Introducción al kernel semántico

El kernel semántico tiene varios paquetes NuGet disponibles. Sin embargo, en la mayoría de los escenarios, normalmente solo necesita Microsoft.SemanticKernel.

Puede instalarlo mediante el siguiente comando:

dotnet add package Microsoft.SemanticKernel

Para obtener la lista completa de paquetes Nuget, consulte el artículo sobre los idiomas admitidos.

Las instrucciones para acceder al SemanticKernel paquete de Python están disponibles aquí. Es tan fácil como:

pip install semantic-kernel

Las instrucciones para acceder al SemanticKernel paquete de Java están disponibles aquí. Es tan fácil como:

<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>com.microsoft.semantic-kernel</groupId>
            <artifactId>semantickernel-bom</artifactId>
            <version>${sk.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

<dependencies>
<dependency>
    <groupId>com.microsoft.semantic-kernel</groupId>
    <artifactId>semantickernel-api</artifactId>
</dependency>
<dependency>
    <groupId>com.microsoft.semantic-kernel</groupId>
    <artifactId>semantickernel-aiservices-openai</artifactId>
</dependency>
</dependencies>

Introducción rápida a los cuadernos

Si es desarrollador de Python o C#, puede empezar a trabajar rápidamente con nuestros cuadernos. Estos cuadernos proporcionan guías paso a paso sobre cómo usar kernel semántico para compilar agentes de IA.

Siga estos pasos para comenzar:

1. Clonación del repositorio de kernel semántico
2. Abrir el repositorio en Visual Studio Code
3. Vaya a _/python/samples/getting_started
4. Abra 00-getting-started.ipynb para empezar a establecer el entorno y crear su primer agente de IA.

Siga estos pasos para comenzar:

1. Clonación del repositorio de kernel semántico
2. Abrir el repositorio en Visual Studio Code
3. Vaya a _/dotnet/notebooks.
4. Abra 00-getting-started.ipynb para empezar a establecer el entorno y crear su primer agente de IA.

// Import packages
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;
using Microsoft.SemanticKernel.Connectors.OpenAI;

// Create a kernel with Azure OpenAI chat completion
var builder = Kernel.CreateBuilder().AddAzureOpenAIChatCompletion(modelId, endpoint, apiKey);

// Add enterprise components
builder.Services.AddLogging(services => services.AddConsole().SetMinimumLevel(LogLevel.Trace));

// Build the kernel
Kernel kernel = builder.Build();
var chatCompletionService = kernel.GetRequiredService<IChatCompletionService>();

// Add a plugin (the LightsPlugin class is defined below)
kernel.Plugins.AddFromType<LightsPlugin>("Lights");

// Enable planning
OpenAIPromptExecutionSettings openAIPromptExecutionSettings = new() 
{
    FunctionChoiceBehavior = FunctionChoiceBehavior.Auto()
};

// Create a history store the conversation
var history = new ChatHistory();

// Initiate a back-and-forth chat
string? userInput;
do {
    // Collect user input
    Console.Write("User > ");
    userInput = Console.ReadLine();

    // Add user input
    history.AddUserMessage(userInput);

    // Get the response from the AI
    var result = await chatCompletionService.GetChatMessageContentAsync(
        history,
        executionSettings: openAIPromptExecutionSettings,
        kernel: kernel);

    // Print the results
    Console.WriteLine("Assistant > " + result);

    // Add the message from the agent to the chat history
    history.AddMessage(result.Role, result.Content ?? string.Empty);
} while (userInput is not null);

import asyncio

from semantic_kernel import Kernel
from semantic_kernel.utils.logging import setup_logging
from semantic_kernel.functions import kernel_function
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior
from semantic_kernel.connectors.ai.chat_completion_client_base import ChatCompletionClientBase
from semantic_kernel.contents.chat_history import ChatHistory
from semantic_kernel.functions.kernel_arguments import KernelArguments

from semantic_kernel.connectors.ai.open_ai.prompt_execution_settings.azure_chat_prompt_execution_settings import (
    AzureChatPromptExecutionSettings,
)

async def main():
    # Initialize the kernel
    kernel = Kernel()

    # Add Azure OpenAI chat completion
    chat_completion = AzureChatCompletion(
        deployment_name="your_models_deployment_name",
        api_key="your_api_key",
        base_url="your_base_url",
    )
    kernel.add_service(chat_completion)

    # Set the logging level for  semantic_kernel.kernel to DEBUG.
    setup_logging()
    logging.getLogger("kernel").setLevel(logging.DEBUG)

    # Add a plugin (the LightsPlugin class is defined below)
    kernel.add_plugin(
        LightsPlugin(),
        plugin_name="Lights",
    )

    # Enable planning
    execution_settings = AzureChatPromptExecutionSettings()
    execution_settings.function_call_behavior = FunctionChoiceBehavior.Auto()

    # Create a history of the conversation
    history = ChatHistory()

    # Initiate a back-and-forth chat
    userInput = None
    while True:
        # Collect user input
        userInput = input("User > ")

        # Terminate the loop if the user says "exit"
        if userInput == "exit":
            break

        # Add user input to the history
        history.add_user_message(userInput)

        # Get the response from the AI
        result = await chat_completion.get_chat_message_content(
            chat_history=history,
            settings=execution_settings,
            kernel=kernel,
        )

        # Print the results
        print("Assistant > " + str(result))

        # Add the message from the agent to the chat history
        history.add_message(result)

# Run the main function
if __name__ == "__main__":
    asyncio.run(main())

OpenAIAsyncClient client = new OpenAIClientBuilder()
    .credential(new AzureKeyCredential(AZURE_CLIENT_KEY))
    .endpoint(CLIENT_ENDPOINT)
    .buildAsyncClient();

// Import the LightsPlugin
KernelPlugin lightPlugin = KernelPluginFactory.createFromObject(new LightsPlugin(),
    "LightsPlugin");

// Create your AI service client
ChatCompletionService chatCompletionService = OpenAIChatCompletion.builder()
    .withModelId(MODEL_ID)
    .withOpenAIAsyncClient(client)
    .build();

// Create a kernel with Azure OpenAI chat completion and plugin
Kernel kernel = Kernel.builder()
    .withAIService(ChatCompletionService.class, chatCompletionService)
    .withPlugin(lightPlugin)
    .build();

// Add a converter to the kernel to show it how to serialise LightModel objects into a prompt
ContextVariableTypes
    .addGlobalConverter(
        ContextVariableTypeConverter.builder(LightModel.class)
            .toPromptString(new Gson()::toJson)
            .build());

// Enable planning
InvocationContext invocationContext = new InvocationContext.Builder()
    .withReturnMode(InvocationReturnMode.LAST_MESSAGE_ONLY)
    .withToolCallBehavior(ToolCallBehavior.allowAllKernelFunctions(true))
    .build();

// Create a history to store the conversation
ChatHistory history = new ChatHistory();

// Initiate a back-and-forth chat
Scanner scanner = new Scanner(System.in);
String userInput;
do {
  // Collect user input
  System.out.print("User > ");

  userInput = scanner.nextLine();
  // Add user input
  history.addUserMessage(userInput);

  // Prompt AI for response to users input
  List<ChatMessageContent<?>> results = chatCompletionService
      .getChatMessageContentsAsync(history, kernel, invocationContext)
      .block();

  for (ChatMessageContent<?> result : results) {
    // Print the results
    if (result.getAuthorRole() == AuthorRole.ASSISTANT && result.getContent() != null) {
      System.out.println("Assistant > " + result);
    }
    // Add the message from the agent to the chat history
    history.addMessage(result);
  }
} while (userInput != null && !userInput.isEmpty());

using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;
using Microsoft.SemanticKernel.Connectors.OpenAI;

import asyncio

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior
from semantic_kernel.connectors.ai.chat_completion_client_base import ChatCompletionClientBase
from semantic_kernel.contents.chat_history import ChatHistory
from semantic_kernel.functions.kernel_arguments import KernelArguments

from semantic_kernel.connectors.ai.open_ai.prompt_execution_settings.azure_chat_prompt_execution_settings import (
    AzureChatPromptExecutionSettings,
)

import com.microsoft.semantickernel.Kernel;
import com.microsoft.semantickernel.aiservices.openai.chatcompletion.OpenAIChatCompletion;
import com.microsoft.semantickernel.contextvariables.ContextVariableTypeConverter;
import com.microsoft.semantickernel.contextvariables.ContextVariableTypes;
import com.microsoft.semantickernel.orchestration.InvocationContext;
import com.microsoft.semantickernel.orchestration.InvocationReturnMode;
import com.microsoft.semantickernel.orchestration.ToolCallBehavior;
import com.microsoft.semantickernel.plugin.KernelPlugin;
import com.microsoft.semantickernel.plugin.KernelPluginFactory;
import com.microsoft.semantickernel.services.chatcompletion.AuthorRole;
import com.microsoft.semantickernel.services.chatcompletion.ChatCompletionService;
import com.microsoft.semantickernel.services.chatcompletion.ChatHistory;
import com.microsoft.semantickernel.services.chatcompletion.ChatMessageContent;

// Create kernel
var builder = Kernel.CreateBuilder()
builder.AddAzureOpenAIChatCompletion(modelId, endpoint, apiKey);

# Initialize the kernel
kernel = Kernel()

# Add Azure OpenAI chat completion
kernel.add_service(AzureChatCompletion(
    deployment_name="your_models_deployment_name",
    api_key="your_api_key",
    base_url="your_base_url",
))

// Create your AI service client
ChatCompletionService chatCompletionService = OpenAIChatCompletion.builder()
    .withModelId(MODEL_ID)
    .withOpenAIAsyncClient(client)
    .build();

// Create a kernel with Azure OpenAI chat completion and plugin
Kernel kernel = Kernel.builder()
    .withAIService(ChatCompletionService.class, chatCompletionService)
    .withPlugin(lightPlugin)
    .build();

3) Agregar servicios empresariales

Una de las principales ventajas de usar kernel semántico es que admite servicios de nivel empresarial. En este ejemplo, hemos agregado el servicio de registro al kernel para ayudar a depurar el agente de IA.

builder.Services.AddLogging(services => services.AddConsole().SetMinimumLevel(LogLevel.Trace));

import logging

# Set the logging level for  semantic_kernel.kernel to DEBUG.
logging.basicConfig(
    format="[%(asctime)s - %(name)s:%(lineno)d - %(levelname)s] %(message)s",
    datefmt="%Y-%m-%d %H:%M:%S",
)
logging.getLogger("kernel").setLevel(logging.DEBUG)

Una vez agregados los servicios, compilamos el kernel y recuperamos el servicio de finalización del chat para su uso posterior.

Kernel kernel = builder.Build();

// Retrieve the chat completion service
var chatCompletionService = kernel.Services.GetRequiredService<IChatCompletionService>();

Una vez configurado el kernel, se recupera el servicio de finalización del chat para su uso posterior.

chat_completion : AzureChatCompletion = kernel.get_service(type=ChatCompletionClientBase)

// Create a kernel with Azure OpenAI chat completion and plugin
Kernel kernel = Kernel.builder()
    .withAIService(ChatCompletionService.class, chatCompletionService)
    .withPlugin(lightPlugin)
    .build();

using System.ComponentModel;
using Microsoft.SemanticKernel;

public class LightsPlugin
{
   // Mock data for the lights
   private readonly List<LightModel> lights = new()
   {
      new LightModel { Id = 1, Name = "Table Lamp", IsOn = false },
      new LightModel { Id = 2, Name = "Porch light", IsOn = false },
      new LightModel { Id = 3, Name = "Chandelier", IsOn = true }
   };

   [KernelFunction("get_lights")]
   [Description("Gets a list of lights and their current state")]
   [return: Description("An array of lights")]
   public async Task<List<LightModel>> GetLightsAsync()
   {
      return lights;
   }

   [KernelFunction("change_state")]
   [Description("Changes the state of the light")]
   [return: Description("The updated state of the light; will return null if the light does not exist")]
   public async Task<LightModel?> ChangeStateAsync(int id, bool isOn)
   {
      var light = lights.FirstOrDefault(light => light.Id == id);

      if (light == null)
      {
         return null;
      }

      // Update the light with the new state
      light.IsOn = isOn;

      return light;
   }
}

public class LightModel
{
   [JsonPropertyName("id")]
   public int Id { get; set; }

   [JsonPropertyName("name")]
   public string Name { get; set; }

   [JsonPropertyName("is_on")]
   public bool? IsOn { get; set; }
}

from typing import Annotated
from semantic_kernel.functions import kernel_function

class LightsPlugin:
    lights = [
        {"id": 1, "name": "Table Lamp", "is_on": False},
        {"id": 2, "name": "Porch light", "is_on": False},
        {"id": 3, "name": "Chandelier", "is_on": True},
    ]

    @kernel_function(
        name="get_lights",
        description="Gets a list of lights and their current state",
    )
    def get_state(
        self,
    ) -> Annotated[str, "the output is a string"]:
        """Gets a list of lights and their current state."""
        return self.lights

    @kernel_function(
        name="change_state",
        description="Changes the state of the light",
    )
    def change_state(
        self,
        id: int,
        is_on: bool,
    ) -> Annotated[str, "the output is a string"]:
        """Changes the state of the light."""
        for light in self.lights:
            if light["id"] == id:
                light["is_on"] = is_on
                return light
        return None

public class LightsPlugin {

  // Mock data for the lights
  private final Map<Integer, LightModel> lights = new HashMap<>();

  public LightsPlugin() {
    lights.put(1, new LightModel(1, "Table Lamp", false));
    lights.put(2, new LightModel(2, "Porch light", false));
    lights.put(3, new LightModel(3, "Chandelier", true));
  }

  @DefineKernelFunction(name = "get_lights", description = "Gets a list of lights and their current state")
  public List<LightModel> getLights() {
    System.out.println("Getting lights");
    return new ArrayList<>(lights.values());
  }

  @DefineKernelFunction(name = "change_state", description = "Changes the state of the light")
  public LightModel changeState(
      @KernelFunctionParameter(name = "id", description = "The ID of the light to change") int id,
      @KernelFunctionParameter(name = "isOn", description = "The new state of the light") boolean isOn) {
    System.out.println("Changing light " + id + " " + isOn);
    if (!lights.containsKey(id)) {
      throw new IllegalArgumentException("Light not found");
    }

    lights.get(id).setIsOn(isOn);

    return lights.get(id);
  }
}

// Add the plugin to the kernel
kernel.Plugins.AddFromType<LightsPlugin>("Lights");

# Add the plugin to the kernel
kernel.add_plugin(
    LightsPlugin(),
    plugin_name="Lights",
)

// Import the LightsPlugin
KernelPlugin lightPlugin = KernelPluginFactory.createFromObject(new LightsPlugin(),
    "LightsPlugin");

OpenAIPromptExecutionSettings openAIPromptExecutionSettings = new()
{
    FunctionChoiceBehavior = FunctionChoiceBehavior.Auto()
};

execution_settings = AzureChatPromptExecutionSettings()
execution_settings.function_call_behavior = FunctionChoiceBehavior.Auto()

// Enable planning
InvocationContext invocationContext = new InvocationContext.Builder()
    .withReturnMode(InvocationReturnMode.LAST_MESSAGE_ONLY)
    .withToolCallBehavior(ToolCallBehavior.allowAllKernelFunctions(true))
    .build();

// Create chat history
var history = new ChatHistory();

// Get the response from the AI
var result = await chatCompletionService.GetChatMessageContentAsync(
    history,
    executionSettings: openAIPromptExecutionSettings,
    kernel: kernel
);

# Create a history of the conversation
history = ChatHistory()

# Get the response from the AI
result = (await chat_completion.get_chat_message_contents(
    chat_history=history,
    settings=execution_settings,
    kernel=kernel,
    arguments=KernelArguments(),
))[0]

userInput = scanner.nextLine();
// Add user input
history.addUserMessage(userInput);

// Prompt AI for response to users input
List<ChatMessageContent<?>> results = chatCompletionService
    .getChatMessageContentsAsync(history, kernel, invocationContext)
    .block();