操作指南：`ChatCompletionAgent`

2025-05-06

重要

此功能处于实验阶段。此阶段的功能正在开发中，在升级到预览阶段或候选发布阶段之前可能会更改。

概述

在这个示例中，我们将探讨如何配置插件以访问 GitHub API，并提供模板化的指示给 ChatCompletionAgent，以回答有关 GitHub 存储库的问题。该方法将逐步说明编码过程中的关键部分。作为任务的一部分，代理将在响应中提供文档引文。

流媒体将用于传递智能助手的响应。这将在任务进行时提供实时更新。

入门

在继续执行功能编码之前，请确保开发环境已完全设置和配置。

首先创建 控制台 项目。然后，包括以下包引用，以确保所有必需的依赖项都可用。

若要从命令行添加包依赖项，请使用 dotnet 以下命令：

dotnet add package Azure.Identity
dotnet add package Microsoft.Extensions.Configuration
dotnet add package Microsoft.Extensions.Configuration.Binder
dotnet add package Microsoft.Extensions.Configuration.UserSecrets
dotnet add package Microsoft.Extensions.Configuration.EnvironmentVariables
dotnet add package Microsoft.SemanticKernel.Connectors.AzureOpenAI
dotnet add package Microsoft.SemanticKernel.Agents.Core --prerelease

重要

如果在 Visual Studio 中管理 NuGet 包，请确保选中 Include prerelease。

项目文件（.csproj）应包含以下 PackageReference 定义：

  <ItemGroup>
    <PackageReference Include="Azure.Identity" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.Binder" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.UserSecrets" Version="<stable>" />
    <PackageReference Include="Microsoft.Extensions.Configuration.EnvironmentVariables" Version="<stable>" />
    <PackageReference Include="Microsoft.SemanticKernel.Agents.Core" Version="<latest>" />
    <PackageReference Include="Microsoft.SemanticKernel.Connectors.AzureOpenAI" Version="<latest>" />
  </ItemGroup>

Agent Framework 是实验性的，需要屏蔽警告。这可以在项目文件（.csproj）中作为一个属性来解决。

  <PropertyGroup>
    <NoWarn>$(NoWarn);CA2007;IDE1006;SKEXP0001;SKEXP0110;OPENAI001</NoWarn>
  </PropertyGroup>

此外，从GitHubPlugin.cs复制 GitHub 插件和模型（GitHubModels.cs以及LearnResources）。在项目文件夹中添加这些文件。

首先创建一个将保存脚本（.py 文件）和示例资源的文件夹。在 .py 文件的顶部包括以下导入：

import asyncio
import os
import sys
from datetime import datetime

from semantic_kernel.agents import ChatCompletionAgent, ChatHistoryAgentThread
from semantic_kernel.connectors.ai import FunctionChoiceBehavior
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.functions import KernelArguments
from semantic_kernel.kernel import Kernel

# Adjust the sys.path so we can use the GitHubPlugin and GitHubSettings classes
# This is so we can run the code from the samples/learn_resources/agent_docs directory
# If you are running code from your own project, you may not need need to do this.
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))

from plugins.GithubPlugin.github import GitHubPlugin, GitHubSettings  # noqa: E402

此外，从github.py复制 GitHub 插件和模型（LearnResources）。在项目文件夹中添加这些文件。

首先创建 Maven 控制台项目。然后，包括以下包引用，以确保所有必需的依赖项都可用。

项目 pom.xml 应包含以下依赖项：

<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>com.microsoft.semantic-kernel</groupId>
            <artifactId>semantickernel-bom</artifactId>
            <version>[LATEST]</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

<dependencies>
    <dependency>
        <groupId>com.microsoft.semantic-kernel</groupId>
        <artifactId>semantickernel-agents-core</artifactId>
    </dependency>

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

此外，从GitHubPlugin.java复制 GitHub 插件和模型（GitHubModels.java以及LearnResources）。在项目文件夹中添加这些文件。

配置

此示例需要配置设置才能连接到远程服务。需要为 OpenAI 或 Azure OpenAI 以及 GitHub 定义设置。

注释

有关 GitHub 个人访问令牌的信息，请参阅：管理个人访问令牌。

# OpenAI
dotnet user-secrets set "OpenAISettings:ApiKey" "<api-key>"
dotnet user-secrets set "OpenAISettings:ChatModel" "gpt-4o"

# Azure OpenAI
dotnet user-secrets set "AzureOpenAISettings:ApiKey" "<api-key>" # Not required if using token-credential
dotnet user-secrets set "AzureOpenAISettings:Endpoint" "<model-endpoint>"
dotnet user-secrets set "AzureOpenAISettings:ChatModelDeployment" "gpt-4o"

# GitHub
dotnet user-secrets set "GitHubSettings:BaseUrl" "https://api.github.com"
dotnet user-secrets set "GitHubSettings:Token" "<personal access token>"

以下类在所有代理示例中均使用。请确保将其包含在项目中，以确保适当的功能。此类充当以下示例的基础组件。

using System.Reflection;
using Microsoft.Extensions.Configuration;

namespace AgentsSample;

public class Settings
{
    private readonly IConfigurationRoot configRoot;

    private AzureOpenAISettings azureOpenAI;
    private OpenAISettings openAI;

    public AzureOpenAISettings AzureOpenAI => this.azureOpenAI ??= this.GetSettings<Settings.AzureOpenAISettings>();
    public OpenAISettings OpenAI => this.openAI ??= this.GetSettings<Settings.OpenAISettings>();

    public class OpenAISettings
    {
        public string ChatModel { get; set; } = string.Empty;
        public string ApiKey { get; set; } = string.Empty;
    }

    public class AzureOpenAISettings
    {
        public string ChatModelDeployment { get; set; } = string.Empty;
        public string Endpoint { get; set; } = string.Empty;
        public string ApiKey { get; set; } = string.Empty;
    }

    public TSettings GetSettings<TSettings>() =>
        this.configRoot.GetRequiredSection(typeof(TSettings).Name).Get<TSettings>()!;

    public Settings()
    {
        this.configRoot =
            new ConfigurationBuilder()
                .AddEnvironmentVariables()
                .AddUserSecrets(Assembly.GetExecutingAssembly(), optional: true)
                .Build();
    }
}

运行示例代码的正确配置入门的最快方法是在项目的根目录（运行脚本的位置）创建 .env 文件。

在 .env 文件中为 Azure OpenAI 或 OpenAI 配置以下设置：

AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://<resource-name>.openai.azure.com/"
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_API_VERSION="..."

OPENAI_API_KEY="sk-..."
OPENAI_ORG_ID=""
OPENAI_CHAT_MODEL_ID=""

配置后，相应的 AI 服务类将选取所需的变量，并在实例化期间使用这些变量。

在系统中定义以下环境变量。

# Azure OpenAI
AZURE_OPENAI_API_KEY=""
AZURE_OPENAI_ENDPOINT="https://<resource-name>.openai.azure.com/"
AZURE_CHAT_MODEL_DEPLOYMENT=""

# OpenAI
OPENAI_API_KEY=""
OPENAI_MODEL_ID=""

在文件的顶部，可以检索其值，如下所示。

// Azure OpenAI
private static final String AZURE_OPENAI_API_KEY = System.getenv("AZURE_OPENAI_API_KEY");
private static final String AZURE_OPENAI_ENDPOINT = System.getenv("AZURE_OPENAI_ENDPOINT");
private static final String AZURE_CHAT_MODEL_DEPLOYMENT = System.getenv().getOrDefault("AZURE_CHAT_MODEL_DEPLOYMENT", "gpt-4o");

// OpenAI
private static final String OPENAI_API_KEY = System.getenv("OPENAI_API_KEY");
private static final String OPENAI_MODEL_ID = System.getenv().getOrDefault("OPENAI_MODEL_ID", "gpt-4o");

编码

此示例的编码过程涉及：

安装程序 - 初始化设置和插件。
Agent 定义 - 使用模板化指令和插件创建 ChatCompletionAgent 。
聊天循环 - 编写驱动用户/代理交互的循环。

最终部分提供了完整的示例代码。有关完整实现，请参阅该部分。

安装

在创建 ChatCompletionAgent 之前，必须初始化配置设置、插件和 Kernel。

在上一Settings部分中引用的类进行初始化。

Settings settings = new();

使用其设置初始化插件。

此时会显示一条消息来指示进度。

Console.WriteLine("Initialize plugins...");
GitHubSettings githubSettings = settings.GetSettings<GitHubSettings>();
GitHubPlugin githubPlugin = new(githubSettings);

gh_settings = GitHubSettings(
    token="<PAT value>"
)
kernel.add_plugin(GitHubPlugin(settings=gh_settings), plugin_name="github")

var githubPlugin = new GitHubPlugin(GITHUB_PAT);

现在，用Kernel和之前创建的IChatCompletionService来初始化GitHubPlugin实例。

Console.WriteLine("Creating kernel...");
IKernelBuilder builder = Kernel.CreateBuilder();

builder.AddAzureOpenAIChatCompletion(
    settings.AzureOpenAI.ChatModelDeployment,
    settings.AzureOpenAI.Endpoint,
    new AzureCliCredential());

builder.Plugins.AddFromObject(githubPlugin);

Kernel kernel = builder.Build();

kernel = Kernel()

# Add the AzureChatCompletion AI Service to the Kernel
service_id = "agent"
kernel.add_service(AzureChatCompletion(service_id=service_id))

settings = kernel.get_prompt_execution_settings_from_service_id(service_id=service_id)
# Configure the function choice behavior to auto invoke kernel functions
settings.function_choice_behavior = FunctionChoiceBehavior.Auto()

OpenAIAsyncClient client = new OpenAIClientBuilder()
    .credential(new AzureKeyCredential(AZURE_OPENAI_API_KEY))
    .endpoint(AZURE_OPENAI_ENDPOINT)
    .buildAsyncClient();

ChatCompletionService chatCompletion = OpenAIChatCompletion.builder()
    .withModelId(AZURE_CHAT_MODEL_DEPLOYMENT)
    .withOpenAIAsyncClient(client)
    .build();

Kernel kernel = Kernel.builder()
    .withAIService(ChatCompletionService.class, chatCompletion)
    .withPlugin(KernelPluginFactory.createFromObject(githubPlugin, "GitHubPlugin"))
    .build();

代理定义

最后，我们准备实例化一个ChatCompletionAgent，包括其指令、关联的Kernel以及默认参数和执行设置。在这种情况下，我们希望自动执行任何插件函数。

Console.WriteLine("Defining agent...");
ChatCompletionAgent agent =
    new()
    {
        Name = "SampleAssistantAgent",
        Instructions =
            """
            You are an agent designed to query and retrieve information from a single GitHub repository in a read-only manner.
            You are also able to access the profile of the active user.

            Use the current date and time to provide up-to-date details or time-sensitive responses.

            The repository you are querying is a public repository with the following name: {{$repository}}

            The current date and time is: {{$now}}. 
            """,
        Kernel = kernel,
        Arguments =
            new KernelArguments(new AzureOpenAIPromptExecutionSettings() { FunctionChoiceBehavior = FunctionChoiceBehavior.Auto() })
            {
                { "repository", "microsoft/semantic-kernel" }
            }
    };

Console.WriteLine("Ready!");

agent = ChatCompletionAgent(
    kernel=kernel,
    name="SampleAssistantAgent",
    instructions=f"""
        You are an agent designed to query and retrieve information from a single GitHub repository in a read-only 
        manner.
        You are also able to access the profile of the active user.

        Use the current date and time to provide up-to-date details or time-sensitive responses.

        The repository you are querying is a public repository with the following name: microsoft/semantic-kernel

        The current date and time is: {{$now}}. 
        """,
    arguments=KernelArguments(
        settings=settings,
    ),
)

// Invocation context for the agent
InvocationContext invocationContext = InvocationContext.builder()
    .withFunctionChoiceBehavior(FunctionChoiceBehavior.auto(true))
    .build()

ChatCompletionAgent agent = ChatCompletionAgent.builder()
    .withName("SampleAssistantAgent")
    .withKernel(kernel)
    .withInvocationContext(invocationContext)
    .withTemplate(
        DefaultPromptTemplate.build(
            PromptTemplateConfig.builder()
                .withTemplate(
                    """
                    You are an agent designed to query and retrieve information from a single GitHub repository in a read-only manner.
                    You are also able to access the profile of the active user.

                    Use the current date and time to provide up-to-date details or time-sensitive responses.

                    The repository you are querying is a public repository with the following name: {{$repository}}

                    The current date and time is: {{$now}}.
                    """)
                .build()))
    .withKernelArguments(
        KernelArguments.builder()
            .withVariable("repository", "microsoft/semantic-kernel-java")
            .withExecutionSettings(PromptExecutionSettings.builder()
                    .build())
            .build())
    .build();

聊天循环

最后，我们能够协调用户与 Agent之间的交互。首先创建一个 ChatHistoryAgentThread 对象来维护聊天状态并创建一个空循环。

ChatHistoryAgentThread agentThread = new();
bool isComplete = false;
do
{
    // processing logic here
} while (!isComplete);

thread: ChatHistoryAgentThread = None
is_complete: bool = False
while not is_complete:
    # processing logic here

AgentThread agentThread = new ChatHistoryAgentThread();
boolean isComplete = false;

while (!isComplete) {
    // processing logic here
}

现在，让我们在前面的循环中捕获用户输入。在这种情况下，将忽略空输入，术语 EXIT 将指示会话已完成。

Console.WriteLine();
Console.Write("> ");
string input = Console.ReadLine();
if (string.IsNullOrWhiteSpace(input))
{
    continue;
}
if (input.Trim().Equals("EXIT", StringComparison.OrdinalIgnoreCase))
{
    isComplete = true;
    break;
}

var message = new ChatMessageContent(AuthorRole.User, input);

Console.WriteLine();

user_input = input("User:> ")
if not user_input:
    continue

if user_input.lower() == "exit":
    is_complete = True
    break

Scanner scanner = new Scanner(System.in);

while (!isComplete) {
    System.out.print("> ");

    String input = scanner.nextLine();
    if (input.isEmpty()) {
        continue;
    }

    if (input.equalsIgnoreCase("exit")) {
        isComplete = true;
        break;
    }

}

若要生成 Agent 对用户输入的响应，请使用 Arguments 调用代理，以提供指定当前日期和时间的最终模板参数。

然后，响应 Agent 会显示给用户。

DateTime now = DateTime.Now;
KernelArguments arguments =
    new()
    {
        { "now", $"{now.ToShortDateString()} {now.ToShortTimeString()}" }
    };
await foreach (ChatMessageContent response in agent.InvokeAsync(message, agentThread, options: new() { KernelArguments = arguments }))
{
    Console.WriteLine($"{response.Content}");
}

arguments = KernelArguments(
    now=datetime.now().strftime("%Y-%m-%d %H:%M")
)

async for response in agent.invoke(messages=user_input, thread=thread, arguments=arguments):
    print(f"{response.content}")
    thread = response.thread

var options = AgentInvokeOptions.builder()
    .withKernelArguments(KernelArguments.builder()
            .withVariable("now", OffsetDateTime.now())
            .build())
    .build();

for (var response : agent.invokeAsync(message, agentThread, options).block()) {
    System.out.println(response.getMessage());
    agentThread = response.getThread();
}

最终

将所有步骤组合在一起，我们提供了此示例的最终代码。下面提供了完整的实现。

请尝试使用这些建议的输入：

我的用户名是什么？
描述存储库。
描述在存储库中创建的最新问题。
列出上周关闭的前 10 个问题。
这些问题是如何被标记的？
列出“代理”标签最近打开的 5 个问题

using System;
using System.Threading.Tasks;
using Azure.Identity;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Agents;
using Microsoft.SemanticKernel.ChatCompletion;
using Microsoft.SemanticKernel.Connectors.AzureOpenAI;
using Plugins;

namespace AgentsSample;

public static class Program
{
    public static async Task Main()
    {
        // Load configuration from environment variables or user secrets.
        Settings settings = new();

        Console.WriteLine("Initialize plugins...");
        GitHubSettings githubSettings = settings.GetSettings<GitHubSettings>();
        GitHubPlugin githubPlugin = new(githubSettings);

        Console.WriteLine("Creating kernel...");
        IKernelBuilder builder = Kernel.CreateBuilder();

        builder.AddAzureOpenAIChatCompletion(
            settings.AzureOpenAI.ChatModelDeployment,
            settings.AzureOpenAI.Endpoint,
            new AzureCliCredential());

        builder.Plugins.AddFromObject(githubPlugin);

        Kernel kernel = builder.Build();

        Console.WriteLine("Defining agent...");
        ChatCompletionAgent agent =
            new()
            {
                Name = "SampleAssistantAgent",
                Instructions =
                        """
                        You are an agent designed to query and retrieve information from a single GitHub repository in a read-only manner.
                        You are also able to access the profile of the active user.

                        Use the current date and time to provide up-to-date details or time-sensitive responses.

                        The repository you are querying is a public repository with the following name: {{$repository}}

                        The current date and time is: {{$now}}. 
                        """,
                Kernel = kernel,
                Arguments =
                    new KernelArguments(new AzureOpenAIPromptExecutionSettings() { FunctionChoiceBehavior = FunctionChoiceBehavior.Auto() })
                    {
                        { "repository", "microsoft/semantic-kernel" }
                    }
            };

        Console.WriteLine("Ready!");

        ChatHistoryAgentThread agentThread = new();
        bool isComplete = false;
        do
        {
            Console.WriteLine();
            Console.Write("> ");
            string input = Console.ReadLine();
            if (string.IsNullOrWhiteSpace(input))
            {
                continue;
            }
            if (input.Trim().Equals("EXIT", StringComparison.OrdinalIgnoreCase))
            {
                isComplete = true;
                break;
            }

            var message = new ChatMessageContent(AuthorRole.User, input);

            Console.WriteLine();

            DateTime now = DateTime.Now;
            KernelArguments arguments =
                new()
                {
                    { "now", $"{now.ToShortDateString()} {now.ToShortTimeString()}" }
                };
            await foreach (ChatMessageContent response in agent.InvokeAsync(message, agentThread, options: new() { KernelArguments = arguments }))
            {
                // Display response.
                Console.WriteLine($"{response.Content}");
            }

        } while (!isComplete);
    }
}

import asyncio
import os
import sys
from datetime import datetime

from semantic_kernel.agents import ChatCompletionAgent, ChatHistoryAgentThread
from semantic_kernel.connectors.ai import FunctionChoiceBehavior
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
from semantic_kernel.functions import KernelArguments
from semantic_kernel.kernel import Kernel

# Adjust the sys.path so we can use the GitHubPlugin and GitHubSettings classes
# This is so we can run the code from the samples/learn_resources/agent_docs directory
# If you are running code from your own project, you may not need need to do this.
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))

from plugins.GithubPlugin.github import GitHubPlugin, GitHubSettings  # noqa: E402

async def main():
    kernel = Kernel()

    # Add the AzureChatCompletion AI Service to the Kernel
    service_id = "agent"
    kernel.add_service(AzureChatCompletion(service_id=service_id))

    settings = kernel.get_prompt_execution_settings_from_service_id(service_id=service_id)
    # Configure the function choice behavior to auto invoke kernel functions
    settings.function_choice_behavior = FunctionChoiceBehavior.Auto()

    # Set your GitHub Personal Access Token (PAT) value here
    gh_settings = GitHubSettings(token="")  # nosec
    kernel.add_plugin(plugin=GitHubPlugin(gh_settings), plugin_name="GithubPlugin")

    current_time = datetime.now().isoformat()

    # Create the agent
    agent = ChatCompletionAgent(
        kernel=kernel,
        name="SampleAssistantAgent",
        instructions=f"""
            You are an agent designed to query and retrieve information from a single GitHub repository in a read-only 
            manner.
            You are also able to access the profile of the active user.

            Use the current date and time to provide up-to-date details or time-sensitive responses.

            The repository you are querying is a public repository with the following name: microsoft/semantic-kernel

            The current date and time is: {current_time}. 
            """,
        arguments=KernelArguments(settings=settings),
    )

    thread: ChatHistoryAgentThread = None
    is_complete: bool = False
    while not is_complete:
        user_input = input("User:> ")
        if not user_input:
            continue

        if user_input.lower() == "exit":
            is_complete = True
            break

        arguments = KernelArguments(now=datetime.now().strftime("%Y-%m-%d %H:%M"))

        async for response in agent.invoke(messages=user_input, thread=thread, arguments=arguments):
            print(f"{response.content}")
            thread = response.thread


if __name__ == "__main__":
    asyncio.run(main())

可以在存储库中找到完整的代码，如上所示。

import com.microsoft.semantickernel.Kernel;
import com.microsoft.semantickernel.agents.AgentInvokeOptions;
import com.microsoft.semantickernel.agents.AgentThread;
import com.microsoft.semantickernel.agents.chatcompletion.ChatCompletionAgent;
import com.microsoft.semantickernel.agents.chatcompletion.ChatHistoryAgentThread;
import com.microsoft.semantickernel.aiservices.openai.chatcompletion.OpenAIChatCompletion;
import com.microsoft.semantickernel.contextvariables.ContextVariableTypeConverter;
import com.microsoft.semantickernel.functionchoice.FunctionChoiceBehavior;
import com.microsoft.semantickernel.implementation.templateengine.tokenizer.DefaultPromptTemplate;
import com.microsoft.semantickernel.orchestration.InvocationContext;
import com.microsoft.semantickernel.orchestration.PromptExecutionSettings;
import com.microsoft.semantickernel.plugin.KernelPluginFactory;
import com.microsoft.semantickernel.samples.plugins.github.GitHubModel;
import com.microsoft.semantickernel.samples.plugins.github.GitHubPlugin;
import com.microsoft.semantickernel.semanticfunctions.KernelArguments;
import com.microsoft.semantickernel.semanticfunctions.PromptTemplateConfig;
import com.microsoft.semantickernel.services.chatcompletion.AuthorRole;
import com.microsoft.semantickernel.services.chatcompletion.ChatCompletionService;
import com.microsoft.semantickernel.services.chatcompletion.ChatMessageContent;
import com.azure.ai.openai.OpenAIAsyncClient;
import com.azure.ai.openai.OpenAIClientBuilder;
import com.azure.core.credential.AzureKeyCredential;

import java.time.OffsetDateTime;
import java.util.Scanner;

public class CompletionAgent {
    // Azure OpenAI
    private static final String AZURE_OPENAI_API_KEY = System.getenv("AZURE_OPENAI_API_KEY");
    private static final String AZURE_OPENAI_ENDPOINT = System.getenv("AZURE_OPENAI_ENDPOINT");
    private static final String AZURE_CHAT_MODEL_DEPLOYMENT = System.getenv().getOrDefault("AZURE_CHAT_MODEL_DEPLOYMENT", "gpt-4o");

    // GitHub Personal Access Token
    private static final String GITHUB_PAT = System.getenv("GITHUB_PAT");

    public static void main(String[] args) {
        System.out.println("======== ChatCompletion Agent ========");

        OpenAIAsyncClient client = new OpenAIClientBuilder()
                .credential(new AzureKeyCredential(AZURE_OPENAI_API_KEY))
                .endpoint(AZURE_OPENAI_ENDPOINT)
                .buildAsyncClient();

        var githubPlugin = new GitHubPlugin(GITHUB_PAT);

        ChatCompletionService chatCompletion = OpenAIChatCompletion.builder()
                .withModelId(AZURE_CHAT_MODEL_DEPLOYMENT)
                .withOpenAIAsyncClient(client)
                .build();

        Kernel kernel = Kernel.builder()
            .withAIService(ChatCompletionService.class, chatCompletion)
            .withPlugin(KernelPluginFactory.createFromObject(githubPlugin, "GitHubPlugin"))
            .build();

        InvocationContext invocationContext = InvocationContext.builder()
            .withFunctionChoiceBehavior(FunctionChoiceBehavior.auto(true))
            .withContextVariableConverter(new ContextVariableTypeConverter<>(
                    GitHubModel.Issue.class,
                    o -> (GitHubModel.Issue) o,
                    o -> o.toString(),
                    s -> null))
            .build();

        ChatCompletionAgent agent = ChatCompletionAgent.builder()
            .withName("SampleAssistantAgent")
            .withKernel(kernel)
            .withInvocationContext(invocationContext)
            .withTemplate(
                DefaultPromptTemplate.build(
                    PromptTemplateConfig.builder()
                        .withTemplate(
                            """
                            You are an agent designed to query and retrieve information from a single GitHub repository in a read-only manner.
                            You are also able to access the profile of the active user.

                            Use the current date and time to provide up-to-date details or time-sensitive responses.

                            The repository you are querying is a public repository with the following name: {{$repository}}

                            The current date and time is: {{$now}}.
                            """)
                        .build()))
            .withKernelArguments(
                KernelArguments.builder()
                    .withVariable("repository", "microsoft/semantic-kernel-java")
                    .withExecutionSettings(PromptExecutionSettings.builder()
                            .build())
                    .build())
            .build();

        AgentThread agentThread = new ChatHistoryAgentThread();
        boolean isComplete = false;

        Scanner scanner = new Scanner(System.in);

        while (!isComplete) {
            System.out.print("> ");

            String input = scanner.nextLine();
            if (input.isEmpty()) {
                continue;
            }

            if (input.equalsIgnoreCase("EXIT")) {
                isComplete = true;
                break;
            }

            var message = new ChatMessageContent<>(AuthorRole.USER, input);

            var options = AgentInvokeOptions.builder()
                .withKernelArguments(KernelArguments.builder()
                        .withVariable("now", OffsetDateTime.now())
                        .build())
                .build();

            for (var response : agent.invokeAsync(message, agentThread, options).block()) {
                System.out.println(response.getMessage());
                agentThread = response.getThread();
            }
        }
    }
}

后续步骤

使用指南：OpenAIAssistantAgent 代码解释器

通过

操作指南：ChatCompletionAgent

概述

入门

配置

编码

安装

代理定义

聊天循环

最终

后续步骤

其他资源

操作指南：`ChatCompletionAgent`