LmDotnet工具

Dependency Injection

// In Program.cs or Startup.cs
services.AddLmDotnet(configuration);
services.ValidateOpenRouterUsageConfiguration(configuration);

Installation

dotnet add package AchieveAi.LmDotnetTools.LmCore
dotnet add package AchieveAi.LmDotnetTools.OpenAIProvider
dotnet add package AchieveAi.LmDotnetTools.AnthropicProvider

Quick Setup

```bash

Quick Start

Basic Usage

using AchieveAi.LmDotnetTools.LmCore.Agents;
using AchieveAi.LmDotnetTools.LmCore.Messages;
using AchieveAi.LmDotnetTools.OpenAIProvider.Agents;

// Create an agent
var agent = new OpenClientAgent("MyAgent", openClient);

// Send a message
var messages = new[] { new TextMessage { Role = Role.User, Text = "Hello!" } };
var response = await agent.GenerateReplyAsync(messages);

OpenRouter Usage Tracking

LmDotnet includes comprehensive usage tracking for OpenRouter, providing automatic token and cost monitoring.

Environment variables

export ENABLE_USAGE_MIDDLEWARE=true export OPENROUTER_API_KEY=sk-or-your-api-key-here export USAGE_CACHE_TTL_SEC=300

// Access usage information from UsageMessage var usageMessage = messages.OfType<UsageMessage>().LastOrDefault(); if (usageMessage != null) { var usage = usageMessage.Usage; Console.WriteLine($"Tokens: {usage.TotalTokens}, Cost: ${usage.TotalCost:F4}"); } ```

Configuration

Environment Variables

LmDotnet - Large Language Model SDK for .NET

LmDotnet is a comprehensive .NET SDK for working with large language models (LLMs) from multiple providers including OpenAI, Anthropic, and OpenRouter.

Middleware Pipeline

// Custom middleware for logging, caching, etc.
public class CustomMiddleware : IStreamingMiddleware
{
    public async Task<IAsyncEnumerable<IMessage>> InvokeStreamingAsync(
        MiddlewareContext context, IStreamingAgent agent, CancellationToken cancellationToken)
    {
        // Pre-processing
        yield return await agent.GenerateReplyStreamingAsync(context.Messages, context.Options, cancellationToken);
        // Post-processing
    }
}