本文是基于 LLama 2是由Meta 开源的大语言模型,通过LocalAI 来集成LLama2 来演示Semantic kernel(简称SK) 和 本地大模型的集成示例。
SK 可以支持各种大模型,在官方示例中多是OpenAI 和 Azure OpenAI service 的GPT 3.5+。今天我们就来看一看如何把SK 和 本地部署的开源大模型集成起来。我们使用MIT协议的开源项目「LocalAI「:https://github.com/go-skynet/LocalAI。
LocalAI 是一个本地推理框架,提供了 RESTFul API,与 OpenAI API 规范兼容。它允许你在消费级硬件上本地或者在自有服务器上运行 LLM(和其他模型),支持与 ggml 格式兼容的多种模型家族。不需要 GPU。LocalAI 使用 C++ 绑定来优化速度。它基于用于音频转录的 llama.cpp、gpt4all、rwkv.cpp、ggml、whisper.cpp 和用于嵌入的 bert.cpp。
可参考官方 Getting Started 进行部署,通过LocalAI我们将本地部署的大模型转换为OpenAI的格式,通过SK 的OpenAI 的Connector 访问,这里需要做的是把openai的Endpoint 指向 LocalAI,这个我们可以通过一个自定义的HttpClient来完成这项工作,例如下面的这个示例:
internal class OpenAIHttpclientHandler : HttpClientHandler
{
private KernelSettings _kernelSettings;
public OpenAIHttpclientHandler(KernelSettings settings)
{
this._kernelSettings = settings;
}
protected override async Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken cancellationToken)
{
if (request.RequestUri.LocalPath == "/v1/chat/completions")
{
UriBuilder uriBuilder = new UriBuilder(request.RequestUri)
{
Scheme = this._kernelSettings.Scheme,
Host = this._kernelSettings.Host,
Port = this._kernelSettings.Port
};
request.RequestUri = uriBuilder.Uri;
}
return await base.SendAsync(request, cancellationToken);
}
}
上面我们做好了所有的准备工作,接下来就是要把所有的组件组装起来,让它们协同工作。因此打开Visual studio code 创建一个c# 项目sk-csharp-hello-world,其中Program.cs 内容如下:
using System.Reflection;
using config;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Logging;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;
using Microsoft.SemanticKernel.Connectors.OpenAI;
using Microsoft.SemanticKernel.PromptTemplates.Handlebars;
using Plugins;
var kernelSettings = KernelSettings.LoadSettings();
var handler = new OpenAIHttpclientHandler(kernelSettings);
IKernelBuilder builder = Kernel.CreateBuilder();
builder.Services.AddLogging(c => c.SetMinimumLevel(LogLevel.Information).AddDebug());
builder.AddChatCompletionService(kernelSettings,handler);
builder.Plugins.AddFromType<LightPlugin>();
Kernel kernel = builder.Build();
// Load prompt from resource
using StreamReader reader = new(Assembly.GetExecutingAssembly().GetManifestResourceStream("prompts.Chat.yaml")!);
KernelFunction prompt = kernel.CreateFunctionFromPromptYaml(
reader.ReadToEnd(),
promptTemplateFactory: new HandlebarsPromptTemplateFactory()
);
// Create the chat history
ChatHistory chatMessages = [];
// Loop till we are cancelled
while (true)
{
// Get user input
System.Console.Write("User > ");
chatMessages.AddUserMessage(Console.ReadLine()!);
// Get the chat completions
OpenAIPromptExecutionSettings openAIPromptExecutionSettings = new()
{
};
var result = kernel.InvokeStreamingAsync<StreamingChatMessageContent>(
prompt,
arguments: new KernelArguments(openAIPromptExecutionSettings) {
{ "messages", chatMessages }
});
// Print the chat completions
ChatMessageContent? chatMessageContent = null;
await foreach (var content in result)
{
System.Console.Write(content);
if (chatMessageContent == null)
{
System.Console.Write("Assistant > ");
chatMessageContent = new ChatMessageContent(
content.Role ?? AuthorRole.Assistant,
content.ModelId!,
content.Content!,
content.InnerContent,
content.Encoding,
content.Metadata);
}
else
{
chatMessageContent.Content += content;
}
}
System.Console.WriteLine();
chatMessages.Add(chatMessageContent!);
}
首先,我们做的第一件事是导入一堆必要的命名空间,使一切正常(第 1 行到第 9 行)。
然后,我们创建一个内核构建器的实例(通过模式,而不是因为它是构造函数),这将有助于塑造我们的内核。
IKernelBuilder builder = Kernel.CreateBuilder();
你需要知道每时每刻都在发生什么吗?答案是肯定的!让我们在内核中添加一个日志。我们在第14行添加了日志的支持。
我们想使用Azure,OpenAI中使用Microsoft的AI模型,以及我们LocalAI 集成的本地大模型,我们可以将它们包含在我们的内核中。正如我们在15行看到的那样:
internal static class ServiceCollectionExtensions
{
/// <summary>
/// Adds a chat completion service to the list. It can be either an OpenAI or Azure OpenAI backend service.
/// </summary>
/// <param name="kernelBuilder"></param>
/// <param name="kernelSettings"></param>
/// <exception cref="ArgumentException"></exception>
internal static IKernelBuilder AddChatCompletionService(this IKernelBuilder kernelBuilder, KernelSettings kernelSettings, HttpClientHandler handler)
{
switch (kernelSettings.ServiceType.ToUpperInvariant())
{
case ServiceTypes.AzureOpenAI:
kernelBuilder = kernelBuilder.AddAzureOpenAIChatCompletion(kernelSettings.DeploymentId, endpoint: kernelSettings.Endpoint, apiKey: kernelSettings.ApiKey, serviceId: kernelSettings.ServiceId, kernelSettings.ModelId);
break;
case ServiceTypes.OpenAI:
kernelBuilder = kernelBuilder.AddOpenAIChatCompletion(modelId: kernelSettings.ModelId, apiKey: kernelSettings.ApiKey, orgId: kernelSettings.OrgId, serviceId: kernelSettings.ServiceId);
break;
case ServiceTypes.HunyuanAI:
kernelBuilder = kernelBuilder.AddOpenAIChatCompletion(modelId: kernelSettings.ModelId, apiKey: kernelSettings.ApiKey, httpClient: new HttpClient(handler));
break;
case ServiceTypes.LocalAI:
kernelBuilder = kernelBuilder.AddOpenAIChatCompletion(modelId: kernelSettings.ModelId, apiKey: kernelSettings.ApiKey, httpClient: new HttpClient(handler));
break;
default:
throw new ArgumentException($"Invalid service type value: {kernelSettings.ServiceType}");
}
return kernelBuilder;
}
}
接下来开启一个聊天循环,使用SK的流式传输 InvokeStreamingAsync,如第42行到46行代码所示,运行起来就可以体验下列的效果:
本文示例源代码: https://github.com/geffzhang/sk-csharp-hello-world
参考文章:
Docker部署LocalAI 实现本地私有化 文本转语音(TTS) 语音转文本 GPT功能 | Mr.Pu 个站博客 (putianhui.cn)
LocalAI 自托管、社区驱动的本地 OpenAI API 兼容替代方案