Get insight about your data from a .NET AI chat app

  • Article

Get started with AI development using a .NET 8 console app to connect to an OpenAI gpt-3.5-turbo model. You'll connect to the AI model using Semantic Kernel to analyze hiking data and provide insights.

Prerequisites

  • .NET 8.0 SDK - Install the .NET 8.0 SDK.
  • An API key from OpenAI so you can run this sample.
  • On Windows, PowerShell v7+ is required. To validate your version, run pwsh in a terminal. It should return the current version. If it returns an error, execute the following command: dotnet tool update --global PowerShell.

Get started with AI development using a .NET 8 console app to connect to an OpenAI gpt-3.5-turbo model deployed on Azure. You'll connect to the AI model using Semantic Kernel to analyze hiking data and provide insights.

Prerequisites

Get the sample project

Clone the GitHub repository that contains the sample apps for all of the quickstarts:

git clone https://github.com/dotnet/ai-samples.git

Create the Azure OpenAI service

The sample GitHub repository is structured as an Azure Developer CLI (azd) template, which azd can use to provision the Azure OpenAI service and model for you.

  1. From a terminal or command prompt, navigate to the src\quickstarts\azure-openai directory of the sample repo.

  2. Run the azd up command to provision the Azure OpenAI resources. It might take several minutes to create the Azure OpenAI service and deploy the model.

    azd up

    azd also configures the required user secrets for the sample app, such as the OpenAI access key.

    Note

    If you encounter an error during the azd up deployment, visit the troubleshooting section.

Try the hiking chat sample

  1. From a terminal or command prompt, navigate to the openai\03-ChattingAboutMyHikes directory.

  2. Run the following commands to configure your OpenAI API key as a secret for the sample app:

    dotnet user-secrets init
dotnet user-secrets set OpenAIKey <your-openai-key>

  3. Use the dotnet run command to run the app:

    dotnet run

  1. From a terminal or command prompt, navigate to the azure-openai\02-HikerAI directory.

  2. Use the dotnet run command to run the app:

    dotnet run

    Tip

    If you get an error message, the Azure OpenAI resources might not have finished deploying. Wait a couple of minutes and try again.

Explore the code

The application uses the Microsoft.SemanticKernel package to send and receive requests to an OpenAI service.

The entire application is contained within the Program.cs file. The first several lines of code set configuration values and gets the OpenAI Key that was previously set using the dotnet user-secrets command.

var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
string model = "gpt-3.5-turbo";
string key = config["OpenAIKey"];

The OpenAIChatCompletionService service facilitates the requests and responses.

// Create the OpenAI Chat Completion Service
OpenAIChatCompletionService service = new(model, key);

Once the OpenAIChatCompletionService client is created, the app reads the content of the file hikes.md and uses it to provide more context to the model by adding a system prompt. This influences model behavior and the generated completions during the conversation.

The application uses the Microsoft.SemanticKernel package to send and receive requests to an Azure OpenAI service deployed in Azure.

The entire application is contained within the Program.cs file. The first several lines of code loads up secrets and configuration values that were set in the dotnet user-secrets for you during the application provisioning.

// == Retrieve the local secrets saved during the Azure deployment ==========
var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
string endpoint = config["AZURE_OPENAI_ENDPOINT"];
string deployment = config["AZURE_OPENAI_GPT_NAME"];
string key = config["AZURE_OPENAI_KEY"];

The AzureOpenAIChatCompletionService service facilitates the requests and responses.

// == Create the Azure OpenAI Chat Completion Service  ==========
AzureOpenAIChatCompletionService service = new(deployment, endpoint, key);

Once the OpenAIChatCompletionService client is created, the app reads the content of the file hikes.md and uses it to provide more context to the model by adding a system prompt. This influences model behavior and the generated completions during the conversation.

// Provide context for the AI model
ChatHistory chatHistory = new($"""
    You are upbeat and friendly. You introduce yourself when first saying hello. 
    Provide a short answer only based on the user hiking records below:  

    {File.ReadAllText("hikes.md")}
    """);
Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last().Content}");

The following code adds a user prompt to the model using the AddUserMessage function. The GetChatMessageContentAsync function instructs the model to generate a response based off the system and user prompts.

// Start the conversation
chatHistory.AddUserMessage("Hi!");
Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last().Content}");

chatHistory.Add(
    await service.GetChatMessageContentAsync(
        chatHistory,
        new OpenAIPromptExecutionSettings()
        { 
            MaxTokens = 400 
        }));
Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last().Content}");

The app adds the response from the model to the chatHistory to maintain the chat history or context.

// Continue the conversation with a question.
chatHistory.AddUserMessage(
    "I would like to know the ratio of the hikes I've done in Canada compared to other countries.");

Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last().Content}");

chatHistory.Add(await service.GetChatMessageContentAsync(
    chatHistory,
    new OpenAIPromptExecutionSettings()
    { 
        MaxTokens = 400 
    }));

Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last().Content}");

Customize the system or user prompts to provide different questions and context:

  • How many times did I hike when it was raining?
  • How many times did I hike in 2021?

The model generates a relevant response to each prompt based on your inputs.

Clean up resources

When you no longer need the sample application or resources, remove the corresponding deployment and all resources.

azd down

Troubleshoot

On Windows, you might get the following error messages after running azd up:

postprovision.ps1 is not digitally signed. The script will not execute on the system

The script postprovision.ps1 is executed to set the .NET user secrets used in the application. To avoid this error, run the following PowerShell command:

Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass

Then re-run the azd up command.

Another possible error:

'pwsh' is not recognized as an internal or external command, operable program or batch file. WARNING: 'postprovision' hook failed with exit code: '1', Path: '.\infra\post-script\postprovision.ps1'. : exit code: 1 Execution will continue since ContinueOnError has been set to true.

The script postprovision.ps1 is executed to set the .NET user secrets used in the application. To avoid this error, manually run the script using the following PowerShell command:

.\infra\post-script\postprovision.ps1

The .NET AI apps now have the user secrets configured and they can be tested.

Next steps