Invoke .NET functions using an AI model

In this quickstart, you create a .NET console AI chat app to connect to an AI model with local function calling enabled. The app uses the Microsoft.Extensions.AI library so you can write code using AI abstractions rather than a specific SDK. AI abstractions enable you to change the underlying AI model with minimal code changes.

Clone the sample repository

You can create your own app using the steps in the sections ahead, or you can clone the GitHub repository that contains the completed sample apps for all of the quickstarts. If you plan to use Azure OpenAI, the sample repo is also structured as an Azure Developer CLI template that can provision an Azure OpenAI resource for you.

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

Create the app

Complete the following steps to create a .NET console app to connect to an AI model.

1. In an empty directory on your computer, use the dotnet new command to create a new console app:

   dotnet new console -o FunctionCallingAI
   

2. Change directory into the app folder:

   cd FunctionCallingAI
   

3. Install the required packages:

   dotnet add package Azure.Identity
   dotnet add package Azure.AI.OpenAI
   dotnet add package Microsoft.Extensions.AI
   dotnet add package Microsoft.Extensions.AI.OpenAI
   dotnet add package Microsoft.Extensions.Configuration
   dotnet add package Microsoft.Extensions.Configuration.UserSecrets
   

   dotnet add package Microsoft.Extensions.AI
   dotnet add package Microsoft.Extensions.AI.OpenAI
   dotnet add package Microsoft.Extensions.Configuration
   dotnet add package Microsoft.Extensions.Configuration.UserSecrets
   

4. Open the app in Visual Studio code or your editor of choice

   code .
   

Add the app code

The app uses the Microsoft.Extensions.AI package to send and receive requests to the AI model.

1. In the Program.cs file, add the following code to connect and authenticate to the AI model. The ChatClient is also configured to use function invocation, which allows .NET functions in your code to be called by the AI model.

   using Microsoft.Extensions.Configuration;
   using Microsoft.Extensions.AI;
   using Azure.AI.OpenAI;
   using Azure.Identity;
   
   var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
   string endpoint = config["AZURE_OPENAI_ENDPOINT"];
   string deployment = config["AZURE_OPENAI_GPT_NAME"];
   
   IChatClient client =
       new ChatClientBuilder()
           .UseFunctionInvocation()
           .Use(
               new AzureOpenAIClient(new Uri(endpoint),
               new DefaultAzureCredential())
                   .AsChatClient(deployment));
   

   Note

   DefaultAzureCredential searches for authentication credentials from your local tooling. If you aren't using the azd template to provision the Azure OpenAI resource, you'll need to assign the Azure AI Developer role to the account you used to sign in to Visual Studio or the Azure CLI. For more information, see Authenticate to Azure AI services with .NET.

   using Microsoft.Extensions.AI;
   using Microsoft.Extensions.Configuration;
   using OpenAI;
   
   var config = new ConfigurationBuilder().AddUserSecrets<Program>().Build();
   string model = config["ModelName"];
   string key = config["OpenAIKey"];
   
   IChatClient client =
       new ChatClientBuilder()
           .UseFunctionInvocation()
           .Use(
               new OpenAIClient(key)
                   .AsChatClient(model));
   

2. Create a new ChatOptions object that contains an inline function the AI model can call to get the current weather. The function declaration includes a delegate to run logic and name and description parameters to describe the purpose of the function to the AI model.

   // Add a new plugin with a local .NET function that should be available to the AI model
   var chatOptions = new ChatOptions
   {
       Tools = [AIFunctionFactory.Create((string location, string unit) =>
       {
           // Here you would call a weather API to get the weather for the location
           return "Periods of rain or drizzle, 15 C";
       },
       "get_current_weather",
       "Get the current weather in a given location")]
   };
   

3. Add a system prompt to the chatHistory to provide context and instructions to the model. Send a user prompt with a question that requires the AI model to call the registered function to properly answer the question.

   // System prompt to provide context
   List<ChatMessage> chatHistory = [new(ChatRole.System, """
       You are a hiking enthusiast who helps people discover fun hikes in their area. You are upbeat and friendly.
       """)];
   
   // Weather conversation relevant to the registered function
   chatHistory.Add(new ChatMessage(ChatRole.User,
       "I live in Montreal and I'm looking for a moderate intensity hike. What's the current weather like? "));
   Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last()}");
   
   var response = await client.CompleteAsync(chatHistory, chatOptions);
   chatHistory.Add(new ChatMessage(ChatRole.Assistant, response.Message.Contents));
   Console.WriteLine($"{chatHistory.Last().Role} >>> {chatHistory.Last()}");
   

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

   dotnet run
   

   The app prints a the completion response from the AI model that includes data provided by the .NET function. The AI model understood the registered function was available and called it automatically to generate a proper response.

azd down

Next steps

• Quickstart - Build an AI chat app with .NET
• Generate text and conversations with .NET and Azure OpenAI Completions