPENAI_ENDPOINT' - value: openai.properties.endpoint - } - { - name: 'AZURE_OPENAI_DEPLOYMENT_NAME' - value: openai::gpt4o.name - } - { - name: 'AZURE_OPENAI_API_VERSION' - value: aoaiApiVersion - } - { - name: 'FRONTEND_SITE_NAME' - value: 'https://${format(uniqueNameFormat, 'frontend')}.azurewebsites.net' - } - ] - } - ] - } - - } - - } -resource frontendAppServicePlan 'Microsoft.Web/serverfarms@2021-02-01' = { - name: format(uniqueNameFormat, 'frontend-plan') - location: location - tags: tags - sku: { - name: 'P1v2' - capacity: 1 - tier: 'PremiumV2' - } - properties: { - reserved: true - } - kind: 'linux' // Add this line to support Linux containers -} - -resource frontendAppService 'Microsoft.Web/sites@2021-02-01' = { - name: format(uniqueNameFormat, 'frontend') - location: location - tags: tags - kind: 'app,linux,container' // Add this line - properties: { - serverFarmId: frontendAppServicePlan.id - reserved: true - siteConfig: { - linuxFxVersion:'DOCKER|${frontendDockerImageURL}' - appSettings: [ - { - name: 'DOCKER_REGISTRY_SERVER_URL' - value: dockerRegistryUrl - } - { - name: 'WEBSITES_PORT' - value: '3000' - } - { - name: 'WEBSITES_CONTAINER_START_TIME_LIMIT' // Add startup time limit - value: '1800' // 30 minutes, adjust as needed - } - { - name: 'BACKEND_API_URL' - value: 'https://${containerApp.properties.configuration.ingress.fqdn}' - } - ] - } - } - dependsOn: [containerApp] - identity: { - type: 'SystemAssigned,UserAssigned' - userAssignedIdentities: { - '${pullIdentity.id}': {} - } - } -} - -output cosmosAssignCli string = 'az cosmosdb sql role assignment create --resource-group "${resourceGroup().name}" --account-name "${cosmos.name}" --role-definition-id "${cosmos::contributorRoleDefinition.id}" --scope "${cosmos.id}" --principal-id "fill-in"' diff --git a/docs/ACRBuildAndPushGuide.md b/docs/ACRBuildAndPushGuide.md new file mode 100644 index 00000000..b836ebc7 --- /dev/null +++ b/docs/ACRBuildAndPushGuide.md @@ -0,0 +1,118 @@ +# Azure Container Registry (ACR) â Build & Push Guide + +This guide provides step-by-step instructions to build and push Docker images for **WebApp** and **Backend** services into Azure Container Registry (ACR). + +## đ Prerequisites +Before starting, ensure you have: +- An active [Azure Subscription](https://portal.azure.com/) +- [Azure CLI](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli) installed and logged in +- [Docker Desktop](https://docs.docker.com/get-docker/) installed and running +- Access to your Azure Container Registry (ACR) +- To create an Azure Container Registry (ACR), you can refer to the following guides: + + - [Create Container Registry using Azure CLI](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-get-started-azure-cli) + + - [Create Container Registry using Azure Portal](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-get-started-portal?tabs=azure-cli) + + - [Create Container Registry using PowerShell](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-get-started-powershell) + + - [Create Container Registry using ARM Template](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-get-started-geo-replication-template) + + - [Create Container Registry using Bicep](https://learn.microsoft.com/en-us/azure/container-registry/container-registry-get-started-bicep?tabs=CLI) + +--- + +Login to ACR : +``` bash +az acr login --name $ACR_NAME +``` + +## đ Build and Push Images + +**Backend :** + + ```bash +az acr login --name
+
+
+Option A: GitHub Codespaces (Easiest)
+ +[](https://codespaces.new/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator) + +1. Click the badge above (may take several minutes to load) +2. Accept default values on the Codespaces creation page +3. Wait for the environment to initialize (includes all deployment tools) +4. Proceed to [Step 3: Configure Deployment Settings](#step-3-configure-deployment-settings) + +
+
+
+Option B: VS Code Dev Containers
+ +[](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator) + +**Prerequisites:** +- [Docker Desktop](https://www.docker.com/products/docker-desktop/) installed and running +- [VS Code](https://code.visualstudio.com/) with [Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers) + +**Steps:** +1. Start Docker Desktop +2. Click the badge above to open in Dev Containers +3. Wait for the container to build and start (includes all deployment tools) +4. Proceed to [Step 3: Configure Deployment Settings](#step-3-configure-deployment-settings) + +
+
+
+Option C: Visual Studio Code Web
+ +### VS Code Web + +[&message=Open&color=blue&logo=visualstudiocode&logoColor=white)](https://vscode.dev/azure/?vscode-azure-exp=foundry&agentPayload=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) + +1. Click the badge above (may take a few minutes to load) +2. Sign in with your Azure account when prompted +3. Select the subscription where you want to deploy the solution +4. Wait for the environment to initialize (includes all deployment tools) +5. When prompted in the VS Code Web terminal, choose one of the available options shown below: + +  + +6. **Authenticate with Azure** (VS Code Web requires device code authentication): + ```shell + az login --use-device-code + ``` + > **Note:** In VS Code Web environment, the regular `az login` command may fail. Use the `--use-device-code` flag to authenticate via device code flow. Follow the prompts in the terminal to complete authentication. + +7. Proceed to [Step 3: Configure Deployment Settings](#step-3-configure-deployment-settings) + +
+
+
+## Step 3: Configure Deployment Settings
+
+Review the configuration options below. You can customize any settings that meet your needs, or leave them as defaults to proceed with a standard deployment.
+
+### 3.1 Choose Deployment Type (Optional)
+
+| **Aspect** | **Development/Testing (Default)** | **Production** |
+|------------|-----------------------------------|----------------|
+| **Configuration File** | `main.parameters.json` (sandbox) | Copy `main.waf.parameters.json` to `main.parameters.json` |
+| **Security Controls** | Minimal (for rapid iteration) | Enhanced (production best practices) |
+| **Cost** | Lower costs | Cost optimized |
+| **Use Case** | POCs, development, testing | Production workloads |
+| **Framework** | Basic configuration | [Well-Architected Framework](https://learn.microsoft.com/en-us/azure/well-architected/) |
+| **Features** | Core functionality | Reliability, security, operational excellence |
+
+**To use production configuration:**
+
+**Prerequisite** â Enable the Microsoft.Compute/EncryptionAtHost feature for every subscription (and region, if required) where you plan to deploy VMs or VM scale sets with `encryptionAtHost: true`. Repeat the registration steps below for each target subscription (and for each region when applicable). This step is required for **WAF-aligned** (production) deployments.
+
+Steps to enable the feature:
+
+1. Set the target subscription:
+ Run: Option D: Local Environment
+ +**Required Tools:** +- [PowerShell 7.0+](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell) +- [Azure Developer CLI (azd) 1.18.0+](https://aka.ms/install-azd) +- [Python 3.9+](https://www.python.org/downloads/) +- [Docker Desktop](https://www.docker.com/products/docker-desktop/) +- [Git](https://git-scm.com/downloads) + +**Setup Steps:** +1. Install all required deployment tools listed above +2. Clone the repository: + + ```shell + azd init -t microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator/ + ``` + > **â ī¸ Warning:** The `azd init` command will download and initialize the project template. If you run this command in a directory that already contains project files, it may override your existing changes. Only run this command once when setting up the project for the first time. If you need to update an existing project, consider using `git pull` or manually downloading updates instead. + +3. Open the project folder in your terminal +4. Proceed to [Step 3: Configure Deployment Settings](#step-3-configure-deployment-settings) + +**PowerShell Users:** If you encounter script execution issues, run: +```powershell +Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass +``` + +az account set --subscription "<YourSubscriptionId>"
+2. Register the feature (one time per subscription):
+ Run: az feature register --name EncryptionAtHost --namespace Microsoft.Compute
+3. Wait until registration completes and shows "Registered":
+ Run: az feature show --name EncryptionAtHost --namespace Microsoft.Compute --query properties.state -o tsv
+4. Refresh the provider (if required):
+ Run: az provider register --namespace Microsoft.Compute
+5. Re-run the deployment after registration is complete.
+
+Note: Feature registration can take several minutes. Ensure the feature is registered before attempting deployments that require encryptionAtHost.
+
+Reference: Azure Host Encryption â https://learn.microsoft.com/azure/virtual-machines/disks-enable-host-based-encryption-portal?tabs=azure-cli
+
+Copy the contents from the production configuration file to your main parameters file:
+
+1. Navigate to the `infra` folder in your project
+2. Open `main.waf.parameters.json` in a text editor (like Notepad, VS Code, etc.)
+3. Select all content (Ctrl+A) and copy it (Ctrl+C)
+4. Open `main.parameters.json` in the same text editor
+5. Select all existing content (Ctrl+A) and paste the copied content (Ctrl+V)
+6. Save the file (Ctrl+S)
+
+### 3.2 Set VM Credentials (Optional - Production Deployment Only)
+
+> **Note:** This section only applies if you selected **Production** deployment type in section 3.1. VMs are not deployed in the default Development/Testing configuration.
+
+By default, random GUIDs are generated for VM credentials. To set custom credentials:
+
+```shell
+azd env set AZURE_ENV_VM_ADMIN_USERNAME
+
+
+Configurable Parameters
+ +You can customize various deployment settings before running `azd up`, including Azure regions, AI model configurations (deployment type, version, capacity), container registry settings, and resource names. + +đ **Complete Guide:** See [Parameter Customization Guide](./CustomizingAzdParameters.md) for the full list of available parameters and their usage. + +
+
+
+[Optional] Quota Recommendations
+ +By default, the **GPT model capacity** in deployment is set to **150k tokens**. + +To adjust quota settings, follow these [steps](./AzureGPTQuotaSettings.md). + +**â ī¸ Warning:** Insufficient quota can cause deployment errors. Please ensure you have the recommended capacity or request additional capacity before deploying this solution. + +
+
+
+## Step 4: Deploy the Solution
+
+đĄ **Before You Start:** If you encounter any issues during deployment, check our [Troubleshooting Guide](./TroubleShootingSteps.md) for common solutions.
+
+â ī¸ **Critical: Redeployment Warning** - If you have previously run `azd up` in this folder (i.e., a `.azure` folder exists), you must [create a fresh environment](#creating-a-new-environment) to avoid conflicts and deployment failures.
+
+### 4.1 Authenticate with Azure
+
+```shell
+azd auth login
+```
+
+> **Note for VS Code Web Users:** If you're using VS Code Web and have already authenticated using `az login --use-device-code` in Option C, you may skip this step or proceed with `azd auth login` if prompted.
+
+**For specific tenants:**
+```shell
+azd auth login --tenant-id Reuse Existing Resources
+ +To optimize costs and integrate with your existing Azure infrastructure, you can configure the solution to reuse compatible resources already deployed in your subscription. + +**Supported Resources for Reuse:** + +- **Log Analytics Workspace:** Integrate with your existing monitoring infrastructure by reusing an established Log Analytics workspace for centralized logging and monitoring. [Configuration Guide](./re-use-log-analytics.md) + +- **Azure AI Foundry Project:** Leverage your existing AI Foundry project and deployed models to avoid duplication and reduce provisioning time. [Configuration Guide](./re-use-foundry-project.md) + +**Key Benefits:** +- **Cost Optimization:** Eliminate duplicate resource charges +- **Operational Consistency:** Maintain unified monitoring and AI infrastructure +- **Faster Deployment:** Skip resource creation for existing compatible services +- **Simplified Management:** Reduce the number of resources to manage and monitor + +**Important Considerations:** +- Ensure existing resources meet the solution's requirements and are in compatible regions +- Review access permissions and configurations before reusing resources +- Consider the impact on existing workloads when sharing resources + +
+
+
+### Creating a New Environment
+
+If you need to deploy to a different region, test different configurations, or create additional environments:
+
+Recover from Failed Deployment
+ +**If your deployment failed or encountered errors:** + +1. **Try a different region:** Create a new environment and select a different Azure region during deployment +2. **Clean up and retry:** Use `azd down` to remove failed resources, then `azd up` to redeploy +3. **Check troubleshooting:** Review [Troubleshooting Guide](./TroubleShootingSteps.md) for specific error solutions +4. **Fresh start:** Create a completely new environment with a different name + +**Example Recovery Workflow:** +```shell +# Remove failed deployment (optional) +azd down + +# Create new environment (3-16 chars, alphanumeric only) +azd env new macaeretry + +# Deploy with different settings/region +azd up +``` + +
+
+
+# Select the new environment
+azd env select
+
+# Deploy to the new environment
+azd up
+```
+
+**Example:**
+```shell
+# Create a new environment for production (valid: 3-16 chars)
+azd env new macaeprod
+
+# Switch to the new environment
+azd env select macaeprod
+
+# Deploy with fresh settings
+azd up
+```
+
+> **Environment Name Requirements:**
+> - **Length:** 3-16 characters
+> - **Characters:** Alphanumeric only (letters and numbers)
+> - **Valid examples:** `macae`, `test123`, `myappdev`, `prod2025`
+> - **Invalid examples:** `co` (too short), `my-very-long-environment-name` (too long), `test_env` (underscore not allowed)
+
+
+
+Create a New Environment
+ +**Create Environment Explicitly:** +```shell +# Create a new named environment (3-16 characters, alphanumeric only) +azd env new
+
+```
+
+**View Current Environment:**
+```shell
+azd env get-values
+```
+
+
+
+### Best Practices for Multiple Environments
+
+- **Use descriptive names:** `macaedev`, `macaeprod`, `macaetest` (remember: 3-16 chars, alphanumeric only)
+- **Different regions:** Deploy to multiple regions for testing quota availability
+- **Separate configurations:** Each environment can have different parameter settings
+- **Clean up unused environments:** Use `azd down` to remove environments you no longer need
+
+## Next Steps
+
+Now that your deployment is complete and tested, explore these resources to enhance your experience:
+
+đ **Learn More:**
+- [Local Development Setup](./LocalDevelopmentSetup.md) - Set up your local development environment
+- [Sample Questions](./SampleQuestions.md) - Explore sample questions and workflows
+- [MCP Server Documentation](./mcp_server.md) - Learn about Model Context Protocol server integration
+- [Customizing Parameters](./CustomizingAzdParameters.md) - Advanced configuration options
+- [Azure Account Setup](./AzureAccountSetUp.md) - Detailed Azure subscription configuration
+
+## Need Help?
+
+- đ **Issues:** Check [Troubleshooting Guide](./TroubleShootingSteps.md)
+- đŦ **Support:** Review [Support Guidelines](../SUPPORT.md)
+- đ§ **Development:** See [Contributing Guide](../CONTRIBUTING.md)
+
+## Advanced: Deploy Local Changes
+
+If you've made local modifications to the code and want to deploy them to Azure, follow these steps to swap the configuration files:
+
+> **Note:** To set up and run the application locally for development, see the [Local Development Setup Guide](./LocalDevelopmentSetup.md).
+
+### Step 1: Rename Azure Configuration Files
+
+**In the root directory:**
+1. Rename `azure.yaml` to `azure_custom2.yaml`
+2. Rename `azure_custom.yaml` to `azure.yaml`
+
+### Step 2: Rename Infrastructure Files
+
+**In the `infra` directory:**
+1. Rename `main.bicep` to `main_custom2.bicep`
+2. Rename `main_custom.bicep` to `main.bicep`
+
+### Step 3: Deploy Changes
+
+Run the deployment command:
+```shell
+azd up
+```
+
+> **Note:** These custom files are configured to deploy your local code changes instead of pulling from the GitHub repository.
\ No newline at end of file
diff --git a/docs/LocalDevelopmentSetup.md b/docs/LocalDevelopmentSetup.md
new file mode 100644
index 00000000..f3c050b7
--- /dev/null
+++ b/docs/LocalDevelopmentSetup.md
@@ -0,0 +1,608 @@
+# Local Development Setup Guide
+
+This guide provides comprehensive instructions for setting up the Multi Agent Custom Automation Engine Solution Accelerator for local development across Windows and Linux platforms.
+
+## Important Setup Notes
+
+### Multi-Service Architecture
+
+This application consists of **three separate services** that run independently:
+
+1. **Backend** - Backend APIs related to orchestration and Teams
+2. **Frontend** - React-based user interface
+3. **MCP Server** - MCP server to tools call
+
+> **â ī¸ Critical: Each service must run in its own terminal/console window**
+>
+> - **Do NOT close terminals** while services are running
+> - Open **3 separate terminal windows** for local development
+> - Each service will occupy its terminal and show live logs
+>
+> **Terminal Organization:**
+> - **Terminal 1**: Backend - HTTP server on port 8000
+> - **Terminal 2**: Frontend - Development server on port 3000
+> - **Terminal 3**: MCP server - HTTP streamable server on port 9000
+
+### Path Conventions
+
+**All paths in this guide are relative to the repository root directory:**
+
+```bash
+Multi-Agent-Custom-Automation-Engine-Solution-Accelerator/ â Repository root (start here)
+âââ src/
+â âââ backend/ â cd src/backend
+â â âââ .venv/ â Virtual environment
+â â âââ .env â Backend config file
+â â âââ app.py â Backend Entry Point
+â âââ frontend/ â cd src/frontend
+â â âââ node_modules/ â npm dependencies
+â â âââ .venv/ â Virtual environment
+â â âââ frontend_server.py â Frontend entry point
+â âââ mcp_server/ â cd src/mcp_server
+â â âââ .venv/ â Virtual environment
+â â âââ mcp_server.py â MCP server Entry Point
+âââ docs/ â Documentation (you are here)
+```
+
+**Before starting any step, ensure you are in the repository root directory:**
+
+```bash
+# Verify you're in the correct location
+pwd # Linux/macOS - should show: .../Multi-Agent-Custom-Automation-Engine-Solution-Accelerator
+Get-Location # Windows PowerShell - should show: ...\Multi-Agent-Custom-Automation-Engine-Solution-Accelerator
+
+# If not, navigate to repository root
+cd path/to/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator
+```
+
+### Configuration Files
+
+This project uses Backend `.env` file in Backend directory with different configuration requirements:
+
+- **Backend**: `src/backend/.env`
+
+
+
+## Step 1: Prerequisites - Install Required Tools
+
+### Windows Development
+
+#### Option 1: Native Windows (PowerShell)
+
+```powershell
+# Install Python 3.12+ and Git
+winget install Python.Python.3.12
+winget install Git.Git
+
+# Install Node.js for frontend
+winget install OpenJS.NodeJS.LTS
+
+# Install uv package manager
+py -3.12 -m pip install uv
+```
+
+#### Option 2: Windows with WSL2 (Recommended)
+
+```bash
+# Install WSL2 first (run in PowerShell as Administrator):
+# wsl --install -d Ubuntu
+
+# Then in WSL2 Ubuntu terminal:
+sudo apt update && sudo apt install python3.12 python3.12-venv git curl nodejs npm -y
+
+# Install uv
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source ~/.bashrc
+```
+
+### Linux Development
+
+#### Ubuntu/Debian
+
+```bash
+# Install prerequisites
+sudo apt update && sudo apt install python3.12 python3.12-venv git curl nodejs npm -y
+
+# Install uv package manager
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source ~/.bashrc
+```
+
+#### RHEL/CentOS/Fedora
+
+```bash
+# Install prerequisites
+sudo dnf install python3.12 python3.12-devel git curl gcc nodejs npm -y
+
+# Install uv
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source ~/.bashrc
+```
+
+### Clone the Repository
+
+```bash
+git clone https://github.com/microsoft/Multi-Agent-Custom-Automation-Engine-Solution-Accelerator.git
+cd Multi-Agent-Custom-Automation-Engine-Solution-Accelerator
+```
+
+## Step 2: Development Tools Setup
+
+### Visual Studio Code (Recommended)
+
+#### Required Extensions
+
+Create `.vscode/extensions.json` in the workspace root and copy the following JSON:
+
+```json
+{
+ "recommendations": [
+ "ms-python.python",
+ "ms-python.pylint",
+ "ms-python.black-formatter",
+ "ms-python.isort",
+ "ms-vscode-remote.remote-wsl",
+ "ms-vscode-remote.remote-containers",
+ "redhat.vscode-yaml",
+ "ms-vscode.azure-account",
+ "ms-python.mypy-type-checker"
+ ]
+}
+```
+
+VS Code will prompt you to install these recommended extensions when you open the workspace.
+
+#### Settings Configuration
+
+Create `.vscode/settings.json` and copy the following JSON:
+
+```json
+{
+ "python.defaultInterpreterPath": "${workspaceFolder}/src/backend/.venv/Scripts/python.exe",
+ "python.terminal.activateEnvironment": true,
+ "python.linting.enabled": true,
+ "python.linting.pylintEnabled": false,
+ "python.linting.flake8Enabled": true,
+ "python.formatting.provider": "black",
+ "python.debugging.logLevel": "Debug",
+ "debug.terminal.clearBeforeReusing": true,
+ "debug.onTaskErrors": "showErrors",
+ "debug.showBreakpointsInOverviewRuler": true,
+ "debug.inlineValues": "on",
+ "files.exclude": {
+ "**/__pycache__": true,
+ "**/*.pyc": true
+ },
+ "python.analysis.extraPaths": [
+ "${workspaceFolder}/src/backend",
+ "${workspaceFolder}/src/mcp_server"
+ ],
+ "folders": [
+ {
+ "name": "Backend",
+ "path": "./src/backend"
+ },
+ {
+ "name": "MCP Server",
+ "path": "./src/mcp_server"
+ },
+ {
+ "name": "Frontend",
+ "path": "./src/frontend"
+ }
+ ]
+}
+```
+
+## Step 3: Azure Authentication Setup
+
+Before configuring services, authenticate with Azure:
+
+```bash
+# Login to Azure CLI
+az login
+
+# Set your subscription
+az account set --subscription "your-subscription-id"
+
+# Verify authentication
+az account show
+```
+
+
+### Required Azure RBAC Permissions
+
+To run the application locally, your Azure account needs the following role assignments on the deployed resources:
+
+The **main.bicep** deployment includes the assignment of the appropriate roles to AOAI, Storage account, Search service and Cosmos services. If you want to use resource group which is not deployed by you for local debuggingâyou will need to add your own credentials to access the Cosmos Storage account, Search service and AOAI services. You can add these permissions using the following commands:
+
+#### Get Your Microsoft Entra ID User Object ID (Principal ID)
+
+Your Azure AD User Object ID (also called Principal ID) is required for the role assignments below. Choose either method to obtain it:
+
+**Method 1: Using Azure CLI (Recommended)**
+```bash
+az ad signed-in-user show --query id -o tsv
+```
+
+**Method 2: Using Azure Portal**
+1. Go to [Azure Portal](https://portal.azure.com)
+2. Open **Microsoft Entra ID** (or search "Entra")
+3. In the left menu, select **Users**
+4. Select your account
+5. Under **Identity**, copy the **Object ID**
+
+> **Note:** The `Switch Between Environments
+ +**List Available Environments:** +```shell +azd env list +``` + +**Switch to Different Environment:** +```shell +azd env select+ > _Observe: An analysis of Emily Thompsonâs satisfaction with Contoso has been generated. It provides a proposed plan consisting of four or more steps._ + +- Task: Click **"Approve Task Plan"** Button + > _Note: Average response time is 01 minute 15 seconds._
+ > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._
+ > _Review the output._ + +### **Product Marketing Scenario** +If you select the Marketing team, follow the prompts below. + +>**Agents Used:** Product, Marketing , Proxy + +The Product Marketing Scenario allows users to explore and retrieve information related to Marketing and specific product. Key tasks include: + +_Sample operation:_ +- Task: Switch to **"Product Marketing Team"** from the top left section and click **"Continue"** button. +- Task: From the Quick Tasks, select **"Draft a press release"** and submit it. + > _Note: Average response time is 15â20 seconds._
+ > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 4 or more Steps_ +- Task: Click on **"Approve Task Plan"** Button + > _Note: Average response time is around 01 minute._
+ > _Observe: It goes into "Thinking Process" and observe a spinner "Processing your plan and coordinating with AI Agents"._
+ > _Review the output._ + +### **HR Onboarding Scenario** +If you select the HR team, follow the prompts below. + +>**Agents Used:** HR Helper, Technical support , Proxy + +The HR Onboarding Scenario allows users to explore and retrieve information related to OnBoarding the Employee. Key tasks include: + +_Sample operation:_ + +- Task: Switch to the **"Human Resources Team"** from the top left section and click **"Continue"** +- Task: From the Quick Tasks, select **"Onboard New Employee"** and submit it. + + > _Note: Average response time is 15â20 seconds._
+ > _Observe: If it asks for additional clarification (Human in the loop) Please provide this information irrespective of what specific information is asked. This will prevent agent for asking for multiple clarifications_ + + ```sh + department: hr, role: manager, start date: 11/23/2025, orientation date: 11/25/2025, location: onsite, email: js@contoso.com, mentor: Jim Shorts, benefits package: standard, ID Card: yes, salary: 70000, Laptop : Dell 14 Plus + ``` + > _Observe: It will trigger "Generating Plan Action" and "Proposed Plan" with 4 or more Steps_ + + +- Task: Click on **"Approve Task Plan"** Button. + > _Note: Average response time is around 01 minute 15 seconds._
+ > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"_
+ > _Review the output._ + +### **RFP Analysis Scenario** +If you select the RFP team, follow the prompts below. + +>**Agents Used:** RFP Summary, RFP Risk, RFP Compliance + +The RFP Analysis Scenario allows users to explore and analyze Request for Proposal (RFP) and contract documents. Key tasks include: + +_Sample operation:_ + +- Task: Switch to the **"RFP Team"** from the top left section and click **"Continue"** button. +- Task: From the Quick Tasks, select **"RFP Document Summary"** and submit it. + + > _Note: Average response time is 10â15 minutes._
+ > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 5 or more Steps_ + + +- Task: Click on **"Approve Task Plan"** Button. + > _Note: Average response time is around 01 minute._
+ > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._
+ > _Review the output._ + +### **Contract Compliance Review Scenario** +If you select the Contract Compliance team, follow the prompts below. + +>**Agents Used:** Contract Summary, Contract Risk, Contract Compliance + +The Contract Compliance Review Scenario allows users to explore and analyze NDA and contract documents for compliance and risk assessment. Key tasks include: + +_Sample operation:_ + +- Task: Switch to the **"Contract Compliance Review Team"** from the top left section and click **"Continue"** button. +- Task: From the Quick Tasks, select **"NDA Contract Review"** and submit it. + + > _Note: Average response time is 10â15 minutes._
+ > _Observe: It will trigger the "Generating Plan Action" and give the Proposed Plan with 4 or more Steps_ + + +- Task: Click on **"Approve Task Plan"** Button. + > _Note: Average response time is around 01 minute._
+ > _Observe: It goes into "Thinking Process", "Processing your plan" and "coordinating with AI Agents"._
+ > _Review the output._ + + +This structured approach ensures that users receive automated, AI-coordinated task execution and intelligent responses from specialized agents. diff --git a/docs/SetUpGroundingWithBingSearch.md b/docs/SetUpGroundingWithBingSearch.md new file mode 100644 index 00000000..8ccdd230 --- /dev/null +++ b/docs/SetUpGroundingWithBingSearch.md @@ -0,0 +1,99 @@ + +# đ Grounding with Bing Search â Quick Setup + +This guide walks you through setting up Grounding with Bing Search and connecting it to your Azure AI Foundry project. This tool enables your AI agents to retrieve real-time public web data, enhancing responses with up-to-date information. + +--- + +## â Prerequisites + +- An active **Azure subscription** +- **Azure CLI** installed and logged in (`az login`) +- A **resource group** created +- Register the Bing provider (one-time setup): + + ```bash + az provider register --namespace Microsoft.Bing + +â ī¸ **Important:** +Bing Search Grounding only supports **API key authentication**. +Ensure your **Azure AI Foundry account has Local Authentication enabled**. +If local auth is disabled, you will not be able to connect Bing Search. + +--- + +## đ Step 1: Create a Bing Search Grounding Resource + +### Option A â Azure Portal + +1. In the [Azure Portal](https://portal.azure.com), search for **Bing Search (Grounding)**. +2. Click **Create**. +3. Select your **Subscription** and **Resource Group**. +4. Enter a **Resource Name** and choose a **Pricing Tier (SKU)**. +5. At the bottom of the form, tick the required checkbox: + â *âI confirm I have read and understood the notice above.â* + (You cannot proceed without this.) +6. Click **Review + Create** â **Create**. + +--- + +### Option B â Azure CLI + +Set your variables (replace with your own values): + +```bash +RESOURCE_GROUP="
without additional quota** | Insufficient quota for requested operation | [View Solution](#subscription--access-issues) | +| **ResourceGroupBeingDeleted** | Resource group deletion in progress | [View Solution](#resource-group--deployment-management) | +| **FlagMustBeSetForRestore** | Soft-deleted resource requires restore flag or purge | [View Solution](#miscellaneous) | +| **ParentResourceNotFound** | Parent resource does not exist or cannot be found | [View Solution](#resource-identification--references) | +| **AccountProvisioningStateInvalid** | Resource used before provisioning completed | [View Solution](#resource-state--provisioning) | +| **InternalSubscriptionIsOverQuotaForSku** | Subscription quota exceeded for the requested SKU | [View Solution](#quota--capacity-limitations) | +| **InvalidResourceGroup** | Invalid resource group configuration | [View Solution](#resource-group--deployment-management) | +| **RequestDisallowedByPolicy** | Azure Policy blocking the requested operation | [View Solution](#subscription--access-issues) | + +## đ Table of Contents + +- [Subscription & Access Issues](#subscription--access-issues) +- [Quota & Capacity Limitations](#quota--capacity-limitations) +- [Regional & Location Issues](#regional--location-issues) +- [Resource Naming & Validation](#resource-naming--validation) +- [Resource Identification & References](#resource-identification--references) +- [Network & Infrastructure Configuration](#network--infrastructure-configuration) +- [Configuration & Property Errors](#configuration--property-errors) +- [Resource State & Provisioning](#resource-state--provisioning) +- [Miscellaneous](#miscellaneous) + +## Subscription & Access Issues + +| Issue/Error Code | Description | Steps to Resolve | +|-----------|-------------|------------------| +| **ReadOnlyDisabledSubscription** | Subscription is disabled or in read-only state |
- Check if you have an active subscription before starting the deployment
- Depending on the type of the Azure Subscription, the expiration date might have been reached
- You have to activate the Azure Subscription before creating any Azure resource
- Refer to [Reactivate a disabled Azure subscription](https://learn.microsoft.com/en-us/azure/cost-management-billing/manage/subscription-disabled) documentation
AllowBringYourOwnPublicIpAddress** | Required feature not registered in subscription | **Enable `AllowBringYourOwnPublicIpAddress` Feature**
Before deploying the resources, you may need to enable the **Bring Your Own Public IP Address** feature in Azure. This is required only once per subscription.
**Steps:**
- Run the following command to register the feature:
`az feature register --namespace Microsoft.Network --name AllowBringYourOwnPublicIpAddress` - Wait for the registration to complete. Check the status using:
`az feature show --namespace Microsoft.Network --name AllowBringYourOwnPublicIpAddress --query properties.state` - The output should show: "Registered"
- Once the feature is registered, refresh the provider:
`az provider register --namespace Microsoft.Network`
- Check your quota usage using:
`az vm list-usage --location "" -o table` - To request more quota refer to [VM Quota Request](https://techcommunity.microsoft.com/blog/startupsatmicrosoftblog/how-to-increase-quota-for-specific-types-of-azure-virtual-machines/3792394)
- **Check tenant match:** Ensure your deployment identity (user/SP) and the target resource group are in the same tenant:
`az account show`
`az group show --name` - **Verify pipeline/service principal:** If using CI/CD, confirm the service principal belongs to the same tenant and has permissions on the resource group
- **Avoid cross-tenant references:** Make sure your Bicep doesn't reference subscriptions, resource groups, or resources in another tenant
- **Test minimal deployment:** Deploy a simple resource to the same resource group to confirm identity and tenant are correct
- **Guest/external accounts:** Avoid using guest users from other tenants; use native accounts or SPs in the tenant
- This typically indicates that an Azure Policy is preventing the requested action due to policy restrictions in your subscription
- For more details and guidance on resolving this issue, refer to: [RequestDisallowedByPolicy](https://learn.microsoft.com/en-us/troubleshoot/azure/azure-kubernetes/create-upgrade-delete/error-code-requestdisallowedbypolicy)
**Example error message:**
`SpecialFeatureOrQuotaIdRequired: The current subscription does not have access to this model 'Format:OpenAI,Name:o3,Version:2025-04-16'.`
**Resolution:**
To gain access, submit a request using the official form:
đ [Azure OpenAI Model Access Request](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUQ1VGQUEzRlBIMVU2UFlHSFpSNkpOR0paRSQlQCN0PWcu)
You'll need to use this form if you require access to the following restricted models:
- gpt-5
- o3
- o3-pro
- deep research
- reasoning summary
- gpt-image-1
- This error occurs when the resource provider is not registered in your subscription
- To register it, refer to [Register Resource Provider](https://learn.microsoft.com/en-us/azure/azure-resource-manager/troubleshooting/error-register-resource-provider?tabs=azure-cli) documentation
ManagedEnvironmentProvisioningError** | Subscription quota exceeded for the requested SKU | Quotas are applied per resource group, subscriptions, accounts, and other scopes. For example, your subscription might be configured to limit the number of vCPUs for a region. If you attempt to deploy a virtual machine with more vCPUs than the permitted amount, you receive an error that the quota was exceeded.
For PowerShell, use the `Get-AzVMUsage` cmdlet to find virtual machine quotas:
`Get-AzVMUsage -Location "West US"`
Based on available quota you can deploy application otherwise, you can request for more quota | +| **InsufficientQuota** | Not enough quota available in subscription |
- Check if you have sufficient quota available in your subscription before deployment
- To verify, refer to the [quota_check](../docs/quota_check.md) file for details
**Common Causes:**
- Deploying to regions with low quota limits (e.g., Sweden Central allows only 1 environment)
- Multiple deployments without cleaning up previous environments
- Exceeding the standard limit of 15 environments in most major regions
**Resolution:**
- **Delete unused environments** in the target region, OR
- **Deploy to a different region** with available capacity, OR
- **Request quota increase** via [Azure Support](https://go.microsoft.com/fwlink/?linkid=2208872)
**Reference:**
- [Azure Container Apps quotas](https://learn.microsoft.com/en-us/azure/container-apps/quotas)
- [Azure subscription and service limits](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/azure-subscription-service-limits)
- When the resource SKU you've selected, such as VM size, isn't available for a location or zone
- If you're deploying an Azure Spot VM or Spot scale set instance, and there isn't any capacity for Azure Spot in this location. For more information, see Spot error messages
**Common Causes:**
- High demand in the selected region (e.g., East US, West Europe)
- Specific SKUs experiencing capacity constraints (Free, Shared, or certain Premium tiers)
- Multiple rapid deployments in the same region
**Resolution:**
- **Wait and Retry** (15-30 minutes): `azd up`
- **Deploy to a New Resource Group** (Recommended for urgent cases):
```
azd down --force --purge
azd up
``` - **Try a Different Region:**
Update region in `main.bicep` or `azure.yaml` to a less congested region (e.g., `westus2`, `centralus`, `northeurope`) - **Use a Different SKU/Tier:**
If using Free/Shared tier, upgrade to Basic or Standard
Check SKU availability: `az appservice list-locations --sku`
**Reference:** [Azure App Service Plans](https://learn.microsoft.com/en-us/azure/app-service/overview-hosting-plans) | + +-------------------------------- + +## Resource Group & Deployment Management + +| Issue/Error Code | Description | Steps to Resolve | +|-----------------|-------------|------------------| +| **ResourceGroupNotFound** | Specified resource group does not exist | **Option 1:**
- Go to [Azure Portal](https://portal.azure.com/#home)
- Click on **"Resource groups"** option
 - Search for the resource group in the search bar. If it exists, you can proceed
**Option 2:**
- This error can occur if you deploy using the same .env file from a previous deployment
- Create a new environment before redeploying:
`azd env new`
- Go to [Azure Portal](https://portal.azure.com/#home)
- Go to resource group option and search for targeted resource group
- If the resource group is being deleted, you cannot use it. Create a new one or use a different resource group
- This occurs when a deployment is already in progress and another deployment is triggered in the same resource group
- Cancel the ongoing deployment before starting a new one
- Do not initiate a new deployment until the previous one is completed
- **Check deployment history:**
Go to Azure Portal â Resource Group â Deployments
Review the detailed error message - **Identify the root cause:**
Dependent resource failed to deploy
Validation error occurred
Manual cancellation was triggered - **Validate template:**
`az deployment group validate --resource-group--template-file main.bicep` - **Check resource limits/quotas**
- **Fix the failed dependency**
- **Retry deployment:**
`az deployment group create --resource-group--template-file main.bicep`
đĄ **Note:** DeploymentCanceled is a wrapper error â check inner errors in deployment logs | +| **DeploymentCanceled(user.canceled)** | User manually canceled the deployment |
- Deployment was manually canceled by the user (Portal, CLI, or pipeline)
- Check deployment history and logs to confirm who/when it was canceled
- If accidental, retry the deployment
- For pipelines, ensure no automation or timeout is triggering cancellation
- Use deployment locks or retry logic to prevent accidental cancellations
- This occurs when the user deletes a previous deployment along with the resource group, then redeploys the same RG with the same environment name but in a different location
- Do not change the location when redeploying a deleted RG, OR
- Use new names for the RG and environment during redeployment
- Some resources may be stuck deleting or have dependencies; check RG resources and status
- Ensure no resource locks or Azure Policies are blocking deletion
- Retry deletion via CLI/PowerShell:
`az group delete --name--yes --no-wait` - Check Activity Log to identify failing resources
- Escalate to Azure Support if deletion is stuck
**Resolution:**
- **Verify resource availability by region:**
`az provider show --namespace--query "resourceTypes[?resourceType==' '].locations" -o table` - **Check Azure Products by Region:**
[Azure Products by Region](https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region/) - **Supported regions for this deployment:**
- `australiaeast`
- `centralus`
- `eastasia`
- `eastus2`
- `japaneast`
- `northeurope`
- `southeastasia`
- `uksouth`
- **Redeploy:**
`azd up`
**Resolution:**
- **Option 1: Delete and Redeploy:**
`azd down --force --purge`
after purge redeploy app `azd up` - **Option 2: Create new environment with different region:**
`azd env new`
`azd env set AZURE_LOCATION`
`azd up` - **Option 3: Keep existing deployment:**
Revert configuration files to use the original region
â ī¸ **Important:** Backup critical data before deleting resources.
**Reference:** [Move Azure resources across regions](https://learn.microsoft.com/en-us/azure/resource-mover/overview) | +| **ServiceUnavailable/ResourceNotFound** | Service unavailable or restricted in selected region |
- Regions are restricted to guarantee compatibility with paired regions and replica locations for data redundancy and failover scenarios based on articles [Azure regions list](https://learn.microsoft.com/en-us/azure/reliability/regions-list) and [Azure Database for MySQL Flexible Server - Azure Regions](https://learn.microsoft.com/azure/mysql/flexible-server/overview#azure-regions)
- You can request more quota, refer [Quota Request](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/create-support-request-quota-increase) Documentation
ProvisioningDisabled** | Resource provisioning restricted or disabled in region |
- This error occurs when provisioning of a resource is restricted in the selected region. It usually happens because the service is not available in that region or provisioning has been temporarily disabled
- Regions are restricted to guarantee compatibility with paired regions and replica locations for data redundancy and failover scenarios based on articles [Azure regions list](https://learn.microsoft.com/en-us/azure/reliability/regions-list) and [Azure Database for MySQL Flexible Server - Azure Regions](https://learn.microsoft.com/azure/mysql/flexible-server/overview#azure-regions)
- If you need to use the same region, you can request a quota or provisioning exception. Refer [Quota Request](https://docs.microsoft.com/en-us/azure/sql-database/quota-increase-request) for more details
- This issue happens when you try to create a **Storage Account** with a redundancy configuration (e.g., `Standard_GRS`) that is **not supported in the selected Azure region**
- Example: Creating a storage account with **GRS** in **italynorth** will fail with error:
`az storage account create -n mystorageacct123 -g myResourceGroup -l italynorth --sku Standard_GRS --kind StorageV2` - To check supported SKUs for your region:
`az storage account list-skus -l italynorth -o table` - Use a supported redundancy option (e.g., Standard_LRS) in the same region or deploy the Storage Account in a region that supports your chosen redundancy
- For more details, refer to [Azure Storage redundancy documentation](https://learn.microsoft.com/en-us/azure/storage/common/storage-redundancy?utm_source=chatgpt.com)
- Ensure the resource name is within the allowed length and naming rules defined for that specific resource type, you can refer [Resource Naming Convention](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/resource-name-rules) document
- Must start and end with an alphanumeric character (letter or number)
- Allowed characters: `aâz`, `0â9`, `- (hyphen)`
- Cannot start or end with a hyphen -
- No spaces, underscores (_), periods (.), or special characters
- Must be unique within the Azure region & subscription
- Length: 3â33 characters (for AML workspaces)
- **Check name length** - Ensure the Key Vault name is between 3 and 24 characters
- **Validate allowed characters** - The name can only contain letters (aâz, AâZ) and numbers (0â9). Hyphens are allowed, but not at the beginning or end, and not consecutive (--)
- **Ensure proper start and end** - The name must start with a letter. The name must end with a letter or digit (not a hyphen)
- **Test with a new name** - Example of a valid vault name: â `cartersaikeyvault1`, â `securevaultdemo`, â `kv-project123`
- Verify resource names are globally unique
- If you already created an account/resource with same name in another subscription or resource group, check and delete it before reusing the name
- By default in this template we are using unique prefix with every resource/account name to avoid this kind for errors
ResourceNotFound/
DeploymentOutputEvaluationFailed/
CanNotRestoreANonExistingResource/
The language expression property array index is out of bounds** | Invalid or non-existent resource ID reference |
- Before using any resource ID, ensure it follows the correct format
- Verify that the resource ID you are passing actually exists
- Make sure there are no typos in the resource ID
- Verify that the provisioning state of the existing resource is `Succeeded` by running the following command to avoid this error while deployment or restoring the resource:
`az resource show --ids--query "properties.provisioningState"` - Sample Resource IDs format:
Log Analytics Workspace Resource ID: `/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.OperationalInsights/workspaces/{workspaceName}`
Azure AI Foundry Project Resource ID: `/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{name}` - You may encounter the error `The language expression property array index '8' is out of bounds` if the resource ID is incomplete. Please ensure your resource ID is correct and contains all required information, as shown in sample resource IDs
- For more information refer [Resource Not Found errors solutions](https://learn.microsoft.com/en-us/azure/azure-resource-manager/troubleshooting/error-not-found?tabs=bicep)
- You can refer to the [Parent Resource Not found](https://learn.microsoft.com/en-us/azure/azure-resource-manager/troubleshooting/error-parent-resource?tabs=bicep) documentation if you encounter this error
**Example causes:**
- The specified **Object ID** is invalid or belongs to another tenant
- The principal was recently created but Azure AD has not yet replicated it
- Attempting to assign a role to a non-existing or deleted Service Principal/User/Group
**How to fix:**
- Verify that the **principal ID is correct** and exists in the same directory/tenant:
`az ad sp show --id` - If the principal was just created, wait a few minutes and retry
- Explicitly set the principalType property (ServicePrincipal, User, or Group) in your ARM/Bicep template to avoid replication delays
- If the principal does not exist, create it again before assigning roles
- For more details, see [Azure PrincipalType documentation](https://learn.microsoft.com/en-us/azure/role-based-access-control/troubleshooting?tabs=bicep)
**It can occur if:**
- The SQL server name is typed incorrectly
- The SQL server was **deleted** but is still being referenced
- You are working in the **wrong subscription context**
- The server exists in a **different subscription/tenant** where you don't have access
**Reproduce:**
Run an Azure CLI command with a non-existent server name:
`az sql db list --server sql-doesnotexist --resource-group myResourceGroup`
or
`az sql server show --name sql-caqfrhxr4i3hyj --resource-group myResourceGroup`
**Resolution:**
- Verify the SQL Server name exists in your subscription:
`az sql server list --output table` - Make sure you are targeting the correct subscription:
`az account show`
`az account set --subscription` - If the server was deleted, either restore it (if possible) or update references to use a valid existing server
- Ensure the subnet's IP address range falls within the virtual network's address space
- Always validate that the subnet CIDR block is a subset of the VNet range
- For Azure Bastion, the AzureBastionSubnet must be at least /27
- Confirm that the AzureBastionSubnet is deployed inside the VNet
- **Check container source:** Confirm whether the deployment is using a Docker image or Azure Container Registry (ACR)
- **Verify ACR configuration:** If ACR is included, review its settings to ensure they comply with Azure requirements
- **Check export settings:** If export is disabled in ACR, make sure public network access is also disabled
- **Redeploy after fix:** Correct the configuration and redeploy. This will prevent the Conflict error during deployment
- For more information refer [ACR Data Loss Prevention](https://learn.microsoft.com/en-us/azure/container-registry/data-loss-prevention) document
- The deployment values either include values that aren't recognized, or required values are missing. Confirm the values for your resource type
- You can refer [Invalid Request Content error](https://learn.microsoft.com/en-us/azure/azure-resource-manager/troubleshooting/common-deployment-errors#:~:text=InvalidRequestContent,Template%20reference) documentation
- This error happens because File Change Audit logs aren't supported on Basic SKU App Service Plans
- Upgrading to Premium/Isolated SKU (supports File Change Audit), or
- Disabling File Change Audit in Diagnostic Settings if you must stay on Basic
- Always cross-check the [supported log types](https://aka.ms/supported-log-types) before adding diagnostic logs to your Bicep templates
**Resolution:**
- Create a **new storage account** with `isHnsEnabled=true` if you require hierarchical namespace
- Migration may be needed if you already have data
- Refer to [Storage Account Update Restrictions](https://aka.ms/storageaccountupdate) for more details
- The AccountProvisioningStateInvalid error occurs when you try to use resources while they are still in the Accepted provisioning state
- This means the deployment has not yet fully completed
- To avoid this error, wait until the provisioning state changes to Succeeded
- Only use the resources once the deployment is fully completed
- This error occurs when a user attempts to redeploy a resource that previously failed to provision
- To resolve the issue, delete the failed deployment first, then start a new deployment
- For guidance on deleting a resource from a Resource Group, refer to the following link: [Delete an Azure Cosmos DB account](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/manage-with-powershell#delete-account:~:text=%3A%24enableMultiMaster-,Delete%20an%20Azure%20Cosmos%20DB%20account,-This%20command%20deletes)
**Common causes:**
- Deleting a Search service and immediately trying to recreate it with the same name
- Rapid redeployments using the same service name in Bicep/ARM templates
- The deletion operation is asynchronous and takes several minutes to complete
**Resolution:**
- **Wait for deletion to complete** (10-15 minutes) before redeploying
- **Use a different service name** - append timestamp or unique identifier to the name
- **Implement retry logic** with exponential backoff as suggested in the error message
- **Check deletion status** before recreating:
`az search service show --name--resource-group ` - For Bicep deployments, ensure your naming strategy includes unique suffixes to avoid conflicts
- For more details, refer to [Azure Search service limits](https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity)
ServiceModelDeprecated/
InvalidResourceProperties** | Model not supported or deprecated in selected region |
- The updated model may not be supported in the selected region. Please verify its availability in the [Azure AI Foundry models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions) document
NameUnavailable/
CustomDomainInUse** | Soft-deleted resource requires restore flag or purge | This error occurs when you try to deploy a Cognitive Services resource that was **soft-deleted** earlier. Azure requires you to explicitly set the **`restore` flag** to `true` if you want to recover the soft-deleted resource. If you don't want to restore the resource, you must **purge the deleted resource** first before redeploying.
**Example causes:**
- Trying to redeploy a Cognitive Services account with the same name as a previously deleted one
- The deleted resource still exists in a **soft-delete retention state**
**How to fix:**
- If you want to restore â add `"restore": true` in your template properties
- If you want a fresh deployment â purge the resource using:
`az cognitiveservices account purge --name--resource-group --location ` - For more details, refer to [Soft delete and resource restore](https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/delete-resource-group?tabs=azure-powershell)
- The error is likely due to an improperly built container image. For resolution steps, refer to the [Azure Container Registry (ACR) â Build & Push Guide](./ACRBuildAndPushGuide.md)
+ {title}
+ {subtitle && (
+
+ {subtitle}
+
+ )}
+ {(primaryButtonText || secondaryButtonText) && (
+
+ );
+};
+
+export default ContentNotFound;
diff --git a/src/frontend/src/components/common/PlanCancellationDialog.tsx b/src/frontend/src/components/common/PlanCancellationDialog.tsx
new file mode 100644
index 00000000..eaa6ec7b
--- /dev/null
+++ b/src/frontend/src/components/common/PlanCancellationDialog.tsx
@@ -0,0 +1,70 @@
+import React from 'react';
+import {
+ Dialog,
+ DialogTrigger,
+ DialogSurface,
+ DialogTitle,
+ DialogContent,
+ DialogBody,
+ DialogActions,
+ Button,
+ DialogOpenChangeEvent,
+ DialogOpenChangeData
+} from '@fluentui/react-components';
+import { Warning20Regular } from '@fluentui/react-icons';
+import "../../styles/Panel.css";
+
+interface PlanCancellationDialogProps {
+ isOpen: boolean;
+ onConfirm: () => void;
+ onCancel: () => void;
+ loading?: boolean;
+}
+
+/**
+ * Confirmation dialog for plan cancellation when navigating during active plans
+ */
+const PlanCancellationDialog: React.FC
+ {primaryButtonText && (
+
+ )}
+ {secondaryButtonText && (
+
+ )}
+
+ )}
+
+
+ Current Team
+
+
+ {selectedTeam ? selectedTeam.name : 'No team selected'}
+
+
+ );
+}
+export default TeamSelected;
\ No newline at end of file
diff --git a/src/frontend/src/components/common/TeamSelector.tsx b/src/frontend/src/components/common/TeamSelector.tsx
new file mode 100644
index 00000000..d4c1f4c9
--- /dev/null
+++ b/src/frontend/src/components/common/TeamSelector.tsx
@@ -0,0 +1,763 @@
+import React, { useState } from 'react';
+import {
+ Button,
+ Dialog,
+ DialogTrigger,
+ DialogSurface,
+ DialogTitle,
+ DialogContent,
+ DialogBody,
+ Text,
+ Spinner,
+ Body1,
+ Caption1,
+ Badge,
+ Input,
+ Radio,
+ RadioGroup,
+ Tab,
+ TabList,
+ Tooltip,
+ DialogOpenChangeEvent,
+ DialogOpenChangeData,
+ SelectTabEvent,
+ SelectTabData,
+ InputOnChangeData
+} from '@fluentui/react-components';
+import {
+ ChevronUpDown16Regular,
+ DeleteRegular,
+ Search20Regular,
+ Dismiss20Regular,
+ CheckmarkCircle20Filled,
+ Delete20Filled
+} from '@fluentui/react-icons';
+import { TeamConfig } from '../../models/Team';
+import { TeamService } from '../../services/TeamService';
+
+import styles from '../../styles/TeamSelector.module.css';
+
+interface TeamSelectorProps {
+ onTeamSelect?: (team: TeamConfig | null) => void;
+ onTeamUpload?: () => Promise setTempSelectedTeam(team)}
+ >
+ {/* Radio Button */}
+
+ }
+ appearance="subtle"
+ size="small"
+ disabled={true}
+ className={`${styles.deleteButton} ${styles.deleteButtonDisabled || ''}`}
+ onClick={(e: React.MouseEvent) => e.stopPropagation()}
+ />
+
+ ) : (
+ }
+ appearance="subtle"
+ size="small"
+ onClick={(e: React.MouseEvent) => handleDeleteTeam(team, e)}
+ className={styles.deleteButton}
+ />
+ )}
+
+ );
+ };
+
+ return (
+ <>
+
+
+
+
+ );
+};
+
+export default TeamSelector;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/HomeInput.tsx b/src/frontend/src/components/content/HomeInput.tsx
new file mode 100644
index 00000000..c4684918
--- /dev/null
+++ b/src/frontend/src/components/content/HomeInput.tsx
@@ -0,0 +1,293 @@
+import {
+ Body1Strong,
+ Button,
+ Caption1,
+ Title2
+} from "@fluentui/react-components";
+
+import React, { useRef, useEffect, useState } from "react";
+import { useNavigate, useLocation } from "react-router-dom";
+
+import "./../../styles/Chat.css";
+import "../../styles/prism-material-oceanic.css";
+import "./../../styles/HomeInput.css";
+
+import { HomeInputProps, iconMap, QuickTask } from "../../models/homeInput";
+import { TaskService } from "../../services/TaskService";
+import { NewTaskService } from "../../services/NewTaskService";
+
+import ChatInput from "@/coral/modules/ChatInput";
+import InlineToaster, { useInlineToaster } from "../toast/InlineToaster";
+import PromptCard from "@/coral/components/PromptCard";
+import { Send } from "@/coral/imports/bundleicons";
+import { Clipboard20Regular } from "@fluentui/react-icons";
+
+// Icon mapping function to convert string icons to FluentUI icons
+const getIconFromString = (
+ iconString: string | React.ReactNode
+): React.ReactNode => {
+ // If it's already a React node, return it
+ if (typeof iconString !== "string") {
+ return iconString;
+ }
+
+ return iconMap[iconString] || iconMap["default"] ||
+ {/* Team name */}
+
+
+ {/* Agent badges - show agent names only */}
+
+ {team.name}
+
+
+ {/* Team description */}
+
+ {team.description}
+
+
+
+ {team.agents.slice(0, 4).map((agent) => (
+
+ {agent.name}
+
+ ))}
+ {team.agents.length > 4 && (
+
+ +{team.agents.length - 4}
+
+ )}
+
+
+ {/* Three-dot Menu Button */}
+ {isDefault ? (
+
+
+ );
+};
+
+export default HomeInput;
diff --git a/src/frontend/src/components/content/PlanChat.tsx b/src/frontend/src/components/content/PlanChat.tsx
new file mode 100644
index 00000000..81193d74
--- /dev/null
+++ b/src/frontend/src/components/content/PlanChat.tsx
@@ -0,0 +1,111 @@
+import React from "react";
+import { PlanChatProps, MPlanData } from "../../models/plan";
+import InlineToaster from "../toast/InlineToaster";
+import { AgentMessageData } from "@/models";
+import renderUserPlanMessage from "./streaming/StreamingUserPlanMessage";
+import renderPlanResponse from "./streaming/StreamingPlanResponse";
+import { renderPlanExecutionMessage, renderThinkingState } from "./streaming/StreamingPlanState";
+import ContentNotFound from "../NotFound/ContentNotFound";
+import PlanChatBody from "./PlanChatBody";
+import renderAgentMessages from "./streaming/StreamingAgentMessage";
+import StreamingBufferMessage from "./streaming/StreamingBufferMessage";
+
+interface SimplifiedPlanChatProps extends PlanChatProps {
+ onPlanReceived?: (planData: MPlanData) => void;
+ initialTask?: string;
+ planApprovalRequest: MPlanData | null;
+ waitingForPlan: boolean;
+ messagesContainerRef: React.RefObject
+
+
+ {
+ setRAIError(null);
+ if (textareaRef.current) {
+ textareaRef.current.focus();
+ }
+ }}
+ onDismiss={() => setRAIError(null)}
+ />
+ )} */}
+
+
+ }
+ />
+
+
+
+
+ How can I help?
+
+
+ {/* Legal Disclaimer for Contract Compliance Review Team */}
+ {isLegalTeam && (
+
+
+ Disclaimer: This tool is not intended to give
+ legal advice; it is intended solely for the purpose of assessing
+ contract compliance against internal guidance and policy frameworks.
+
+
+ )}
+
+ {/* Show RAI error if present */}
+ {/* {raiError && (
+
+ {tasksToDisplay.length > 0 && (
+ <>
+
+
+ Quick tasks
+
+
+
+
+
+ )}
+ {tasksToDisplay.length === 0 && selectedTeam && (
+
+ {tasksToDisplay.map((task) => (
+ handleQuickTaskClick(task)}
+ disabled={submitting}
+ />
+ ))}
+
+
+ No starting tasks available for this team
+
+ )}
+ {!selectedTeam && (
+
+ Select a team to see available tasks
+
+ )}
+
+ {/* Messages Container */}
+
+ );
+};
+
+export default PlanChat;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/PlanChatBody.tsx b/src/frontend/src/components/content/PlanChatBody.tsx
new file mode 100644
index 00000000..d91b3728
--- /dev/null
+++ b/src/frontend/src/components/content/PlanChatBody.tsx
@@ -0,0 +1,77 @@
+import ChatInput from "@/coral/modules/ChatInput";
+import { PlanChatProps } from "@/models";
+import { Button } from "@fluentui/react-components";
+import { Send } from "@/coral/imports/bundleicons";
+
+interface SimplifiedPlanChatProps extends PlanChatProps {
+ planData: any;
+ input: string;
+ setInput: (input: string) => void;
+ submittingChatDisableInput: boolean;
+ OnChatSubmit: (input: string) => void;
+ waitingForPlan: boolean;
+}
+
+const PlanChatBody: React.FC
+ {/* User plan message */}
+ {renderUserPlanMessage(planApprovalRequest, initialTask, planData)}
+
+ {/* AI thinking state */}
+ {renderThinkingState(waitingForPlan)}
+
+ {/* Plan response with all information */}
+ {renderPlanResponse(planApprovalRequest, handleApprovePlan, handleRejectPlan, processingApproval, showApprovalButtons)}
+ {renderAgentMessages(agentMessages)}
+
+ {showProcessingPlanSpinner && renderPlanExecutionMessage()}
+ {/* Streaming plan updates */}
+ {showBufferingText && (
+
+
+ {/* Chat Input - only show if no plan is waiting for approval */}
+
+ OnChatSubmit(input)}
+ disabledChat={submittingChatDisableInput}
+ placeholder="Type your message here..."
+ style={{
+ fontSize: '16px',
+ borderRadius: '8px',
+ // border: '1px solid var(--colorNeutralStroke1)',
+ // backgroundColor: 'var(--colorNeutralBackground1)',
+ width: '100%',
+ boxSizing: 'border-box',
+ }}
+ >
+
+
+ );
+}
+
+export default PlanChatBody;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/PlanPanelLeft.tsx b/src/frontend/src/components/content/PlanPanelLeft.tsx
new file mode 100644
index 00000000..ddfd41b3
--- /dev/null
+++ b/src/frontend/src/components/content/PlanPanelLeft.tsx
@@ -0,0 +1,269 @@
+import PanelLeft from "@/coral/components/Panels/PanelLeft";
+import PanelLeftToolbar from "@/coral/components/Panels/PanelLeftToolbar";
+import {
+ Body1Strong,
+ Toast,
+ ToastBody,
+ ToastTitle,
+ Tooltip,
+ useToastController,
+} from "@fluentui/react-components";
+import {
+ ChatAdd20Regular,
+ ErrorCircle20Regular,
+} from "@fluentui/react-icons";
+import TaskList from "./TaskList";
+import { useCallback, useEffect, useState } from "react";
+import { useNavigate, useParams } from "react-router-dom";
+import { Plan, PlanPanelLefProps, Task, UserInfo } from "@/models";
+import { apiService } from "@/api";
+import { TaskService } from "@/services";
+import ContosoLogo from "../../coral/imports/ContosoLogo";
+import "../../styles/PlanPanelLeft.css";
+import PanelFooter from "@/coral/components/Panels/PanelFooter";
+import PanelUserCard from "../../coral/components/Panels/UserCard";
+import { getUserInfoGlobal } from "@/api/config";
+import TeamSelector from "../common/TeamSelector";
+import { TeamConfig } from "../../models/Team";
+import TeamSelected from "../common/TeamSelected";
+import TeamService from "@/services/TeamService";
+
+const PlanPanelLeft: React.FC
+
+
+
+
+
+
+ );
+};
+
+export default PlanPanelLeft;
diff --git a/src/frontend/src/components/content/PlanPanelRight.tsx b/src/frontend/src/components/content/PlanPanelRight.tsx
new file mode 100644
index 00000000..48442578
--- /dev/null
+++ b/src/frontend/src/components/content/PlanPanelRight.tsx
@@ -0,0 +1,139 @@
+import React from "react";
+import {
+ Body1,
+} from "@fluentui/react-components";
+import {
+ ArrowTurnDownRightRegular,
+} from "@fluentui/react-icons";
+import { PlanDetailsProps } from "../../models";
+import { getAgentIcon, getAgentDisplayNameWithSuffix } from '../../utils/agentIconUtils';
+import ContentNotFound from "../NotFound/ContentNotFound";
+import "../../styles/planpanelright.css";
+
+
+const PlanPanelRight: React.FC
+ {isHomePage && (
+
+ {
+ if (e.key === "Enter" || e.key === " ") {
+ e.preventDefault();
+ onNewTaskButton();
+ }
+ }}
+ >
+ New task
+
+
+
+
+ +
+ {/* User Card */}
+
+
+ No plan available
+
+ );
+ }
+
+ // Extract plan steps from the planApprovalRequest
+ const extractPlanSteps = () => {
+ if (!planApprovalRequest.steps || planApprovalRequest.steps.length === 0) {
+ return [];
+ }
+
+ return planApprovalRequest.steps.map((step, index) => {
+ const action = step.action || step.cleanAction || '';
+ const isHeading = action.trim().endsWith(':');
+
+ return {
+ text: action.trim(),
+ isHeading,
+ key: `${index}-${action.substring(0, 20)}`
+ };
+ }).filter(step => step.text.length > 0);
+ };
+
+ // Render Plan Section
+ const renderPlanSection = () => {
+ const planSteps = extractPlanSteps();
+
+ return (
+
+
+ Plan Overview
+
+
+ {planSteps.length === 0 ? (
+
+ );
+ };
+
+ // Render Agents Section
+ const renderAgentsSection = () => {
+ const agents = planApprovalRequest?.team || [];
+
+ return (
+
+ Plan is being generated...
+
+ ) : (
+
+ {planSteps.map((step, index) => (
+
+ )}
+
+ {step.isHeading ? (
+ // Heading - larger text, bold
+
+ {step.text}
+
+ ) : (
+ // Sub-step - with arrow
+
+ ))}
+
+
+ {step.text}
+
+
+ )}
+
+
+ Agent Team
+
+
+ {agents.length === 0 ? (
+
+ );
+ };
+
+ // Main render
+ return (
+
+ No agents assigned yet...
+
+ ) : (
+
+ {agents.map((agentName, index) => (
+
+ )}
+
+ {/* Agent Icon */}
+
+ ))}
+
+ {getAgentIcon(agentName, planData, planApprovalRequest)}
+
+
+ {/* Agent Info - just name */}
+
+
+ {getAgentDisplayNameWithSuffix(agentName)}
+
+
+
+ {/* Plan section on top */}
+ {renderPlanSection()}
+
+ {/* Agents section below with line demarcation */}
+ {renderAgentsSection()}
+
+ );
+};
+
+export default PlanPanelRight;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/TaskList.tsx b/src/frontend/src/components/content/TaskList.tsx
new file mode 100644
index 00000000..aadb626c
--- /dev/null
+++ b/src/frontend/src/components/content/TaskList.tsx
@@ -0,0 +1,101 @@
+import {
+ Button,
+ Menu,
+ MenuTrigger,
+ Caption1,
+ Skeleton,
+ SkeletonItem,
+} from "@fluentui/react-components";
+import { MoreHorizontal20Regular } from "@fluentui/react-icons";
+import React from "react";
+import "../../styles/TaskList.css";
+import { Task, TaskListProps } from "@/models";
+import {
+ Accordion,
+ AccordionHeader,
+ AccordionItem,
+ AccordionPanel,
+} from "@fluentui/react-components";
+
+const TaskList: React.FC onTaskSelect(task.id)}
+ onKeyDown={(e) => {
+ if (e.key === "Enter" || e.key === " ") {
+ e.preventDefault();
+ onTaskSelect(task.id);
+ }
+ }}
+ >
+
+
+ );
+ };
+
+ const renderSkeleton = (key: string) => (
+
+ {task.date}
+ )}
+ {/* {task.status == "inprogress" && (
+ {`${task?.completed_steps} of ${task?.total_steps} completed`}
+ )} */}
+
+
+
+ {task.name}
+
+ {task.date && task.status == "completed" && (
+
+
+
+
+ );
+
+ return (
+
+
+
+
+
+
+ Completed
+
+
+ {(loading || isLoadingTeam)
+ ? Array.from({ length: 5 }, (_, i) =>
+ renderSkeleton(`completed-${i}`)
+ )
+ : completedTasks.map(renderTaskItem)}
+
+
+
+
+
+ );
+};
+
+export default TaskList;
diff --git a/src/frontend/src/components/content/contoso.tsx b/src/frontend/src/components/content/contoso.tsx
new file mode 100644
index 00000000..0a72809c
--- /dev/null
+++ b/src/frontend/src/components/content/contoso.tsx
@@ -0,0 +1,18 @@
+const ContosoLogo: React.FC = () => {
+ return (
+
+ );
+}
+
+export default ContosoLogo;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/streaming/StreamingAgentMessage.tsx b/src/frontend/src/components/content/streaming/StreamingAgentMessage.tsx
new file mode 100644
index 00000000..26e76f21
--- /dev/null
+++ b/src/frontend/src/components/content/streaming/StreamingAgentMessage.tsx
@@ -0,0 +1,227 @@
+import React from "react";
+import { AgentMessageData, AgentMessageType } from "@/models";
+import ReactMarkdown from "react-markdown";
+import remarkGfm from "remark-gfm";
+import rehypePrism from "rehype-prism";
+import { Body1, Tag, makeStyles, tokens } from "@fluentui/react-components";
+import { TaskService } from "@/services";
+import { PersonRegular } from "@fluentui/react-icons";
+import { getAgentIcon, getAgentDisplayName } from '@/utils/agentIconUtils';
+
+interface StreamingAgentMessageProps {
+ agentMessages: AgentMessageData[];
+ planData?: any;
+ planApprovalRequest?: any;
+}
+
+const useStyles = makeStyles({
+ container: {
+ maxWidth: '800px',
+ margin: '0 auto 32px auto',
+ padding: '0 24px',
+ display: 'flex',
+ alignItems: 'flex-start',
+ gap: '16px',
+ fontFamily: tokens.fontFamilyBase
+ },
+ avatar: {
+ width: '32px',
+ height: '32px',
+ borderRadius: '50%',
+ display: 'flex',
+ alignItems: 'center',
+ justifyContent: 'center',
+ flexShrink: 0
+ },
+ humanAvatar: {
+ backgroundColor: 'var(--colorBrandBackground)'
+ },
+ botAvatar: {
+ backgroundColor: 'var(--colorNeutralBackground3)'
+ },
+ messageContent: {
+ flex: 1,
+ maxWidth: 'calc(100% - 48px)',
+ display: 'flex',
+ flexDirection: 'column'
+ },
+ humanMessageContent: {
+ alignItems: 'flex-end'
+ },
+ botMessageContent: {
+ alignItems: 'flex-start'
+ },
+ agentHeader: {
+ display: 'flex',
+ alignItems: 'center',
+ gap: '12px',
+ marginBottom: '8px'
+ },
+ agentName: {
+ fontWeight: '600',
+ fontSize: '14px',
+ color: 'var(--colorNeutralForeground1)',
+ lineHeight: '20px'
+ },
+ messageBubble: {
+ padding: '12px 16px',
+ borderRadius: '8px',
+ fontSize: '14px',
+ lineHeight: '1.5',
+ wordWrap: 'break-word'
+ },
+ humanBubble: {
+ backgroundColor: 'var(--colorBrandBackground)',
+ color: 'white !important', // Force white text in both light and dark modes
+ maxWidth: '80%',
+ padding: '12px 16px',
+ lineHeight: '1.5',
+ alignSelf: 'flex-end'
+ },
+ botBubble: {
+ backgroundColor: 'var(--colorNeutralBackground2)',
+ color: 'var(--colorNeutralForeground1)',
+ maxWidth: '100%',
+ alignSelf: 'flex-start',
+
+ },
+
+ clarificationBubble: {
+ backgroundColor: 'var(--colorNeutralBackground2)',
+ color: 'var(--colorNeutralForeground1)',
+ padding: '6px 8px',
+ borderRadius: '8px',
+ fontSize: '14px',
+ lineHeight: '1.5',
+ wordWrap: 'break-word',
+ maxWidth: '100%',
+ alignSelf: 'flex-start'
+ },
+
+ actionContainer: {
+ display: 'flex',
+ alignItems: 'center',
+ marginTop: '12px',
+ paddingTop: '8px',
+ borderTop: '1px solid var(--colorNeutralStroke2)'
+ },
+
+ copyButton: {
+ height: '28px',
+ width: '28px'
+ },
+ sampleTag: {
+ fontSize: '11px',
+ opacity: 0.7
+ }
+});
+
+// Check if message is a clarification request
+const isClarificationMessage = (content: string): boolean => {
+ const clarificationKeywords = [
+ 'need clarification',
+ 'please clarify',
+ 'could you provide more details',
+ 'i need more information',
+ 'please specify',
+ 'what do you mean by',
+ 'clarification about'
+ ];
+
+ const lowerContent = content.toLowerCase();
+ return clarificationKeywords.some(keyword => lowerContent.includes(keyword));
+};
+
+const renderAgentMessages = (
+ agentMessages: AgentMessageData[],
+ planData?: any,
+ planApprovalRequest?: any
+) => {
+ const styles = useStyles();
+
+ if (!agentMessages?.length) return null;
+
+ // Filter out messages with empty content
+ const validMessages = agentMessages.filter(msg => msg.content?.trim());
+ if (!validMessages.length) return null;
+
+ return (
+ <>
+ {validMessages.map((msg, index) => {
+ const isHuman = msg.agent_type === AgentMessageType.HUMAN_AGENT;
+ const isClarification = !isHuman && isClarificationMessage(msg.content || '');
+
+ return (
+
+ {/* Avatar */}
+
+ );
+ })}
+
+ );
+};
+
+export default renderAgentMessages;
\ No newline at end of file
diff --git a/src/frontend/src/components/content/streaming/StreamingBufferMessage.tsx b/src/frontend/src/components/content/streaming/StreamingBufferMessage.tsx
new file mode 100644
index 00000000..c3bd7c56
--- /dev/null
+++ b/src/frontend/src/components/content/streaming/StreamingBufferMessage.tsx
@@ -0,0 +1,228 @@
+import React, { useState, useEffect, useRef } from 'react';
+import {
+ Button,
+} from '@fluentui/react-components';
+import { CheckmarkCircle20Regular, ArrowTurnDownRightRegular } from '@fluentui/react-icons';
+import ReactMarkdown from "react-markdown";
+import remarkGfm from "remark-gfm";
+import rehypePrism from "rehype-prism";
+
+interface StreamingBufferMessageProps {
+ streamingMessageBuffer: string;
+ isStreaming?: boolean;
+}
+
+// Convert to a proper React component instead of a function
+const StreamingBufferMessage: React.FC
+ {isHuman ? (
+
+
+ {/* Message Content */}
+
+ {/* Agent Header (only for bots) */}
+ {!isHuman && (
+
+
+
+ {getAgentDisplayName(msg.agent)}
+
+
+ AI Agent
+
+
+ )}
+
+ {/* Message Bubble */}
+
+
+
+ {/* Header */}
+
+
+
+ {/* Content area - collapsed state */}
+ {!isExpanded && (
+
+
+
+
+
+ {/* Top fade overlay for collapsed state */}
+
+
+