Skip to content

Quick Deploy Guide [Option B]

Prerequisites

  • Azure subscription with Contributor access & Role Based Access Control access
  • VS Code, Azure Developer CLI (aka.ms/azd), Python 3.10+, Git
  • For Fabric deployment: Microsoft Fabric workspace (F8+ capacity) with admin permissions
  • Microsoft ODBC Driver 18

Choose Your Development Environment

Local Visual Studio Code: Open Visual Studio Code. From the File menu, select Open Folder and choose the folder where you want to deploy the workshop.

Or choose one of the options below:

Open in GitHub Codespaces Open in VS Code Web

Note: Please use this optional prompt if you would like to use GitHub Copilot to run the workshop: 

Can you please follow the step by step in https://microsoft.github.io/agentic-applications-for-unified-data-foundation-solution-accelerator/deployment-guide-optionB/ for me. My Fabric Workspace id = <YOUR_FABRIC_WORKSPACE_ID>. Pass it using the --fabric-workspace-id parameter when running the build solution script.
Important instructions:
Do NOT make any code changes to the repository files. 
Only follow the deployment guide instructions exactly as documented. 
Run the commands step by step and wait for each to complete before proceeding.
If I encounter any errors or issues, help me troubleshoot and resolve them before continuing.
Explain what each step does before running it.
If a step fails, suggest solutions based on the error message.

Full Deployment (Fabric + Foundry)

1. Configure Fabric workspace

1a. Create a Fabric capacity in Azure

Already have a Fabric capacity?

If you already have a Fabric capacity (F8+), you can skip this step and use your existing capacity.

Follow the instructions here: Create a Fabric capacity in Azure →

1b. Create a Fabric workspace

Already have a Fabric workspace?

If you already have a Fabric workspace linked to a Fabric capacity, you can skip this step and use your existing workspace.

Follow the instructions here: Create a Fabric workspace →

1c. Verify workspace settings

Fabric IQ must be enabled

Ensure that Fabric IQ is enabled on your tenant before proceeding. This setting is configured in the Fabric Admin Portal.

  1. Go to Fabric Admin Portal → Tenant settings.
  2. Search for and enable both of the following preview features:
    • Ontology (preview)
    • Graph (preview)
    • Data agent item types (preview)
    • Copilot and Azure OpenAI Service
  3. These settings may take a upto 15 minutes to take effect.

For detailed instructions, refer to the official documentation: Fabric IQ Tenant Settings.

  1. Open your newly created workspace or an existing workspace.
  2. Click the Workspace settings gear icon (⚙️) in the top-right area.
  3. Go to License info and verify:
    • The workspace is assigned to a Fabric capacity
    • The capacity SKU is F8 or higher

2. Clone the repository

git clone https://github.com/microsoft/agentic-applications-for-unified-data-foundation-solution-accelerator.git

cd agentic-applications-for-unified-data-foundation-solution-accelerator

3. Deploy Azure resources

azd auth login

az login

VS Code Web users: Use az login --use-device-code since browser-based login is not supported in VS Code Web.

Register the Microsoft Cognitive Services resource provider (required if not already registered on your subscription):

az provider register --namespace Microsoft.CognitiveServices

azd up

When you start the deployment, you will need to set the following parameters:

Setting Description Default value
Environment Name A unique 3–20 character alphanumeric value used to prefix resources, preventing conflicts with others. env_name
Azure Subscription The Azure subscription to deploy resources into. Only prompted if you have multiple subscriptions. (auto-selected if only one)
Azure Region The region where resources will be created. (empty)
AI Model Location The region where AI model will be created *(empty)

Different tenant? Use: azd auth login --tenant-id <tenant-id>

4. Setup Python environment

python -m venv .venv

.venv\Scripts\activate   # or: source .venv/bin/activate

pip install uv && uv pip install -r scripts/requirements.txt

5. Build the solution

Retrieve your Fabric workspace ID

You will need your workspace ID to pass as a parameter when building the solution.

  1. Open your workspace in Microsoft Fabric.

  2. Look at the URL — the workspace ID is the GUID that appears after /groups/:

    https://app.fabric.microsoft.com/groups/{workspace-id}/...

    Copy workspace ID from URL

  3. Copy the workspace ID.

Finding the workspace ID

For more details, refer to the Microsoft documentation: Identify your workspace ID.

Run the build

az login

VS Code Web users: Use az login --use-device-code since browser-based login is not supported in VS Code Web.

python scripts/00_build_solution.py --from 02 --fabric-workspace-id <your-workspace-id>

Note: If you omit --fabric-workspace-id, the script will prompt you for it interactively. Press Enter key to start or Ctrl+C to cancel the process.

6. Test the agent

python scripts/08_test_agent.py

Sample questions to try:

  • "What is the average score from inspections?"
  • "What constitutes a failed inspection?"
  • "Do any inspections violate quality control standards in our Inspection Procedures?"

7. Test the Fabric Data Agent

  1. Go to your Microsoft Fabric workspace
  2. Select "New item" → Search for "Data Agent" → select data agent, provide a name and click create
  3. Add data source → Select your Ontology resource for this workshop
  4. Click Agent instructions from top menu and add the below agent instructions: 
    You are a helpful assistant that can answer user questions using data.
Support group by in GQL.
  5. Click Publish from the top menu and select Publish.

Note: The Ontology set up may take up to 15 minutes so retry after some time if you don't see good responses.

Sample questions to try:

  • "How many tickets are high priority"
  • "What is the average score from inspections?"
  • Show tickets grouped by status.

8. Deploy and launch the application

azd env set AZURE_ENV_DEPLOY_APP true

azd up

9. Set up app permissions

python scripts/00_build_solution.py --from 09

Note: Press Enter key to start or Ctrl+C to cancel the process.

After the agent configuration & API permission set up completes, open the app URL shown in the output.

10. Customize for Your Industry (Optional)

Follow steps in this page to Customize for your use case.

Repository: github.com/microsoft/agentic-applications-for-unified-data-foundation-solution-accelerator