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。文章来源:https://www.toymoban.com/news/detail-825316.html
完整实现代码放在 github 上,详见 https://github.com/cnblogs/semantic-kernel-dashscope/tree/v0.1.0文章来源地址https://www.toymoban.com/news/detail-825316.html
到了这里,关于实现阿里云模型服务灵积 DashScope 的 Semantic Kernel Connector的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!