语义工具路由库

dotnet add package ElBruno.ModelContextProtocol.MCPToolRouter

// Mode 1: Embeddings only — fast, no LLM needed
var results = await ToolRouter.SearchAsync(prompt, tools, topK: 3);

// Mode 2: LLM-assisted — best for verbose/complex prompts
var results = await ToolRouter.SearchUsingLLMAsync(prompt, tools, topK: 5);

┌─────────────────────────────────────────────────────────────────┐
│  Mode 1: Embeddings Filter (Fast, Simple)                       │
│                                                                  │
│  User Prompt ──► Embed ──► Cosine Similarity ──► Top-K Tools    │
│                                                                  │
│  "What's the weather?" → [0.89 get_weather, 0.45 send_email]   │
└─────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────┐
│  Mode 2: Hybrid Search (Precise, Complex)                        │
│                                                                  │
│  User Prompt ──┬──► Embed (baseline) ────────────────┐           │
│                └──► LLM Distill ──► Split Phrases ──►├─► Merge   │
│                     ──► Embed Each ──────────────────┘  ──► TopK │
│                                                                  │
│  "Hey, I was thinking about my trip and need to know if it's    │
│   going to rain in Tokyo..." → "check weather Tokyo,            │
│   set reminder" → search each + merge with baseline             │
└─────────────────────────────────────────────────────────────────┘

using ElBruno.ModelContextProtocol.MCPToolRouter;
using ModelContextProtocol.Protocol;

var tools = new[]
{
    new Tool { Name = "get_weather", Description = "Get current weather for a location" },
    new Tool { Name = "send_email", Description = "Send an email message to a recipient" },
    new Tool { Name = "search_files", Description = "Search for files by name or content" },
    new Tool { Name = "calculate", Description = "Perform mathematical calculations" },
    new Tool { Name = "translate_text", Description = "Translate text between languages" }
};

// One-liner: route and get results immediately
var results = await ToolRouter.SearchAsync("What's the temperature outside?", tools, topK: 3);

foreach (var r in results)
    Console.WriteLine($"  {r.Tool.Name}: {r.Score:F3}");
// Output:
//   get_weather: 0.847
//   calculate: 0.312
//   translate_text: 0.201

// Build once, reuse many times (e.g., in a web API or agent loop)
await using var index = await ToolIndex.CreateAsync(tools);

var results = await index.SearchAsync("What's the temperature outside?", topK: 3);

using ElBruno.ModelContextProtocol.MCPToolRouter;
using ModelContextProtocol.Protocol;

var tools = new Tool[] 
{
    new Tool { Name = "get_weather", Description = "Get current weather for a location" },
    new Tool { Name = "send_email", Description = "Send an email message to a recipient" },
    new Tool { Name = "search_files", Description = "Search for files by name or content" },
    new Tool { Name = "calculate", Description = "Perform mathematical calculations" },
    new Tool { Name = "translate_text", Description = "Translate text between languages" }
};

// One-liner: the local LLM is downloaded and managed automatically
var results = await ToolRouter.SearchUsingLLMAsync(
    "Hey, I was thinking about my trip next week and I need to know " +
    "if it's going to rain in Tokyo. Also remind me to call the dentist.",
    tools, topK: 5);

// The LLM distills this to action phrases: "check weather Tokyo, set reminder call dentist"
// Then each phrase + the original prompt are searched and results merged
foreach (var r in results)
    Console.WriteLine($"  {r.Tool.Name}: {r.Score:F3}");
// Output:
//   get_weather: 0.912
//   calculate: 0.287
//   translate_text: 0.156

// Pass your own IChatClient for prompt distillation
var results = await ToolRouter.SearchUsingLLMAsync(
    "Complex prompt here...",
    tools, chatClient, topK: 5);

await using var router = await ToolRouter.CreateAsync(tools, chatClient);
var results = await router.RouteAsync("Complex prompt here...", topK: 5);

using var client = await LocalChatClient.CreateAsync();
var info = client.ModelInfo;
Console.WriteLine($"Model: {info?.ModelName}");
Console.WriteLine($"  Effective Max Sequence Length: {info?.MaxSequenceLength} tokens");
Console.WriteLine($"  Config Max Sequence Length: {info?.ConfigMaxSequenceLength} tokens");

using Azure;
using Azure.AI.OpenAI;
using OpenAI.Chat;

// Create Azure OpenAI ChatClient
var chatClient = new AzureOpenAIClient(
    new Uri("https://your-resource.openai.azure.com/"),
    new AzureKeyCredential("your-api-key"))
    .GetChatClient("gpt-5-mini");

// Route to relevant tools only (using Mode 1 as example)
var relevant = await ToolRouter.SearchAsync(userPrompt, allTools, topK: 3);

// Add only filtered tools to the chat call — saving tokens!
var chatOptions = new ChatCompletionOptions();
foreach (var r in relevant)
    chatOptions.Tools.Add(ChatTool.CreateFunctionTool(r.Tool.Name, r.Tool.Description ?? ""));

var response = await chatClient.CompleteChatAsync([new UserChatMessage(userPrompt)], chatOptions);

var options = new ToolIndexOptions
{
    QueryCacheSize = 20,                          // LRU cache for repeated queries (0 = disabled)
    EmbeddingTextTemplate = "{Name}: {Description}" // Customize how tools are embedded
};

await using var index = await ToolIndex.CreateAsync(tools, options);

// Save
using var file = File.Create("tools.bin");
await index.SaveAsync(file);

// Load (instant warm-start — no re-embedding)
using var stream = File.OpenRead("tools.bin");
await using var loaded = await ToolIndex.LoadAsync(stream);

await index.AddToolsAsync(new[] { new Tool { Name = "new_tool", Description = "..." } });
index.RemoveTools(new[] { "obsolete_tool" });

builder.Services.AddMcpToolRouter(tools, opts =>
{
    opts.QueryCacheSize = 20;
});

// Inject IToolIndex anywhere
app.MapGet("/search", async (IToolIndex index, string query)
    => await index.SearchAsync(query, topK: 3));

IEmbeddingGenerator<string, Embedding<float>> myGenerator = /* your provider */;
await using var index = await ToolIndex.CreateAsync(tools, myGenerator, options);

var options = new ToolIndexOptions { QueryCacheSize = 20 };
await using var index = await ToolIndex.CreateAsync(tools, options);

var result1 = await index.SearchAsync("weather in Tokyo");     // ~10ms: embedding generated
var result2 = await index.SearchAsync("weather in Tokyo");     // ~0ms: cache hit

var options = new ToolIndexOptions { EmbeddingModelCacheDirectory = "/secure/models" };
await using var index = await ToolIndex.CreateAsync(tools, options);

var options = new ToolRouterOptions { MaxPromptLength = 2000 };

dotnet user-secrets set "AzureOpenAI:Endpoint" "https://your-resource.openai.azure.com/" --id elbruno-mcp-samples
dotnet user-secrets set "AzureOpenAI:ApiKey" "your-api-key" --id elbruno-mcp-samples
dotnet user-secrets set "AzureOpenAI:DeploymentName" "gpt-5-mini" --id elbruno-mcp-samples

dotnet restore ElBruno.ModelContextProtocol.slnx
dotnet build ElBruno.ModelContextProtocol.slnx
dotnet test ElBruno.ModelContextProtocol.slnx