实现阿里云模型服务灵积 DashScope 的 Semantic Kernel Connector

Semantic Kernel 内置的
IChatCompletionService
实现只支持 OpenAI 与 Azure OpenAI，而我却打算结合 DashScope(阿里云模型服务灵积) 学习 Semantic Kernel。

于是决定自己动手实现一个支持 DashScope 的 Semantic Kernel Connector —— DashScopeChatCompletionService，实现的过程也是学习 Semantic Kernel 源码的过程，
而且借助
Sdcb.DashScope
，实现变得更容易了，详见前一篇博文
借助 .NET 开源库 Sdcb.DashScope 调用阿里云灵积通义千问 API

这里只实现用于调用 chat completion 服务的 connector，所以只需实现
IChatCompletionService
接口，该接口继承了
IAIService
接口，一共需要实现2个方法+1个属性。

public sealed class DashScopeChatCompletionService : IChatCompletionService
{
    public IReadOnlyDictionary<string, object?> Attributes { get; }

    public Task<IReadOnlyList<ChatMessageContent>> GetChatMessageContentsAsync(ChatHistory chatHistory, PromptExecutionSettings? executionSettings = null, Kernel? kernel = null, CancellationToken cancellationToken = default)
    {
        throw new NotImplementedException();
    }

    public IAsyncEnumerable<StreamingChatMessageContent> GetStreamingChatMessageContentsAsync(ChatHistory chatHistory, PromptExecutionSettings? executionSettings = null, Kernel? kernel = null, CancellationToken cancellationToken = default)
    {
        throw new NotImplementedException();
    }
}

先实现
GetChatMessageContentsAsync
方法，调用
Kernel.InvokePromptAsync
方法时会用到这个方法。

实现起来比较简单，就是转手买卖：

把 Semantic Kernel 的
ChatHistory
转换为 Sdcb.DashScope 的
IReadOnlyList<ChatMessage>
把 Semantic Kernel 的
PromptExecutionSettings
转换为 Sdcb.DashScope 的
ChatParameters
把 Sdcb.DashScope 的
ResponseWrapper<ChatOutput, ChatTokenUsage>
转换为 Semantic Kernel 的
IReadOnlyList<ChatMessageContent>

实现代码如下：

public async Task<IReadOnlyList<ChatMessageContent>> GetChatMessageContentsAsync(ChatHistory chatHistory, PromptExecutionSettings? executionSettings = null, Kernel? kernel = null, CancellationToken cancellationToken = default)
{
    var chatMessages = chatHistory
        .Where(x => !string.IsNullOrEmpty(x.Content))
        .Select(x => new ChatMessage(x.Role.ToString(), x.Content!)).
        ToList();

    ChatParameters? chatParameters = null;
    if (executionSettings?.ExtensionData?.Count > 0)
    {
        var json = JsonSerializer.Serialize(executionSettings.ExtensionData);
        chatParameters = JsonSerializer.Deserialize<ChatParameters>(
            json,
            new JsonSerializerOptions { NumberHandling = JsonNumberHandling.AllowReadingFromString });
    }

    var response = await _dashScopeClient.TextGeneration.Chat(_modelId, chatMessages, chatParameters, cancellationToken);

    return [new ChatMessageContent(new AuthorRole(chatMessages.First().Role), response.Output.Text)];
}

接下来实现
GetStreamingChatMessageContentsAsync
，调用
Kernel.InvokePromptStreamingAsync
时会用到它，同样也是转手买卖。

ChatHistory
与
PromptExecutionSettings
参数的转换与
GetChatMessageContentsAsync
一样，所以引入2个扩展方法
ChatHistory.ToChatMessages
与
PromptExecutionSettings.ToChatParameters
减少重复代码，另外需要将
ChatParameters.IncrementalOutput
设置为
true
。

不同之处是返回值类型，需要将 Sdcb.DashScope 的
IAsyncEnumerable<ResponseWrapper<ChatOutput, ChatTokenUsage>>
转换为
IAsyncEnumerable<StreamingChatMessageContent>

实现代码如下：

public async IAsyncEnumerable<StreamingChatMessageContent> GetStreamingChatMessageContentsAsync(
    ChatHistory chatHistory,
    PromptExecutionSettings? executionSettings = null,
    Kernel? kernel = null,
    [EnumeratorCancellation] CancellationToken cancellationToken = default)
{
    var chatMessages = chatHistory.ToChatMessages();
    var chatParameters = executionSettings?.ToChatParameters() ?? new ChatParameters();
    chatParameters.IncrementalOutput = true;

    var responses = _dashScopeClient.TextGeneration.ChatStreamed(_modelId, chatMessages, chatParameters, cancellationToken);

    await foreach (var response in responses)
    {
        yield return new StreamingChatMessageContent(new AuthorRole(chatMessages[0].Role), response.Output.Text);
    }
}

到这里2个方法就实现好了，还剩下很容易实现的1个属性，轻松搞定

public sealed class DashScopeChatCompletionService : IChatCompletionService
{
    private readonly DashScopeClient _dashScopeClient;
    private readonly string _modelId;
    private readonly Dictionary<string, object?> _attribues = [];

    public DashScopeChatCompletionService(
        IOptions<DashScopeClientOptions> options,
        HttpClient httpClient)
    {
        _dashScopeClient = new(options.Value.ApiKey, httpClient);
        _modelId = options.Value.ModelId;
        _attribues.Add(AIServiceExtensions.ModelIdKey, _modelId);
    }

    public IReadOnlyDictionary<string, object?> Attributes => _attribues;
}

到此，DashScopeChatCompletionService 的实现就完成了。

接下来，实现一个扩展方法，将 DashScopeChatCompletionService 注册到依赖注入容器

public static class DashScopeServiceCollectionExtensions
{
    public static IKernelBuilder AddDashScopeChatCompletion(
        this IKernelBuilder builder,
        string? serviceId = null,
        Action<HttpClient>? configureClient = null,
        string configSectionPath = "dashscope")
    {
        Func<IServiceProvider, object?, DashScopeChatCompletionService> factory = (serviceProvider, _) =>
            serviceProvider.GetRequiredService<DashScopeChatCompletionService>();

        if (configureClient == null)
        {
            builder.Services.AddHttpClient<DashScopeChatCompletionService>();
        }
        else
        {
            builder.Services.AddHttpClient<DashScopeChatCompletionService>(configureClient);
        }

        builder.Services.AddOptions<DashScopeClientOptions>().BindConfiguration(configSectionPath);
        builder.Services.AddKeyedSingleton<IChatCompletionService>(serviceId, factory);
        return builder;
    }
}

为了方便通过配置文件配置 ModelId 与 ApiKey，引入了
DashScopeClientOptions

public class DashScopeClientOptions : IOptions<DashScopeClientOptions>
{
    public string ModelId { get; set; } = string.Empty;

    public string ApiKey { get; set; } = string.Empty;

    public DashScopeClientOptions Value => this;
}

最后就是写测试代码验证实现是否成功，为了减少代码块的长度，下面的代码片段只列出其中一个测试用例

public class DashScopeChatCompletionTests
{
    [Fact]
    public async Task ChatCompletion_InvokePromptAsync_WorksCorrectly()
    {
        // Arrange
        var builder = Kernel.CreateBuilder();
        builder.Services.AddSingleton(GetConfiguration());
        builder.AddDashScopeChatCompletion();
        var kernel = builder.Build();

        var prompt = @"<message role=""user"">博客园是什么网站</message>";
        PromptExecutionSettings settings = new()
        {
            ExtensionData = new Dictionary<string, object>()
            {
                { "temperature", "0.8" }
            }
        };
        KernelArguments kernelArguments = new(settings);

        // Act
        var result = await kernel.InvokePromptAsync(prompt, kernelArguments);

        // Assert
        Assert.Contains("博客园", result.ToString());
        Trace.WriteLine(result.ToString());
    }

    private static IConfiguration GetConfiguration()
    {
        return new ConfigurationBuilder()
            .SetBasePath(Directory.GetCurrentDirectory())
            .AddJsonFile("appsettings.json")
            .AddUserSecrets<DashScopeChatCompletionTests>()
            .Build();
    }
}

最后的最后就是运行测试，在 appsettings.json 中添加模型Id

{
  "dashscope": {
    "modelId": "qwen-max"
  }
}

注：
qwen-max
是通义千问千亿级大模型

通过 user-secrets 添加 api key

dotnet user-secrets set "dashscope:apiKey" "sk-xxx"

dotnet test
命令运行测试

A total of 1 test files matched the specified pattern.
博客园是一个专注于提供信息技术(IT)领域知识分享和技术交流的中文博客平台，创建于2004年。博客园主要由软件开发人员、系统管理员以及对IT技术有深厚兴趣的人群使用，用户可以在该网站上撰写和发布自己的博客文章，内容涵盖编程、软件开发、云计算、人工智能等多个领域。同时，博客园也提供了丰富的技术文档、教程资源和社区互动功能，旨在促进IT专业人士之间的交流与学习。

Passed!  - Failed:     0, Passed:     1, Skipped:     0, Total:     1, Duration: < 1 ms - SemanticKernel.DashScope.IntegrationTest.dll (net8.0)

测试通过！连接 DashScope 的 Semantic Kernel Connector 初步实现完成。

完整实现代码放在 github 上，详见
https://github.com/cnblogs/semantic-kernel-dashscope/tree/v0.1.0

实现阿里云模型服务灵积 DashScope 的 Semantic Kernel Connector

添加新评论

最新文章

最近回复

分类

归档

其它