Agentic Telegram AI bot with LangChain nodes and new tools
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
{
"id": "U8EOTtZvmZPMYc6m",
"meta": {
"instanceId": "fb924c73af8f703905bc09c9ee8076f48c17b596ed05b18c0ff86915ef8a7c4a",
"templateCredsSetupCompleted": true
},
"name": "Agentic Telegram AI bot with LangChain nodes and new tools",
"tags": [],
"nodes": [
{
"id": "13b3488e-af72-4d89-bef4-e9b895e3bf76",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1640,
580
],
"parameters": {
"model": "gpt-4o",
"options": {
"temperature": 0.7,
"frequencyPenalty": 0.2
}
},
"credentials": {
"openAiApi": {
"id": "rveqdSfp7pCRON1T",
"name": "Ted's Tech Talks OpenAi"
}
},
"typeVersion": 1
},
{
"id": "864937a1-43f6-4055-bdea-61ab07db9903",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1760,
580
],
"parameters": {
"sessionKey": "=chat_with_{{ $('Listen for incoming events').first().json.message.chat.id }}",
"contextWindowLength": 10
},
"typeVersion": 1
},
{
"id": "4ef838d4-feaa-4bd3-b2c7-ccd938be4373",
"name": "Listen for incoming events",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
1580,
360
],
"webhookId": "322dce18-f93e-4f86-b9b1-3305519b7834",
"parameters": {
"updates": [
"*"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "9dexJXnlVPA6wt8K",
"name": "Chat & Sound"
}
},
"typeVersion": 1
},
{
"id": "fed51c41-2846-4a1a-a5f5-ce121ee7fe88",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
1460,
180
],
"parameters": {
"color": 7,
"width": 926.3188190787038,
"height": 553.452795998601,
"content": "## Generate an image with Dall-E-3 and send it via Telegram"
},
"typeVersion": 1
},
{
"id": "1c7a204b-3ed7-47bd-a434-202b05272d18",
"name": "Send final reply",
"type": "n8n-nodes-base.telegram",
"onError": "continueErrorOutput",
"position": [
2140,
360
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Listen for incoming events').first().json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "9dexJXnlVPA6wt8K",
"name": "Chat & Sound"
}
},
"typeVersion": 1.1
},
{
"id": "bebbe9d4-47ba-4c13-9e1e-d36bfe6e472e",
"name": "Send back an image",
"type": "n8n-nodes-base.telegramTool",
"position": [
2020,
580
],
"parameters": {
"file": "={{ $fromAI(\"url\", \"a valid url of an image\", \"string\", \" \") }}",
"chatId": "={{ $('Listen for incoming events').first().json.message.from.id }}",
"operation": "sendDocument",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "9dexJXnlVPA6wt8K",
"name": "Chat & Sound"
}
},
"typeVersion": 1.2
},
{
"id": "38f2410d-bd55-4ddf-8aaa-4e28919de78f",
"name": "Generate image in Dalle",
"type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
"position": [
1880,
580
],
"parameters": {
"url": "https://api.openai.com/v1/images/generations",
"method": "POST",
"sendBody": true,
"authentication": "predefinedCredentialType",
"parametersBody": {
"values": [
{
"name": "model",
"value": "dall-e-3",
"valueProvider": "fieldValue"
},
{
"name": "prompt"
}
]
},
"toolDescription": "Call this tool to request a Dall-E-3 model, when the user asks to draw something. If you gеt a response from this tool, forward it to the Telegram tool.",
"nodeCredentialType": "openAiApi"
},
"credentials": {
"openAiApi": {
"id": "rveqdSfp7pCRON1T",
"name": "Ted's Tech Talks OpenAi"
}
},
"typeVersion": 1.1
},
{
"id": "34265eab-9f37-475a-a2ae-a6c37c69c595",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1780,
360
],
"parameters": {
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "=You are a helpful assistant. You are communicating with a user named {{ $json.message.from.first_name }}. Address the user by name every time. If the user asks for an image, always send the link to the image in the final reply."
},
"promptType": "define"
},
"typeVersion": 1.7
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "b36989c5-295a-4df6-84e9-776815509bc9",
"connections": {
"AI Agent": {
"main": [
[
{
"node": "Send final reply",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Send back an image": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Generate image in Dalle": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Listen for incoming events": {
"main": [
[
{
"node": "AI Agent",
"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
- @N8N/N8N Nodes Langchain.Lmchatopenai
- @N8N/N8N Nodes Langchain.Memorybufferwindow
- Telegramtrigger
- Stickynote
- Telegram
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
- 在n8n中导入工作流JSON文件
- 配置Gmail节点的认证信息
- 设置AI分类器的API密钥
- 自定义分类规则和标签映射
- 测试工作流执行
- 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