Use any LLM-Model via OpenRouter

工作流概述

这是一个包含8个节点的中等工作流,主要用于自动化处理各种任务。

工作流源代码

下载
{
  "id": "VhN3CX6QPBkX77pZ",
  "meta": {
    "instanceId": "98bf0d6aef1dd8b7a752798121440fb171bf7686b95727fd617f43452393daa3",
    "templateCredsSetupCompleted": true
  },
  "name": "Use any LLM-Model via OpenRouter",
  "tags": [
    {
      "id": "uumvgGHY5e6zEL7V",
      "name": "Published Template",
      "createdAt": "2025-02-10T11:18:10.923Z",
      "updatedAt": "2025-02-10T11:18:10.923Z"
    }
  ],
  "nodes": [
    {
      "id": "b72721d2-bce7-458d-8ff1-cc9f6d099aaf",
      "name": "Settings",
      "type": "n8n-nodes-base.set",
      "position": [
        -420,
        -640
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "3d7f9677-c753-4126-b33a-d78ef701771f",
              "name": "model",
              "type": "string",
              "value": "deepseek/deepseek-r1-distill-llama-8b"
            },
            {
              "id": "301f86ec-260f-4d69-abd9-bde982e3e0aa",
              "name": "prompt",
              "type": "string",
              "value": "={{ $json.chatInput }}"
            },
            {
              "id": "a9f65181-902d-48f5-95ce-1352d391a056",
              "name": "sessionId",
              "type": "string",
              "value": "={{ $json.sessionId }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "a4593d64-e67a-490e-9cb4-936cc46273a0",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -460,
        -740
      ],
      "parameters": {
        "width": 180,
        "height": 400,
        "content": "## Settings
Specify the model"
      },
      "typeVersion": 1
    },
    {
      "id": "3ea3b09a-0ab7-4e0f-bb4f-3d807d072d4e",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -240,
        -740
      ],
      "parameters": {
        "color": 3,
        "width": 380,
        "height": 400,
        "content": "## Run LLM
Using OpenRouter to make model fully configurable"
      },
      "typeVersion": 1
    },
    {
      "id": "19d47fcb-af37-4daa-84fd-3f43ffcb90ff",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -660,
        -640
      ],
      "webhookId": "71f56e44-401f-44ba-b54d-c947e283d034",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "f5a793f2-1e2f-4349-a075-9b9171297277",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -180,
        -640
      ],
      "parameters": {
        "text": "={{ $json.prompt }}",
        "options": {},
        "promptType": "define"
      },
      "typeVersion": 1.7
    },
    {
      "id": "dbbd9746-ca25-4163-91c5-a9e33bff62a4",
      "name": "Chat Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -80,
        -460
      ],
      "parameters": {
        "sessionKey": "={{ $json.sessionId }}",
        "sessionIdType": "customKey"
      },
      "typeVersion": 1.3
    },
    {
      "id": "ef368cea-1b38-455b-b46a-5d0ef7a3ceb3",
      "name": "LLM Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -200,
        -460
      ],
      "parameters": {
        "model": "={{ $json.model }}",
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "66JEQJ5kJel1P9t3",
          "name": "OpenRouter"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "32601e76-0979-4690-8dcf-149ddbf61983",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -460,
        -320
      ],
      "parameters": {
        "width": 600,
        "height": 240,
        "content": "## Model examples

* openai/o3-mini
* google/gemini-2.0-flash-001
* deepseek/deepseek-r1-distill-llama-8b
* mistralai/mistral-small-24b-instruct-2501:free
* qwen/qwen-turbo

For more see https://openrouter.ai/models"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "6d0caf5d-d6e6-4059-9211-744b0f4bc204",
  "connections": {
    "Settings": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLM Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Chat Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Settings",
            "type": "main",
            "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

  • Set
  • Stickynote
  • @N8N/N8N Nodes Langchain.Chattrigger
  • @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