Files
semantic-kernel/dotnet/notebooks/00-getting-started.ipynb
T

4.3 KiB

Watch the Getting Started Quick Start Video

Important

You will need an .NET 10 SDK and Polyglot to get started with this notebook using .NET Interactive.

Step 1: Configure your AI service credentials

Use this notebook first, to choose whether to run these notebooks with OpenAI or Azure OpenAI, and to save your credentials in the configuration file.

In [ ]:
// Load some helper functions, e.g. to load values from settings.json
#!import config/Settings.cs 

Step 2: Import Semantic Kernel SDK from NuGet

In [ ]:
// Import Semantic Kernel
#r "nuget: Microsoft.SemanticKernel, 1.23.0"

Step 3: Instantiate the Kernel

In [ ]:
using Microsoft.SemanticKernel;
using Kernel = Microsoft.SemanticKernel.Kernel;

//Create Kernel builder
var builder = Kernel.CreateBuilder();
In [ ]:
// Configure AI service credentials used by the kernel
var (useAzureOpenAI, model, azureEndpoint, apiKey, orgId) = Settings.LoadFromFile();

if (useAzureOpenAI)
    builder.AddAzureOpenAIChatCompletion(model, azureEndpoint, apiKey);
else
    builder.AddOpenAIChatCompletion(model, apiKey, orgId);

var kernel = builder.Build();

Step 4: Load and Run a Plugin

In [ ]:
// FunPlugin directory path
var funPluginDirectoryPath = Path.Combine(System.IO.Directory.GetCurrentDirectory(), "..", "..", "prompt_template_samples", "FunPlugin");

// Load the FunPlugin from the Plugins Directory
var funPluginFunctions = kernel.ImportPluginFromPromptDirectory(funPluginDirectoryPath);

// Construct arguments
var arguments = new KernelArguments() { ["input"] = "time travel to dinosaur age" };

// Run the Function called Joke
var result = await kernel.InvokeAsync(funPluginFunctions["Joke"], arguments);

// Return the result to the Notebook
Console.WriteLine(result);