Semantic Kernel人工智能：1、从DeepSeek API调用到Semantic Kernel集成：
引言：AI期间下的谈天机器人开发范式演进在生成式AI技术发作的当下，基于大语言模子（LLM）的谈天机器人开发已形成尺度化技术链路。本文将结合DeepSeek API与微软Semantic Kernel框架，以C#语言实战演示从底子API调用到高级框架集成的完整开发流程。
环境准备与底子配置
[*].NET 9 SDK
[*]Visual Studio 2022或VSCode
[*]DeepSeek API密钥官网申请
DeepSeek API底子调用
DeepSeek API的Endpoint地址为：https://api.deepseek.com/chat/completions，相关文档可查看官方文档
[*]单轮对话实现
代码示例
public async Task<ResponseBody> GetChatMessageContentsAsync(CancellationToken cancellationToken = new CancellationToken())
{
var client = new HttpClient();
var request = new HttpRequestMessage(HttpMethod.Post, _builder.Endpoint);
request.Headers.Add("Accept", "application/json");
request.Headers.Add("Authorization", $"Bearer {_builder.ApiKey}");
_body.Stream = false;
var content = new StringContent(_body.SerializeObject(), null, "application/json");
request.Content = content;
var response = await client.SendAsync(request, cancellationToken);
var responseBody = await response.Content.ReadAsStringAsync(cancellationToken);
return JsonConvert.DeserializeObject<ResponseBody>(responseBody) ?? new ResponseBody();
}
[*]流式响应处理
代码示例
public async IAsyncEnumerable<ResponseBody> GetStreamingChatMessageContentsAsync( CancellationToken cancellationToken = new CancellationToken())
{
var client = new HttpClient();
var request = new HttpRequestMessage(HttpMethod.Post, _builder.Endpoint);
request.Headers.Add("Accept", "application/json");
request.Headers.Add("Authorization", $"Bearer {_builder.ApiKey}");
_body.Stream = true;
var content = new StringContent(_body.SerializeObject(), null, "application/json");
request.Content = content;
var response = await client.SendAsync(request, cancellationToken);
var stream = await response.Content.ReadAsStreamAsync(cancellationToken);
var reader = new StreamReader(stream);
while (!reader.EndOfStream)
{
var line = await reader.ReadLineAsync(cancellationToken);
if (string.IsNullOrEmpty(line) || line.StartsWith(":")) continue;
if (line.StartsWith("data: "))
{
var jsonData = line["data: ".Length ..];
if (jsonData == "") break;
yield return JsonConvert.DeserializeObject<ResponseBody>(jsonData) ?? new ResponseBody();
}
}
}Semantic Kernel框架集成
Semantic Kernel是一种轻型开源开发工具包，可用于轻松生成 AI 代理并将最新的 AI 模子集成到 C#、Python 或 Java 代码库中。 它充当一个高效的中心件，可实现企业级解决方案的快速交付。
DeepSeek API与Semantic Kernel框架集成，可快速实现基于大语言模子的谈天机器人开发。由于DeepSeek API与OpenAI API的兼容性，因此DeepSeek API与Semantic Kernel框架的集成非常简单。只需使用OpenAI的连接器，即可快速实现DeepSeek API与Semantic Kernel框架的集成。
[*]NuGet包安装
dotnet add package Microsoft.SemanticKernel
[*]Semantic Kernel初始化
var openAIClientCredential = new ApiKeyCredential(apiKey);
var openAIClientOption = new OpenAIClientOptions
{
Endpoint = new Uri("https://api.deepseek.com"),
};
var builder = Kernel.CreateBuilder()
.AddOpenAIChatCompletion(modelId, new OpenAIClient(openAIClientCredential, openAIClientOption));
var kernel = builder.Build();
[*]谈天机器人开发
var chatCompletionService = kernel.GetRequiredService();Console.WriteLine("
免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。
页:
[1]