Integrating AI with Open-Meteo API for Enhanced Weather Forecasting

工作流概述

这是一个包含12个节点的复杂工作流,主要用于自动化处理各种任务。

工作流源代码

下载
{
  "id": "Nfh274NHoDy7pB4M",
  "meta": {
    "instanceId": "00493e38fecfc163cb182114bc2fab90114038eb9aad665a7a752d076920d3d5",
    "templateCredsSetupCompleted": true
  },
  "name": "Integrating AI with Open-Meteo API for Enhanced Weather Forecasting",
  "tags": [],
  "nodes": [
    {
      "id": "80debfe0-c591-4ba1-aca1-068adac62aa9",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        100,
        -300
      ],
      "webhookId": "4a44e974-db62-4727-9913-12a22bc88e01",
      "parameters": {
        "public": true,
        "options": {
          "title": "N8N 👋",
          "subtitle": "Weather Assistant: Example of Tools Using ChatGPT",
          "allowFileUploads": false,
          "loadPreviousSession": "memory"
        },
        "initialMessages": "Type like this: Weather Forecast for the Next 7 Days in São Paulo"
      },
      "typeVersion": 1.1
    },
    {
      "id": "ec375027-1c0d-438b-9fca-7bc4fbef2479",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        420,
        -60
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "bhRvwBXztNmJVObo",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "bd2f5967-8188-4b1f-9255-8008870aaf7b",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -540,
        -640
      ],
      "parameters": {
        "color": 5,
        "width": 500,
        "height": 720,
        "content": "## Integrating AI with Open-Meteo API for Enhanced Weather Forecasting

## Use case

### Workshop

We are using this workflow in our workshops to teach how to use Tools a.k.a functions with artificial intelligence. In this specific case, we will use a generic \"AI Agent\" node to illustrate that it could use other models from different data providers.

### Enhanced Weather Forecasting

In this small example, it's easy to demonstrate how to obtain weather forecast results from the Open-Meteo site to accurately display the upcoming days.

This can be used to plan travel decisions, for example.

## What this workflow does

1. We will make an HTTP request to find out the geographic coordinates of a city.
2. Then, we will make other HTTP requests to discover the weather for the upcoming days.

In this workshop, we demonstrate that the AI will be able to determine which tool to call first—it will first call the geolocation tool and then the weather forecast tool. All of this within a single client conversation call.


## Setup

Insert an OpenAI Key and activate the workflow.

by Davi Saranszky Mesquita
https://www.linkedin.com/in/mesquitadavi/"
      },
      "typeVersion": 1
    },
    {
      "id": "3cfeea52-a310-4101-8377-0f393bf54c8d",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        60,
        -440
      ],
      "parameters": {
        "width": 340,
        "height": 220,
        "content": "## Create an Hosted Web Chat

### And setup the trigger!

Example: https://website/webhook/4a4..../chat"
      },
      "typeVersion": 1
    },
    {
      "id": "55713ffc-da61-4594-99f4-ca6b448cbee2",
      "name": "Generic AI Tool Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        440,
        -300
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.7
    },
    {
      "id": "7f608ddc-87bb-4e54-84a8-4db6b7f95011",
      "name": "Chat Memory Buffer",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        200,
        -60
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "77f82443-1efe-47d3-92ec-aa193853c8a5",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        320,
        0
      ],
      "parameters": {
        "width": 260,
        "content": "-


## Setup OpenAI Key"
      },
      "typeVersion": 1
    },
    {
      "id": "ed37ea94-3cff-47cb-bf45-bce620b0f056",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        780,
        60
      ],
      "parameters": {
        "color": 4,
        "width": 280,
        "height": 360,
        "content": "### Open Meteo SPEC - City Geolocation

This tool will go to the URL https://geocoding-api.open-meteo.com/v1/search to fetch the geolocation data of the city, and I only need to get the name of the city.

So, I will ask the user to input the name of the city and pass some pre-existing information, such as returning only the first city and returning in JSON format.

- name (By Model) - And placeholder - The parameter that the AI will need to fill in as required.

- count - 1 by default because I want only the first city.

- format - Putting JSON for no specific reason, but OpenAI could figure out how to process that information."
      },
      "typeVersion": 1
    },
    {
      "id": "f9b0e65d-a85e-4511-bdd2-adf54b1c039d",
      "name": "A tool to get the weather forecast based on geolocation",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1100,
        -160
      ],
      "parameters": {
        "url": "https://api.open-meteo.com/v1/forecast",
        "sendQuery": true,
        "parametersQuery": {
          "values": [
            {
              "name": "latitude"
            },
            {
              "name": "longitude"
            },
            {
              "name": "daily",
              "value": "temperature_2m_max,precipitation_sum",
              "valueProvider": "fieldValue"
            },
            {
              "name": "timezone",
              "value": "GMT",
              "valueProvider": "fieldValue"
            },
            {
              "name": "forecast_days"
            }
          ]
        },
        "toolDescription": "To get forecast of next [forecast_days] input the geolocation of an City",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "longitude",
              "type": "number",
              "description": "longitude"
            },
            {
              "name": "latitude",
              "type": "number",
              "description": "latitude"
            },
            {
              "name": "forecast_days",
              "type": "number",
              "description": "forecast_days number of days ahead"
            }
          ]
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "76382491-dd75-4b51-a2d8-cb9782246af8",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1240,
        -220
      ],
      "parameters": {
        "color": 4,
        "width": 280,
        "height": 320,
        "content": "### Open Meteo SPEC - Weather Forecast

This tool will go to the Open Meteo site with the geolocation information at https://api.open-meteo.com/v1/forecast

It will pass the information on latitude, longitude, and the number of days for which it will bring data.

There are many default pieces of information within, but the focus is not to explain the Open Meteo API.

Variables like latitude, longitude, and forecast_days are self-explanatory for OpenAI, making it the easiest tool to configure.

- latitude (By Model) and Placeholder
- longitude (By Model) and Placeholder
- forecast_days (By Model) and Placeholder
"
      },
      "typeVersion": 1
    },
    {
      "id": "1c8087ce-6800-4ece-8234-23914e21a692",
      "name": "A tool for inputting the city and obtaining geolocation",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        820,
        -100
      ],
      "parameters": {
        "url": "=https://geocoding-api.open-meteo.com/v1/search",
        "sendQuery": true,
        "parametersQuery": {
          "values": [
            {
              "name": "name"
            },
            {
              "name": "count",
              "value": "1",
              "valueProvider": "fieldValue"
            },
            {
              "name": "format",
              "value": "json",
              "valueProvider": "fieldValue"
            }
          ]
        },
        "toolDescription": "Input the City and get geolocation, geocode or coordinates from Requested City",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "name",
              "type": "string",
              "description": "Requested City"
            }
          ]
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "15ae7421-eff9-4677-b8cf-b7bbb5d2385e",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -100,
        340
      ],
      "parameters": {
        "color": 3,
        "width": 840,
        "height": 80,
        "content": "## Within N8N, there will be a chat button to test, or you can use the external chat link from the trigger."
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "778e2544-db78-4836-8bd1-771f333a621c",
  "connections": {
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Generic AI Tool Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Chat Memory Buffer": {
      "ai_memory": [
        [
          {
            "node": "When chat message received",
            "type": "ai_memory",
            "index": 0
          },
          {
            "node": "Generic AI Tool Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Generic AI Tool Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "A tool for inputting the city and obtaining geolocation": {
      "ai_tool": [
        [
          {
            "node": "Generic AI Tool Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "A tool to get the weather forecast based on geolocation": {
      "ai_tool": [
        [
          {
            "node": "Generic AI Tool Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  }
}

功能特点

  • 自动检测新邮件
  • AI智能内容分析
  • 自定义分类规则
  • 批量处理能力
  • 详细的处理日志

技术分析

节点类型及作用

  • @N8N/N8N Nodes Langchain.Chattrigger
  • @N8N/N8N Nodes Langchain.Lmchatopenai
  • Stickynote
  • @N8N/N8N Nodes Langchain.Agent
  • @N8N/N8N Nodes Langchain.Memorybufferwindow

复杂度评估

配置难度:
★★★★☆
维护难度:
★★☆☆☆
扩展性:
★★★★☆

实施指南

前置条件

  • 有效的Gmail账户
  • n8n平台访问权限
  • Google API凭证
  • AI分类服务订阅

配置步骤

  1. 在n8n中导入工作流JSON文件
  2. 配置Gmail节点的认证信息
  3. 设置AI分类器的API密钥
  4. 自定义分类规则和标签映射
  5. 测试工作流执行
  6. 配置定时触发器(可选)

关键参数

参数名称 默认值 说明
maxEmails 50 单次处理的最大邮件数量
confidenceThreshold 0.8 分类置信度阈值
autoLabel true 是否自动添加标签

最佳实践

优化建议

  • 定期更新AI分类模型以提高准确性
  • 根据邮件量调整处理批次大小
  • 设置合理的分类置信度阈值
  • 定期清理过期的分类规则

安全注意事项

  • 妥善保管API密钥和认证信息
  • 限制工作流的访问权限
  • 定期审查处理日志
  • 启用双因素认证保护Gmail账户

性能优化

  • 使用增量处理减少重复工作
  • 缓存频繁访问的数据
  • 并行处理多个邮件分类任务
  • 监控系统资源使用情况

故障排除

常见问题

邮件未被正确分类

检查AI分类器的置信度阈值设置,适当降低阈值或更新训练数据。

Gmail认证失败

确认Google API凭证有效且具有正确的权限范围,重新进行OAuth授权。

调试技巧

  • 启用详细日志记录查看每个步骤的执行情况
  • 使用测试邮件验证分类逻辑
  • 检查网络连接和API服务状态
  • 逐步执行工作流定位问题节点

错误处理

工作流包含以下错误处理机制:

  • 网络超时自动重试(最多3次)
  • API错误记录和告警
  • 处理失败邮件的隔离机制
  • 异常情况下的回滚操作