使用说明
代理MCP天气情报系统🌤️🤖
全面 代理模型上下文协议(MCP) 通过精心编排的多代理架构提供智能天气服务的系统。专为可扩展的代理应用程序而构建,具有 完全支持Docker 和 流线型Web UI 便于部署和交互。
🌟 主要特点
🌐 web界面
- 流媒体聊天界面:类似ChatGPT的界面位于
http://localhost:8501 - 实时交互:与气象机构直接沟通
- 可视化仪表板:系统健康监测和代理状态
- 移动响应:适用于台式机、平板电脑和移动设备
🤖 多智能体协调
- 智能警报代理:主动的天气监测和个性化警报
- 气象情报员:多源数据聚合和分析
- 旅行社:基于位置的天气规划和建议
- 代理商协调中心:所有气象代理的集中编排
🐳 Docker第一架构
- 完全集装箱化:天气服务器+Ollama LLM+Streamlit UI+设置自动化
- 多服务编排:生产就绪的微服务架构
- 生产就绪:通过安全最佳实践和健康检查优化了Dockerfile
- 一个命令部署:通过以下方式启动整个系统
./start-docker.sh
🔧 模块化架构
- 服务器注册表:MCP服务器的自动发现和管理
- 代理协调器:与本地LLM进行智能工作流协调
- 多代理支持:专门气象机构的可扩展框架
- 健康监测:使用全面的健康端点进行实时状态跟踪
- API-初步设计:带有交互式文档的RESTful API
/docs
🤖 高级代理能力
- 自然语言处理:通过LLM集成了解复杂的天气查询
- 智能任务路由:自动将查询委托给专门的代理
- 多地点协调:同时比较和分析多个城市的天气
- 主动警报系统:具有个性化通知和阈值的智能监控
- 本地LLM集成:Ollama驱动的推理和决策
- 上下文感知响应:维护对话历史和学习
🌐 综合气象服务
- 实时天气:通过多个API了解全球任何城市的当前状况
- 高级预测:使用美国国家气象局API进行详细预测
- 智能报警系统:天气警报、紧急通知和自定义阈值
- 多源情报:来自weather.gov、wttr.in和其他来源的数据融合
- 旅行计划:基于位置的天气分析,用于行程规划和建议
🏗️ 系统架构
┌─────────────────────────────────────────────────────────────────────────────┐
│ Docker Network: weather-mcp-network │
│ │
│ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ ┌─────────┐ │
│ │ Streamlit UI │ │ Weather MCP │ │ Ollama LLM │ │ Setup │ │
│ │ :8501 │ │ Server :8000 │ │ Server :11434 │ │ Agent │ │
│ │ ┌─────────────┐ │ │ ┌─────────────┐ │ │ ┌─────────────┐ │ │ (Init) │ │
│ │ │ Chat UI │ │ │ │ MCP API │ │ │ │ Models: │ │ │ ┌─────┐ │ │
│ │ │ Dashboard │◄┼──┼─┤ Health │◄┼──┼─┤ - llama3 │ │ │ │Auto │ │ │
│ │ │ Monitoring│ │ │ │ Agent Hub │ │ │ │ - phi3 │ │ │ │Setup│ │ │
│ │ └─────────────┘ │ │ └─────────────┘ │ │ └─────────────┘ │ │ └─────┘ │ │
│ └─────────────────┘ └─────────────────┘ └─────────────────┘ └─────────┘ │
│ │ │ │ │ │
└───────────┼─────────────────────┼─────────────────────┼──────────────┼──────┘
│ │ │ │
│ │ │ │
┌───────────▼─────────────────────▼─────────────────────▼──────────────▼──────┐
│ Host System │
│ 🌐 http://localhost:8501 (Streamlit Chat Interface) │
│ 🔧 http://localhost:8000 (Weather API + Agent Coordination) │
│ 🤖 http://localhost:11434 (Ollama LLM Engine) │
│ 📚 http://localhost:8000/docs (Interactive API Documentation) │
└───────────────────────────────────────────────────────────────────────────────┘
代理协调流程
User Query ─► Streamlit UI ─► Agent Coordination Hub ─► Specialized Agents
│ │ │
│ │ ┌─────────────┐
│ └──────────────┤Smart Alert │
│ │Agent │
│ ┌───────┤Weather Intel│
│ │ │Travel Agent │
│ │ └─────────────┘
│ │ │
│ ▼ ▼
│ Ollama LLM ──► API Results
│ │ │
└──────────── Response ◄───────┴──────────────┘
⚡ TL;DR-使用3个命令入门
git clone <your-repo-url> && cd weather
chmod +x *.sh && ./start-docker.sh
# ✅ Chat Interface: http://localhost:8501
# ✅ API Server: http://localhost:8000
# ✅ System ready with Streamlit UI!
您立即获得的内容:
- 🌐 Streamlit聊天界面 在
http://localhost:8501-类似ChatGPT的天气助手 - 🔧 天气API 在
http://localhost:8000-带代理协调的完整MCP服务器 - 📚 API文件 在
http://localhost:8000/docs-交互式OpenAPI文档 - 🤖 奥拉马LLM 在
http://localhost:11434-用于智能响应的本地AI模型
📋 需求
- 码头工人 (20.10或更高版本)使用Docker Compose
- 8GB+内存 (适用于Ollama LLM型号:llama3+phi3)
- 15GB+磁盘空间 (适用于容器图像+模型+日志)
- 网络连接 (用于天气API和初始模型下载)
- 可用端口:8000(API)、8501(Streamlit)、11434(Ollama)
🚀 Docker快速入门
选项1:带有便利脚本的完整系统(推荐)
# 1. Clone the repository
git clone <your-repo-url>
cd weather-mcp-agent
# 2. Make scripts executable (Linux/macOS)
chmod +x *.sh
# 3. Validate your environment (optional but recommended)
./validate-docker.sh
# 4. Start the complete system (one command!)
./start-docker.sh
# 5. For verbose output and logs
./start-docker.sh --verbose
# 6. Stop the system when done
./stop-docker.sh
选项1b:手动Docker命令
# 1. Clone the repository
git clone <your-repo-url>
cd weather-mcp-agent
# 2. Start the complete system (Weather Server + Ollama + Models)
docker-compose up -d
# 3. Monitor the startup process
docker-compose logs -f
# 4. Wait for model downloads (first run only, may take 5-10 minutes)
# You'll see: "Models ready!" when everything is set up
# 5. Test the system
curl http://localhost:8000/health
系统将在以下地点提供:
- 🌐 流媒体聊天界面: http://localhost:8501(主界面)
- 🔧 天气API: http://localhost:8000(REST API+代理集线器)
- 🤖 奥拉马LLM: http://localhost:11434(AI模型)
- 📚 API文档: http://localhost:8000/docs(交互式文档)
选项2:带演示的开发设置
# Start system and run demo
docker-compose --profile demo up
# Or run demo separately after system is up
docker-compose up -d
docker-compose run weather-demo
选项3:本地开发(非Docker)
# 1. Install Ollama locally
brew install ollama # macOS
# or download from https://ollama.ai/download
# 2. Start Ollama and pull models
ollama serve &
ollama pull llama3
ollama pull phi3
# 3. Install Python dependencies
pip install -r requirements.txt
# 4. Environment configuration is ready!
# The .env file is already set up for local development
# For production, copy .env.production.template to .env.production and customize
# 5. Start the weather server
python main.py server
🐳 Docker管理命令
便利脚本(推荐)
# Development/testing
./start-docker.sh # Default setup
./start-docker.sh --dev # Development mode (live reload)
./start-docker.sh --demo # Include demo client
./start-docker.sh --verbose # Show detailed logs
# Production deployment
./start-docker.sh --prod # Production configuration
./start-docker.sh --prod --build # Production with fresh build
# Management
./stop-docker.sh # Stop (can restart)
./stop-docker.sh --cleanup # Remove containers
./stop-docker.sh --remove-data # Remove everything including models
手动Docker命令
# Default setup
docker-compose up -d
# Development mode (with live reload)
docker-compose -f docker-compose.yml -f docker-compose.dev.yml up -d
# Production mode (optimized settings)
docker-compose -f docker-compose.yml -f docker-compose.prod.yml up -d
# View logs (all services)
docker-compose logs -f
# View logs (specific service)
docker-compose logs -f weather-server
docker-compose logs -f ollama
# Stop all services
docker-compose down
# Restart services
docker-compose restart
# Rebuild and restart (after code changes)
docker-compose up -d --build
# Pull latest images
docker-compose pull
环境配置
| 环境 | 功能 | 用例 |
|---|---|---|
| 默认 | 标准设置,禁用API密钥 | 本地开发和测试 |
| 发展 | 实时重新加载、调试日志记录、宽松的安全性 | 主动开发 |
| 生产 | 优化性能、启用安全性、资源限制 | 生产部署 |
维护命令
# Check service status
docker-compose ps
# Access container shell
docker-compose exec weather-server bash
docker-compose exec ollama bash
# View system resources
docker-compose top
# Clean up (removes containers, networks, volumes)
docker-compose down -v --remove-orphans
# Remove all unused Docker resources
docker system prune -a
开发命令
# Run with demo profile
docker-compose --profile demo up
# Override environment variables
ENVIRONMENT=development docker-compose up -d
# Run single command in container
docker-compose run weather-server python --version
docker-compose run weather-server python demo.py
# Mount local code for development
# (uncomment volume in docker-compose.yml: - .:/app)
📚 用法示例
🌐 主要:Streamlit聊天界面 (推荐)
打开http://localhost:8501试试这些:
💬 "What's the weather like in San Francisco right now?"
💬 "Set up weather alerts for New York with temperature thresholds"
💬 "Compare weather conditions in London, Paris, and Tokyo"
💬 "Plan my outdoor activities for this weekend in Seattle"
💬 "Any severe weather alerts for California today?"
💬 "What's the best time to travel to Miami this week?"
特征:
- 🤖 自然语言处理:键入内容就像您在与ChatGPT聊天一样
- 📊 可视化仪表板:实时代理状态和系统健康监测
- 💾 对话历史:跨多个查询维护上下文
- 📱 移动响应:适用于手机和平板电脑
🔧 API测试(高级用户)
# System Health Check
curl http://localhost:8000/health
# Agent Coordination Status
curl http://localhost:8000/info
# Direct Weather Query
curl -X POST http://localhost:8000/tools/get_weather \
-H "Content-Type: application/json" \
-d '{"city": "San Francisco"}'
# Smart Alert Setup via API
curl -X POST http://localhost:8000/tools/setup_smart_alerts \
-H "Content-Type: application/json" \
-d '{
"locations": ["New York", "Boston"],
"alert_types": ["severe_weather", "temperature_extreme"],
"thresholds": {"temperature_high": 85, "temperature_low": 32}
}'
# Multi-Location Weather Intelligence
curl -X POST http://localhost:8000/tools/get_weather_intelligence \
-H "Content-Type: application/json" \
-d '{"locations": ["London", "Paris", "Rome"], "analysis_type": "comparison"}'
🐍 Python集成
# Direct Agent Usage
from agent_coordination_hub import AgentCoordinationHub
from smart_alert_agent import AlertAgent
# Initialize coordination system
hub = AgentCoordinationHub()
result = await hub.process_request("Weather in Tokyo with travel recommendations")
# Smart alerts with custom thresholds
alert_agent = AlertAgent()
config = {
"locations": ["San Francisco", "Seattle"],
"alert_types": ["severe_weather", "temperature_extreme"],
"thresholds": {"temperature_high": 80, "temperature_low": 40}
}
alerts = await alert_agent.setup_smart_alerts(config)
🛠️ Docker故障排除
常见问题及解决方法
问题:Ollama容器无法启动
# Check if port 11434 is already in use
lsof -i :11434
# If occupied, stop the local Ollama service
brew services stop ollama
# Check container logs
docker-compose logs ollama
问题:模型下载失败或超时
# Manually pull models with more verbose output
docker-compose exec ollama ollama pull llama3
docker-compose exec ollama ollama pull phi3
# Check available disk space (models are 4GB+ each)
docker system df
问题:天气服务器无法连接到Ollama
# Check network connectivity
docker-compose exec weather-server curl http://ollama:11434/api/version
# Verify Ollama health
curl http://localhost:11434/api/version
# Check container network
docker network ls
docker network inspect weather-mcp-network
问题:内存不足错误
# Check Docker memory limits
docker stats
# Increase Docker Desktop memory limit to 8GB+
# Docker Desktop > Settings > Resources > Memory
# Monitor container memory usage
docker-compose exec weather-server free -h
问题:端口冲突
# Check what's using port 8000
lsof -i :8000
# Use different ports
SERVER_PORT=8080 docker-compose up -d
# Or modify docker-compose.yml ports section
性能优化
# Pre-pull all images
docker-compose pull
# Build with cache optimization
DOCKER_BUILDKIT=1 docker-compose build
# Limit container resources
# Add to docker-compose.yml under services:
# weather-server:
# deploy:
# resources:
# limits:
# memory: 2g
# reservations:
# memory: 1g
日志和调试
# Detailed logging
LOG_LEVEL=DEBUG docker-compose up -d
# Follow all logs with timestamps
docker-compose logs -f -t
# Export logs for analysis
docker-compose logs > system-logs.txt
# Access container filesystems
docker-compose exec weather-server ls -la /app/logs/
⚙️ 环境配置
环境文件概述
该项目包括一个承诺 .env 针对本地开发进行了优化的文件:
| 文件 | 目的 | 致力于Git |
|---|---|---|
.env |
本地开发默认值 | ✅ 是的 |
.env.example |
带所有选项的模板 | ✅ 是的 |
.env.production.template |
生产模板 | ✅ 是的 |
.env.production |
您的生产配置 | ❌ 否(在本地创建) |
.env.local |
个人覆盖 | ❌ 否(忽略) |
地方发展
这 .env 文件是 随时可用 使用安全默认值:
# Clone and run immediately - no .env setup needed!
git clone <your-repo>
cd weather-mcp-agent
./start-docker.sh
当地发展特点:
- ✅
ENVIRONMENT=development - ✅ 已启用调试日志记录
- ✅ CORS允许本地主机源
- ✅ API密钥要求已禁用
- ✅ 测试的高速率限制
- ✅ 包括原始数据和执行日志
定制
创建 .env.local 对于个人覆盖(被git忽略):
# .env.local - personal overrides
LOG_LEVEL=DEBUG
OLLAMA_MODEL=phi3
SERVER_PORT=8001
环境变量优先级
- 环境变量 (最高优先级)
.env.local(个人优先权).env(承诺违约)
🚀 使用Docker进行生产部署
步骤1:生产环境配置
# 1. Clone to production server
git clone <your-repo-url>
cd weather-mcp-agent
# 2. Create production environment file
cp .env.production.template .env.production
# 3. Edit production settings (REQUIRED - update all sensitive values)
nano .env.production
关键生产设置:
ENVIRONMENT=production
API_KEY_REQUIRED=true
API_KEY=your-secure-production-key
ALLOWED_ORIGINS=https://yourdomain.com
RATE_LIMIT_PER_MINUTE=60
LOG_LEVEL=INFO
步骤2:SSL/TLS配置(可选)
# Add SSL certificates to docker-compose.yml
mkdir -p ./ssl
# Copy your cert.pem and key.pem to ./ssl/
# Update .env.production
SSL_CERT_PATH=/app/ssl/cert.pem
SSL_KEY_PATH=/app/ssl/key.pem
步骤3:生产部署
# Method 1: Using convenience script (recommended)
./start-docker.sh --build
# Method 2: Manual deployment
docker-compose -f docker-compose.yml --env-file .env.production up -d
# Method 3: With custom configuration
docker-compose up -d --build
步骤4:生产验证
# Check all services are running
docker-compose ps
# Verify health endpoints
curl https://yourdomain.com:8000/health
curl https://yourdomain.com:8000/info
# Check logs for any issues
docker-compose logs -f --tail=100
# Method 4: Docker with external Ollama
docker build -t weather-mcp .
docker run -p 8000:8000 --env-file .env --add-host=host.docker.internal:host-gateway weather-mcp
生产终点:
- 🏥
GET /health-全面的健康检查和服务验证 - ⚡
GET /health/quick-无需外部电话即可快速进行健康检查 - 📊
GET /info-服务器功能和元数据 - 🌤️
POST /tools/get_weather-当前天气(限速) - 📅
POST /tools/get_forecast-天气预报(验证坐标) - 🚨
POST /tools/get_alerts-天气警报(仅限美国各州)
管理命令:
# Production server management
python main.py start # Start production server
python main.py status # System health and status
python main.py config # View current configuration
python main.py validate # Validate configuration
# Development/testing (disabled in production)
python main.py interactive # Interactive client mode
python main.py demo # System demonstration
python main.py servers # Server registry info
📁 项目结构
weather/
├── 🌐 Web Interface
│ └── streamlit_app.py # Streamlit Chat UI (Primary Interface)
├── 🤖 Agent Coordination System
│ ├── agent_coordination_hub.py # Central agent coordinator
│ ├── smart_alert_agent.py # Proactive weather monitoring agent
│ ├── weather_intelligence_agent.py # Multi-source data analysis agent
│ └── travel_agent.py # Location-based travel planning agent
├── � Core MCP Server
│ ├── main.py # Production entry point & CLI management
│ ├── weather.py # Weather MCP server implementation
│ ├── config.py # Configuration management
│ ├── server_registry.py # Server discovery & health monitoring
│ └── health_server.py # Health check endpoints
├── 🚀 Orchestration & Workflows
│ ├── simple_orchestrator.py # Basic agentic workflow orchestrator
│ └── agent_orchestrator.py # Advanced LangGraph orchestrator
├── 🛠️ Development & Testing
│ ├── mcp_client.py # Interactive client for testing
│ ├── demo.py # System demonstration scripts
│ └── run_server.py # Alternative server startup
├── � Docker & Deployment
│ ├── Dockerfile # Production container image
│ ├── docker-compose.yml # Multi-service orchestration
│ ├── start-docker.sh # Comprehensive startup script
│ ├── stop-docker.sh # Clean shutdown script
│ └── setup-ollama.sh # Ollama model setup automation
├── 📋 Configuration & Dependencies
│ ├── requirements.txt # Python dependencies
│ ├── pyproject.toml # Project metadata (v0.2.0)
│ ├── .env # Environment variables (Docker-ready)
│ └── .env.example # Configuration template
└── 📚 Documentation
├── README.md # This comprehensive guide
├── SETUP.md # Quick setup instructions
├── DOCKER.md # Docker-specific documentation
├── DEPLOYMENT.md # Production deployment guide
├── WORKING_SYSTEM_SUMMARY.md # System status & test cases
├── AGENT_COORDINATION_GUIDE.md # Agent development guide
└── CONTRIBUTING.md # Contribution guidelines
💬 交互式使用示例
🌐 Streamlit聊天界面 (http://localhost:8501)
这 主要方式 与您的天气情报系统交互:
🔮 智能天气查询:
💬 "What's the weather like in London right now?"
🤖 "🌤️ London Weather Update:
🌡️ Temperature: 15°C (feels like 13°C)
🌧️ Conditions: Light drizzle
💨 Wind: 12 mph from the west
📊 Humidity: 78%"
💬 "Set up weather alerts for my commute route"
🤖 "I'll set up smart alerts for your locations. What cities should I monitor?"
💬 "Compare weather in New York, London, and Tokyo"
🤖 "🌍 Multi-City Weather Comparison:
🗽 New York: 22°C, Sunny, Perfect for outdoor activities
🇬🇧 London: 15°C, Overcast, Light jacket recommended
🗾 Tokyo: 28°C, Humid, Stay hydrated!"
� 高级功能:
- 对话记忆:跨问题保持上下文
- 可视化仪表板:实时系统运行状况和代理状态
- 移动响应:手机和平板电脑的完美界面
- 多智能体协调:自动路由到专门的气象机构
🛠️ API命令示例 (高级用户)
# System Status & Health
curl http://localhost:8000/health
curl http://localhost:8000/info
# Agent Coordination
curl -X POST http://localhost:8000/agent/coordinate \
-H "Content-Type: application/json" \
-d '{"query": "Weather alerts for California with travel advice"}'
🛠️ API集成示例
直接服务器API调用
# Get current weather
curl -X POST http://localhost:8000/tools/get_weather \
-H "Content-Type: application/json" \
-d '{"city": "London"}'
# Get forecast (requires coordinates)
curl -X POST http://localhost:8000/tools/get_forecast \
-H "Content-Type: application/json" \
-d '{"latitude": 51.5074, "longitude": -0.1278}'
# Get weather alerts (US states only)
curl -X POST http://localhost:8000/tools/get_alerts \
-H "Content-Type: application/json" \
-d '{"state": "CA"}'
服务器发现和运行状况
# Check server health
curl http://localhost:8000/health
# Get server capabilities
curl http://localhost:8000/info
🔧 扩展系统
添加新的MCP服务器
# Register a new server in server_registry.py
from server_registry import registry, MCPServer
# Define new server
finance_server = MCPServer(
name="finance-server",
host="localhost",
port=8001,
description="Financial data and stock information",
tools=["get_stock_price", "get_market_news", "analyze_portfolio"],
tags=["finance", "stocks", "market"]
)
# Register it
registry.register_server(finance_server)
自定义任务类型
# Extend TaskType enum in simple_orchestrator.py
class TaskType(Enum):
WEATHER_QUERY = "weather_query"
FORECAST_ANALYSIS = "forecast_analysis"
ALERT_MONITORING = "alert_monitoring"
MULTI_LOCATION = "multi_location"
FINANCIAL_ANALYSIS = "financial_analysis" # New!
GENERAL_INQUIRY = "general_inquiry"
🎯 代理设计原则
1.模块化
- 每个组件都有一个明确的责任
- 易于扩展新的服务器和功能
- 编排器和服务器之间的松耦合
2.智能路由
- 任务分类决定工作流路径
- 位置提取支持多位置查询
- 使用优雅的回退进行错误处理
3.可扩展性
- 服务器注册表支持动态添加服务器
- 自动故障转移的运行状况监控
- 并发处理的异步操作
4.可观察性
- 用于调试的详细执行日志
- 绩效指标和时间安排
- 健康状态监测
🔮 高级功能(可选)
LangGraph集成
对于更复杂的代理工作流,请启用高级编排器:
# Install additional dependencies
uv add langgraph langchain-ollama
# Use agent_orchestrator.py instead of simple_orchestrator.py
from agent_orchestrator import WeatherOrchestrator
# Requires Ollama running locally
ollama serve
多智能体协调
该系统旨在支持多代理场景:
# Example: Weather + Travel planning agent
travel_query = "What's the weather like in my travel destinations this week?"
# → Orchestrator coordinates:
# 1. Extract travel destinations
# 2. Get weather for each location
# 3. Get forecasts for travel dates
# 4. Provide travel recommendations
📊 监控与调试
健康检查
# Check all servers
💬 You: servers
📊 Found 1 registered servers:
✅ Online: 1
❌ Offline: 0
⚠️ Error: 0
❓ Unknown: 0
执行日志
每个查询都提供详细的执行跟踪:
🔍 Execution Log:
1. Classified task as: weather_query
2. Extracted locations: ['London']
3. Gathered weather data for 1 locations
4. Generated response
🔒 生产安全
环境变量
生产部署所需:
# Server Configuration
SERVER_HOST=0.0.0.0
SERVER_PORT=8000
ENVIRONMENT=production
# Security
API_KEY_REQUIRED=true
API_KEY=your-secure-api-key-here
RATE_LIMIT_PER_MINUTE=100
ALLOWED_ORIGINS=https://yourdomain.com
# Logging
LOG_LEVEL=INFO
LOG_FILE_PATH=/var/log/weather-mcp/server.log
安全功能
- 输入验证 使用Pydantic模型
- 速率限制 每个端点(可配置)
- API密钥验证 (可选)
- CORS保护 具有可配置的来源
- 请求大小限制 防止DoS
- 综合录井 用于审计跟踪
- 错误清理 防止信息泄露
� 生产监控
健康检查
# Quick health check
curl http://localhost:8000/health/quick
# Comprehensive health check (includes external APIs)
curl http://localhost:8000/health
# Server info and capabilities
curl http://localhost:8000/info
日志记录
生产日志的结构包括:
- 请求/响应日志记录
- 使用堆栈跟踪进行错误跟踪
- 性能指标
- 安全事件(速率限制、身份验证失败)
# View logs (if using file logging)
tail -f /var/log/weather-mcp/server.log
# Check log level
python main.py config | grep -i log
性能优化
- 异步请求处理 使用httpx
- 连接池 用于外部API
- 请求超时控制
- 指数退避 用于API重试
- 响应缓存 (可配置)
- 资源限制 以及速率限制
�🚨 故障排除
常见生产问题:
-
服务器无法启动:检查端口可用性和环境变量
# Check port usage lsof -ti:8000 # Validate configuration python main.py validate # Check environment python main.py config -
Ollama连接问题:确保Olama正在运行且可访问
# Check if Ollama is running ollama list # If not running, start Ollama ollama serve # Test connection to Ollama curl http://localhost:11434/api/version # Verify model is available ollama run llama3 "Hello, test message" -
内存使用率高:调整工作人员数量和连接限制
# Reduce workers in production uvicorn weather:app --workers 2 --max-requests 1000 -
API超时:外部气象服务可能很慢
# Check API status curl -w "%{time_total}\n" http://localhost:8000/health -
利率限制问题:调整环境变量的限制
# In .env file RATE_LIMIT_PER_MINUTE=200 SERVER_TIMEOUT=45.0
日志分析
# Find errors in logs
grep -i error /var/log/weather-mcp/server.log
# Check API performance
grep "response_time" /var/log/weather-mcp/server.log
# Monitor rate limiting
grep "rate.*limit" /var/log/weather-mcp/server.log
🤝 贡献
我们欢迎捐款!以下是如何开始:
- 分叉存储库
- 创建要素分支:
git checkout -b feature/amazing-feature - 进行更改
- 添加测试 对于新功能
- 运行测试套件:
uv run main.py test - 提交您的更改:
git commit -m 'Add amazing feature' - 推到分支:
git push origin feature/amazing-feature - 打开拉取请求
贡献领域:
- 新MCP服务器:添加天气邻近服务(交通、活动等)
- 增强NLP:改进位置提取和查询理解
- 高级编排:实施复杂的多步骤工作流程
- 数据源:集成其他天气API和服务
- 文档:改进指南和示例
- 生产特点:添加监控、缓存和性能改进
- 增强的安全性:其他身份验证方法和安全强化
✅ Docker部署清单
预部署
- []已安装Docker引擎20.10+
- []已安装Docker Compose v2.0+或Docker Compose v1.29+
- []系统有8GB+RAM可用
- []Ollama型号的10GB+磁盘空间
- []用于API访问和模型下载的互联网连接
环境设置
- []克隆存储库并使脚本可执行(
chmod +x *.sh) - []环境已验证(
./validate-docker.sh) - []已配置生产环境(
.env.production) - []已配置SSL证书(如果使用HTTPS)
部署验证
- []所有容器均已成功启动(
docker-compose ps) - []健康检查通过(
curl localhost:8000/health) - []Ollama模型已下载(
docker-compose logs ollama-setup) - []天气API端点响应(
curl localhost:8000/tools/get_weather) - []日志显示没有错误(
docker-compose logs)
生产就绪
- []API密钥已配置且安全
- []适当配置速率限制
- []为您的域配置的CORS设置
- []已配置监控和警报
- []配置和数据的备份策略
- []为容器设置的资源限制
📄 许可证
此项目根据MIT许可证获得许可-请参阅 许可证 文件以获取详细信息。
🎬 演示场景
🌐 打开http://localhost:8501并尝试这些智能天气工作流程:
🏃♂️ 个人计划
💬 "Plan my outdoor workout routine for San Francisco this week"
💬 "Should I bring an umbrella to my meeting in Seattle tomorrow?"
💬 "What's the best day for a picnic in Central Park this weekend?"
💬 "When should I schedule my outdoor photography session in London?"
✈️ 旅游情报
💬 "I'm flying from New York to Los Angeles tomorrow - any weather concerns?"
💬 "Compare weather conditions for my business trip: Boston, Chicago, Denver"
💬 "Best time to visit Tokyo this month based on weather patterns?"
💬 "Should I pack winter clothes for my trip to Montreal next week?"
🚨 智能监控
💬 "Set up weather alerts for my daily commute from Brooklyn to Manhattan"
💬 "Monitor severe weather for my company's offices in California and Texas"
💬 "Alert me if temperature drops below freezing in Chicago this week"
💬 "Watch for storm systems affecting my weekend camping trip in Yosemite"
🏢 业务应用程序
💬 "Weather impact analysis for our retail stores in Florida, Georgia, and South Carolina"
💬 "Construction weather forecast for our project sites in Denver and Phoenix"
💬 "Event planning weather assessment for outdoor venues this month"
每个查询都演示了:
- 🤖 多智能体协调:自动路由到专业代理
- 🧠 情境感知:了解复杂的多部分请求
- 📊 智能分析:来自多个天气源的数据融合
- 💡 主动建议:超越原始数据的可操作见解
📚 依赖项
看 requirements.txt 查看完整的依赖关系列表。关键包:
- 快速API:REST API框架
- LangChain:LLM集成(高级功能可选)
- LangGraph:高级代理编排
- 主控程序:模型上下文协议实现
- 请求/HTTPX:HTTP客户端库
- 派丹蒂克:数据验证
🙏 致谢
- 建立在 模型上下文协议(MCP) 框架
- 天气数据来自 NWS API 和 wttr.in
- 受代理AI社区的启发
📊 当前系统状态 (更新日期:2025年10月16日)
✅ 现场服务
- 🌐 Streamlit聊天界面: http://localhost:8501 ✅ 健康
- 🔧 Weather API+代理中心: http://localhost:8000 ✅ 健康
- 🤖 Ollama LLM发动机: http://localhost:11434 ✅ 健康
- 📚 交互式API文档: http://localhost:8000/docs ✅ 可用的
🤖 活性剂
- 智能警报代理: ✅ 具有自定义阈值的主动天气监测
- 气象情报员: ✅ 多源数据分析和预测
- 旅行社: ✅ 基于位置的规划和建议
- 代理商协调中心: ✅ 中央编排和路由系统
💡 现在试试
- 打开: http://localhost:8501(流媒体聊天)
- 问: “为旧金山设置带温度阈值的天气警报”
- 手表:多智能体协同行动!
📈 系统健康
{
"status": "healthy",
"services": {
"nws_api": "available",
"wttr_in": "available",
"ollama": "healthy"
},
"performance": {
"response_time_ms": 2135.61,
"memory_usage": "available"
},
"environment": "production"
}
内置于❤️ 面向代理AI社区 | 可扩展•模块化•生产就绪 版本0.2.0 | 多智能体协调 | Docker原生 | 流媒体接口