Skip to content

Latest commit

 

History

History
478 lines (396 loc) · 16.8 KB

README.md

File metadata and controls

478 lines (396 loc) · 16.8 KB

多模態整合

多模態應用在人工智慧中越來越重要，能夠實現更豐富的互動和更複雜的任務。Model Context Protocol (MCP) 提供了一個框架，用於構建能處理各種資料類型（如文字、圖片和音訊）的多模態應用。

MCP 不僅支援基於文字的互動，還具備多模態功能，允許模型處理圖片、音訊及其他資料類型。

介紹

在本課程中，你將學習如何建立多模態應用。

學習目標

完成本課程後，你將能夠：

  • 理解多模態的選擇
  • 實作多模態應用程式

多模態支援的架構

多模態 MCP 實作通常包含：

  • 特定模態解析器：將不同媒體類型轉換成模型可處理格式的元件。
  • 特定模態工具：專門處理特定模態（如影像分析、音訊處理）的工具。
  • 統一上下文管理：維持跨模態上下文的系統。
  • 回應生成：能產生包含多種模態的回應能力。

多模態範例：影像分析

以下範例將示範如何分析影像並擷取資訊。

C# 實作

using ModelContextProtocol.SDK.Server;
using ModelContextProtocol.SDK.Server.Tools;
using ModelContextProtocol.SDK.Server.Content;
using System.Text.Json;
using System.IO;
using System.Threading.Tasks;
using System.Collections.Generic;

namespace MultiModalMcpExample
{
    // Tool for image analysis
    public class ImageAnalysisTool : ITool
    {
        private readonly IImageAnalysisService _imageService;
        
        public ImageAnalysisTool(IImageAnalysisService imageService)
        {
            _imageService = imageService;
        }
        
        public string Name => "imageAnalysis";
        public string Description => "Analyzes image content and extracts information";
          public ToolDefinition GetDefinition()
        {
            return new ToolDefinition
            {
                Name = Name,
                Description = Description,
                Parameters = new Dictionary<string, ParameterDefinition>
                {
                    ["imageUrl"] = new ParameterDefinition
                    {
                        Type = ParameterType.String,
                        Description = "URL to the image to analyze" 
                    },
                    ["analysisType"] = new ParameterDefinition
                    {
                        Type = ParameterType.String,
                        Description = "Type of analysis to perform",
                        Enum = new[] { "general", "objects", "text", "faces" },
                        Default = "general"
                    }
                },
                Required = new[] { "imageUrl" }
            };
        }
        
        public async Task<ToolResponse> ExecuteAsync(IDictionary<string, object> parameters)
        {
            // Extract parameters
            string imageUrl = parameters["imageUrl"].ToString();
            string analysisType = parameters.ContainsKey("analysisType") 
                ? parameters["analysisType"].ToString() 
                : "general";
              // Download or access the image
            byte[] imageData = await DownloadImageAsync(imageUrl);
            
            // Analyze based on the requested analysis type
            var analysisResult = analysisType switch
            {
                "objects" => await _imageService.DetectObjectsAsync(imageData),                "text" => await _imageService.RecognizeTextAsync(imageData),
                "faces" => await _imageService.DetectFacesAsync(imageData),
                _ => await _imageService.AnalyzeGeneralAsync(imageData) // Default general analysis
            };
            
            // Return structured result as a ToolResponse
            // Format follows the MCP specification for content structure
            var content = new List<ContentItem>
            {
                new ContentItem
                {
                    Type = ContentType.Text,
                    Text = JsonSerializer.Serialize(analysisResult)
                }
            };
            
            return new ToolResponse
            {
                Content = content,
                IsError = false
            };
        }
        
        private async Task<byte[]> DownloadImageAsync(string url)
        {
            using var httpClient = new HttpClient();
            return await httpClient.GetByteArrayAsync(url);
        }
    }
    
    // Multi-modal MCP server with image and text processing
    public class MultiModalMcpServer
    {
        public static async Task Main(string[] args)
        {
            // Create an MCP server
            var server = new McpServer(
                name: "Multi-Modal MCP Server",
                version: "1.0.0"
            );
            
            // Configure server for multi-modal support
            var serverOptions = new McpServerOptions
            {
                MaxRequestSize = 10 * 1024 * 1024, // 10MB for larger payloads like images
                SupportedContentTypes = new[]
                {
                    "image/jpeg",
                    "image/png",
                    "text/plain",
                    "application/json"
                }
            };
            
            // Create image analysis service
            var imageService = new ComputerVisionService();
            
            // Register image analysis tools
            server.AddTool(new ImageAnalysisTool(imageService));
            
            // Register a text-to-image tool
            services.AddMcpTool<TextAnalysisTool>();
            services.AddMcpTool<ImageAnalysisTool>();
            services.AddMcpTool<DocumentGenerationTool>(); // Tool that can generate documents with text and images
        }
    }
}

在上述範例中，我們：

  • 建立了 ImageAnalysisTool，使用假設的 IImageAnalysisService 來分析影像。
  • 配置 MCP 伺服器以處理較大請求並支援影像內容類型。
  • 將影像分析工具註冊到伺服器。
  • 實作從 URL 下載影像並根據請求類型（物件、文字、臉部等）進行分析的方法。
  • 回傳符合 MCP 規範的結構化結果。

多模態範例：音訊處理

音訊處理是多模態應用中另一個常見的模態。以下範例示範如何實作一個能處理音訊檔案並回傳轉錄結果的音訊轉錄工具。

Java 實作

package com.example.mcp.multimodal;

import com.mcp.server.McpServer;
import com.mcp.tools.Tool;
import com.mcp.tools.ToolRequest;
import com.mcp.tools.ToolResponse;
import com.mcp.tools.ToolExecutionException;
import com.example.audio.AudioProcessor;

import java.util.Base64;
import java.util.HashMap;
import java.util.Map;

// Audio transcription tool
public class AudioTranscriptionTool implements Tool {
    private final AudioProcessor audioProcessor;
    
    public AudioTranscriptionTool(AudioProcessor audioProcessor) {
        this.audioProcessor = audioProcessor;
    }
    
    @Override
    public String getName() {
        return "audioTranscription";
    }
    
    @Override
    public String getDescription() {
        return "Transcribes speech from audio files to text";
    }
    
    @Override
    public Object getSchema() {
        Map<String, Object> schema = new HashMap<>();
        schema.put("type", "object");
        
        Map<String, Object> properties = new HashMap<>();
        
        Map<String, Object> audioUrl = new HashMap<>();
        audioUrl.put("type", "string");
        audioUrl.put("description", "URL to the audio file to transcribe");
        
        Map<String, Object> audioData = new HashMap<>();
        audioData.put("type", "string");
        audioData.put("description", "Base64-encoded audio data (alternative to URL)");
        
        Map<String, Object> language = new HashMap<>();
        language.put("type", "string");
        language.put("description", "Language code (e.g., 'en-US', 'es-ES')");
        language.put("default", "en-US");
        
        properties.put("audioUrl", audioUrl);
        properties.put("audioData", audioData);
        properties.put("language", language);
        
        schema.put("properties", properties);
        schema.put("required", Arrays.asList("audioUrl"));
        
        return schema;
    }
    
    @Override
    public ToolResponse execute(ToolRequest request) {
        try {
            byte[] audioData;
            String language = request.getParameters().has("language") ? 
                request.getParameters().get("language").asText() : "en-US";
                
            // Get audio either from URL or direct data
            if (request.getParameters().has("audioUrl")) {
                String audioUrl = request.getParameters().get("audioUrl").asText();
                audioData = downloadAudio(audioUrl);
            } else if (request.getParameters().has("audioData")) {
                String base64Audio = request.getParameters().get("audioData").asText();
                audioData = Base64.getDecoder().decode(base64Audio);
            } else {
                throw new ToolExecutionException("Either audioUrl or audioData must be provided");
            }
            
            // Process audio and transcribe
            Map<String, Object> transcriptionResult = audioProcessor.transcribe(audioData, language);
            
            // Return transcription result
            return new ToolResponse.Builder()
                .setResult(transcriptionResult)
                .build();
        } catch (Exception ex) {
            throw new ToolExecutionException("Audio transcription failed: " + ex.getMessage(), ex);
        }
    }
    
    private byte[] downloadAudio(String url) {
        // Implementation for downloading audio from URL
        // ...
        return new byte[0]; // Placeholder
    }
}

// Main application with audio and other modalities
public class MultiModalApplication {
    public static void main(String[] args) {
        // Configure services
        AudioProcessor audioProcessor = new AudioProcessor();
        ImageProcessor imageProcessor = new ImageProcessor();
        
        // Create and configure server
        McpServer server = new McpServer.Builder()
            .setName("Multi-Modal MCP Server")
            .setVersion("1.0.0")
            .setPort(5000)
            .setMaxRequestSize(20 * 1024 * 1024) // 20MB for audio/video content
            .build();
            
        // Register multi-modal tools
        server.registerTool(new AudioTranscriptionTool(audioProcessor));
        server.registerTool(new ImageAnalysisTool(imageProcessor));
        server.registerTool(new VideoProcessingTool());
        
        // Start server
        server.start();
        System.out.println("Multi-Modal MCP Server started on port 5000");
    }
}

在上述範例中，我們：

  • 建立了 AudioTranscriptionTool，能轉錄音訊檔案。
  • 定義工具的結構，接受 URL 或 base64 編碼的音訊資料。
  • 實作 execute 方法來處理音訊轉錄。
  • 配置 MCP 伺服器以處理多模態請求，包括音訊和影像處理。
  • 將音訊轉錄工具註冊到伺服器。
  • 實作從 URL 下載音訊檔案或解碼 base64 音訊資料的方法。
  • 使用 AudioProcessor 服務來執行實際的轉錄邏輯。
  • 啟動 MCP 伺服器以監聽請求。

多模態範例：多模態回應生成

Python 實作

from mcp_server import McpServer
from mcp_tools import Tool, ToolRequest, ToolResponse, ToolExecutionException
import base64
from PIL import Image
import io
import requests
import json
from typing import Dict, Any, List, Optional

# Image generation tool
class ImageGenerationTool(Tool):
    def get_name(self):
        return "imageGeneration"
        
    def get_description(self):
        return "Generates images based on text descriptions"
    
    def get_schema(self):
        return {
            "type": "object",
            "properties": {
                "prompt": {
                    "type": "string", 
                    "description": "Text description of the image to generate"
                },
                "style": {
                    "type": "string",
                    "enum": ["realistic", "artistic", "cartoon", "sketch"],
                    "default": "realistic"
                },
                "width": {
                    "type": "integer",
                    "default": 512
                },
                "height": {
                    "type": "integer",
                    "default": 512
                }
            },
            "required": ["prompt"]
        }
    
    async def execute_async(self, request: ToolRequest) -> ToolResponse:
        try:
            # Extract parameters
            prompt = request.parameters.get("prompt")
            style = request.parameters.get("style", "realistic")
            width = request.parameters.get("width", 512)
            height = request.parameters.get("height", 512)
            
            # Generate image using external service (example implementation)
            image_data = await self._generate_image(prompt, style, width, height)
            
            # Convert image to base64 for response
            buffered = io.BytesIO()
            image_data.save(buffered, format="PNG")
            img_str = base64.b64encode(buffered.getvalue()).decode()
            
            # Return result with both the image and metadata
            return ToolResponse(
                result={
                    "imageBase64": img_str,
                    "format": "image/png",
                    "width": width,
                    "height": height,
                    "generationPrompt": prompt,
                    "style": style
                }
            )
        except Exception as e:
            raise ToolExecutionException(f"Image generation failed: {str(e)}")
    
    async def _generate_image(self, prompt: str, style: str, width: int, height: int) -> Image.Image:
        """
        This would call an actual image generation API
        Simplified placeholder implementation
        """
        # Return a placeholder image or call actual image generation API
        # For this example, we'll create a simple colored image
        image = Image.new('RGB', (width, height), color=(73, 109, 137))
        return image

# Multi-modal response handler
class MultiModalResponseHandler:
    """Handler for creating responses that combine text, images, and other modalities"""
    
    def __init__(self, mcp_client):
        self.client = mcp_client
    
    async def create_multi_modal_response(self, 
                                         text_content: str, 
                                         generate_images: bool = False,
                                         image_prompts: Optional[List[str]] = None) -> Dict[str, Any]:
        """
        Creates a response that may include generated images alongside text
        """
        response = {
            "text": text_content,
            "images": []
        }
        
        # Generate images if requested
        if generate_images and image_prompts:
            for prompt in image_prompts:
                image_result = await self.client.execute_tool(
                    "imageGeneration",
                    {
                        "prompt": prompt,
                        "style": "realistic",
                        "width": 512,
                        "height": 512
                    }
                )
                
                response["images"].append({
                    "imageData": image_result.result["imageBase64"],
                    "format": image_result.result["format"],
                    "prompt": prompt
                })
        
        return response

# Main application
async def main():
    # Create server
    server = McpServer(
        name="Multi-Modal MCP Server",
        version="1.0.0",
        port=5000
    )
    
    # Register multi-modal tools
    server.register_tool(ImageGenerationTool())
    server.register_tool(AudioAnalysisTool())
    server.register_tool(VideoFrameExtractionTool())
    
    # Start server
    await server.start()
    print("Multi-Modal MCP Server running on port 5000")

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())

接下來的內容

免責聲明：
本文件係使用 AI 翻譯服務 Co-op Translator 進行翻譯。雖然我們致力於確保準確性，但請注意，自動翻譯可能包含錯誤或不準確之處。原始文件的母語版本應視為權威來源。對於重要資訊，建議採用專業人工翻譯。我們不對因使用本翻譯而產生的任何誤解或誤釋負責。