Skip to content

Prerequisites

Before attending the Intelligent App Development Workshop, please ensure you have the following prerequisites in place:

  1. Azure account: A Microsoft Azure account with an active subscription. If you don't have one, sign up for a free trial.
  2. Azure subscription with access enabled for the Azure AI Foundry - For more details, see the Azure AI Foundry documentation on how to get access.

Development Environment Setup

You have the option of using Github Codespaces or your local development environment.

Using Github Codespaces

If using Github Codespaces all prerequisites will be pre-installed, however you will need to create a fork as follows:

  1. Navigate to this link to create a new fork (must be logged into your github account).
  2. Accept the default values and click on "Create fork" which will take you to the forked repository in the browser.
  3. From your forked repository click on the "<> Code" button. Then click on the "Create codespace on main" button.

Using Local Dev Container

If you want to use a local dev container, you're in luck! This repo has a container definition.

  1. Install VS Code with the C# and Dev Container extensions.
  2. Install Docker Desktop locally
  3. Open the repo in VS Code and choose the option to re-open the repo in the dev container. If it's the first time, it may take a while to download the image but you can choose the option to monitor the container log.

Using local development environment

If you prefer using a computer with using a local development environment, the following pre-requisites need to be installed:

  1. Git: Ensure you have Git installed on your computer.
  2. Azure CLI: Install the Azure Command-Line Interface (CLI) to interact with Azure services and manage resources from the command line.
  3. .NET SDK: install .NET SDK to build and run .NET projects.
  4. Docker: Install Docker Desktop to build and run containerized applications.
  5. Node.Js: Install Node.Js to build and run web application.
  6. Azure Development CLI: Install azd to be able to provision and deploy application to Azure.
  7. bash/shell terminal: the lessons assume bash/shell script syntax. If using Windows, either you can either using Git Bash (included when you install Git) or installing WSL (Windows Subsystem for Linux).

Next you will need to clone this repo using:

git clone https://github.com/Azure/intelligent-app-workshop.git

Change directory into cloned repo:

cd intelligent-app-workshop

Set up Azure Resources

  1. Deploy Pre-requisite resource template

    1. In your cli, go to the /workshop/pre-reqs/ directory and run az login
    2. Run azd provision -e sk-test-pre-req. Later, if you choose to deploy the app to ACA, you will deploy to a different resource group (sk-test).
    3. Choose the appropriate subscription and location. eastus2 or swedencentral are recommended.
    4. When complete, you should be able to log to the portal and see the resources:
      1. Go to the Azure Portal.
      2. In the search bar, type in Resource Groups, and choose the Resource Groups page.
      3. Locate the newly created RG and view the resources in it.

  2. Create Azure Grounding with Bing Search resource. We will use this to ensure the LLM can get current data from the internet:

    1. Go to the Azure Portal.
    2. Click on Create A Resource
    3. On the search bar type Grounding with Bing Search and hit enter
    4. Locate Grounding with Bing Search and click Create
    5. On the Create a Grounding with Bing Search Resource page, provide the following information for the fields on the Basics tab:
      • Subscription: The Azure subscription to used for your service.
      • Resource group: Select the resource group created by the prerequisites stack
      • Name: A descriptive and unique name for your Grounding with Bing Search Service resource, such as grounding-bing-search-myid.
      • Region: Global (default).
      • Pricing Tier: Grounding with Bing Search (default)
      • Terms: Check the box to acknowledge the terms of use.
    6. Click Next.
    7. On the Tags tab click Next
    8. Click Create.

  3. Create Agents connection to Grounding with Bing Search resource:

    1. Go to the Azure AI Foundry (https://ai.azure.com/) and choose the project created by bicep.
    2. Scroll down on the left side and click Management Center.
    3. On the left side click Connected Resources.
    4. You will see that the bicep template deployed an OpenAI resource and connected it to your Foundry project.
    5. Click New Connection Newconnection
    6. Scroll down and choose Grounding with Bing Search.
    7. Click Create connection. Groundingconnection
    8. Find the resource you created and click Add connection.
    9. Click Close.
    10. On the Connections page, copy the name of the connection you just created and paste it as the groundingWithBingConnectionId value within the AIFoundryProject element in the appSettings.json file.

  4. Upgrade OpenAI Connection

    1. The OpenAI connection needs to be upgraded to allow you to see your deployed model. On the Connections page, click on your Open AI connection.
    2. Click Upgrade Connection Upgradeconnection
    3. On the left, click Models + Endpoints and you should see your gpt-4o deployment. If you need to adjust settings on it at a later time, this is where you can find it.

appsettings.json Configuration

  1. Go to the workshop/dotnet/Lessons directory. Copy and rename the file appsettings.json.example into each of the lesson directories as follows (example command for Lesson1):

    cp workshop/dotnet/Lessons/appsettings.json.example workshop/dotnet/Lessons/Lesson1/appsettings.json

  2. Store AI Foundry settings in appsettings.json

    1. In Azure AI Foundry main project page, copy the connection string and use it as the connectionString value in the AIFoundryProject element of appsettings.json.
    2. Under My Assets choose Models + Endpoints. Next to the gpt-4o deployment, click Get Endpoint.
    3. Copy the endpoint and store it as endpoint value in the AIFoundryProject element of appsettings.json.
    4. Copy the api key and store as the apiKey value in appsettings.json. OpenAI Deployment settings

  3. We need to obtain an API Key to be able to get stock prices from polygon.io. You can sign up for a free API Key by creating a login. This value will be needed for Lesson 3.

    1. Once logged in, from the polygon.io Dashboard locate the Keys section. Copy the default key value and paste it as the apiKey value within the StockService element in the appsettings.json file.

By ensuring you have completed these prerequisites, you'll be well-prepared to dive into the Intelligent App Development Workshop and make the most of the hands-on learning experience.