application

工作流概述

这是一个包含10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": "39KuujB1fbOvx8Al",
  "meta": {
    "instanceId": "0a5638e14e0c728ef975d18d109cfb41edae575e3d911724f4f1eccde06a729f"
  },
  "name": "OpenAI e-mail classification - application",
  "tags": [],
  "nodes": [
    {
      "id": "6156844f-d1ba-413d-9ab2-02148bef5bf0",
      "name": "Email trigger",
      "type": "n8n-nodes-base.emailReadImap",
      "position": [
        -440,
        120
      ],
      "parameters": {
        "format": "resolved",
        "options": {},
        "postProcessAction": "nothing",
        "dataPropertyAttachmentsPrefixName": "attachment"
      },
      "credentials": {
        "imap": {
          "id": "il5dS1iQxJvOMWbE",
          "name": "IMAP account"
        }
      },
      "typeVersion": 2
    },
    {
      "id": "1aedaa56-d988-469b-86b9-61d50e707950",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        0,
        0
      ],
      "parameters": {
        "height": 200,
        "content": "### Change or add any category you want
Each category can be assigned it's own specific workflow"
      },
      "typeVersion": 1
    },
    {
      "id": "d41ba844-2b99-42bb-80df-cff1b97dcbb9",
      "name": "Classify email",
      "type": "@n8n/n8n-nodes-langchain.textClassifier",
      "position": [
        0,
        120
      ],
      "parameters": {
        "options": {},
        "inputText": "={{ $('Email trigger').first().json.text }}

attachment:
{{ $('Extract data from attachment').first().json.text }}
",
        "categories": {
          "categories": [
            {
              "category": "job_application",
              "description": "for job applications"
            },
            {
              "category": "inbound_lead",
              "description": "for sales inquiries or requests for more information about our products/services"
            },
            {
              "category": "invoice",
              "description": "for invoices"
            },
            {
              "category": "other",
              "description": "for all other sorts of emails"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "b63a864f-f968-4e7e-9da4-d704f3ffa022",
      "name": "Extract variables - email & attachment",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        440,
        20
      ],
      "parameters": {
        "text": "={{ $('Email trigger').first().json.text }}

Resume:
{{ $('Extract data from attachment').first().json.text }}
",
        "options": {},
        "attributes": {
          "attributes": [
            {
              "name": "first_name",
              "description": "first name of the applicant"
            },
            {
              "name": "last_name",
              "description": "last name of the applicant"
            },
            {
              "name": "age",
              "description": "age of the applicant"
            },
            {
              "name": "residence",
              "description": "residence of the applicant"
            },
            {
              "name": "study",
              "description": "relevant completed study of the applicant"
            },
            {
              "name": "work_experience",
              "description": "relevant work experience of the applicant"
            },
            {
              "name": "personal_character",
              "description": "personal characteristics of the applicant"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "398b9240-0d9c-416e-af3b-31ba9e1ac9b2",
      "name": "Extract data from attachment",
      "type": "n8n-nodes-base.extractFromFile",
      "onError": "continueRegularOutput",
      "position": [
        -220,
        120
      ],
      "parameters": {
        "options": {},
        "operation": "pdf",
        "binaryPropertyName": "attachment0"
      },
      "typeVersion": 1,
      "alwaysOutputData": false
    },
    {
      "id": "9f949aac-1681-4f04-983e-8bd5c949987a",
      "name": "OpenAI Chat Model 2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        660,
        200
      ],
      "parameters": {
        "model": "gpt-4o",
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "by5xbXU1Yz36JahE",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "c7a61afe-d68d-407e-8653-46cb123877e9",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        100,
        320
      ],
      "parameters": {
        "model": "gpt-4o",
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "by5xbXU1Yz36JahE",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "5a22e81b-8b60-443e-985b-47d493724389",
      "name": "Workflow 2",
      "type": "n8n-nodes-base.noOp",
      "position": [
        440,
        180
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "808e4f35-604e-4354-ab8b-3ba68940016b",
      "name": "Workflow 3",
      "type": "n8n-nodes-base.noOp",
      "position": [
        600,
        360
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "d793675d-c68d-4f73-a99d-6451be5bea30",
      "name": "workflow 4",
      "type": "n8n-nodes-base.noOp",
      "position": [
        440,
        360
      ],
      "parameters": {},
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "errorWorkflow": "rkMQmtrfcSF3XpMF",
    "executionOrder": "v1"
  },
  "versionId": "28448ab7-6d45-41df-9de3-aad0e187edc5",
  "connections": {
    "Email trigger": {
      "main": [
        [
          {
            "node": "Extract data from attachment",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Classify email": {
      "main": [
        [
          {
            "node": "Extract variables - email & attachment",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Workflow 2",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Workflow 3",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "workflow 4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Classify email",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model 2": {
      "ai_languageModel": [
        [
          {
            "node": "Extract variables - email & attachment",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Extract data from attachment": {
      "main": [
        [
          {
            "node": "Classify email",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract variables - email & attachment": {
      "main": [
        []
      ]
    }
  }
}

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

  • Emailreadimap
  • Stickynote
  • @N8N/N8N Nodes Langchain.Textclassifier
  • @N8N/N8N Nodes Langchain.Informationextractor
  • Extractfromfile

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