Telegram RAG pdf
工作流概述
这是一个包含20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
{
"id": "5Ycrm1MuK8htwd96",
"meta": {
"instanceId": "e5595d8cd58f3a24b5a8cf05dd852846c05423873db868a2b7d01a778210c45a",
"templateCredsSetupCompleted": true
},
"name": "Telegram RAG pdf",
"tags": [],
"nodes": [
{
"id": "9fbce801-8c42-43a4-bc70-d93042d68b2c",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-220,
240
],
"webhookId": "b178f034-9997-4832-9bb4-a43c3015506e",
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1.1
},
{
"id": "1bfc1fbd-86b1-4a8a-9301-fe54497f5acd",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
720,
460
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "d5ad7851-ed40-4b3a-b0d5-aeaf04362f1c",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
860,
460
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "fed803d0-49a2-4b82-8f20-a02a10caa027",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
940,
680
],
"parameters": {
"options": {},
"chunkSize": 3000,
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "ab60f36f-fada-4812-8dbd-441ad372cb80",
"name": "Stop and Error",
"type": "n8n-nodes-base.stopAndError",
"position": [
220,
840
],
"parameters": {
"errorMessage": "An error occurred"
},
"typeVersion": 1
},
{
"id": "c87f1db3-7cc9-4063-9895-4b4d68ea53a1",
"name": "Question and Answer Chain",
"type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
"position": [
-280,
500
],
"parameters": {
"text": "={{ $json.message.text }}
Search the database with the retriever for information for the answer",
"promptType": "define"
},
"typeVersion": 1.3
},
{
"id": "c9bc4c80-8e57-48bc-a405-131ed7348c1d",
"name": "Vector Store Retriever",
"type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
"position": [
-240,
680
],
"parameters": {},
"typeVersion": 1
},
{
"id": "0217056f-2b71-4308-adf1-19dcd4d2cc11",
"name": "Pinecone Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
-280,
860
],
"parameters": {
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "telegram",
"cachedResultName": "telegram"
}
},
"credentials": {
"pineconeApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "693f9026-f47f-48dc-8e5d-e8b832a37235",
"name": "Groq Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGroq",
"position": [
-380,
660
],
"parameters": {
"model": "llama-3.1-70b-versatile",
"options": {}
},
"credentials": {
"groqApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "c7acf014-138f-4be7-b569-c309bb10e50d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
500,
73.04879287725316
],
"parameters": {
"color": 7,
"width": 1139.5159692915001,
"height": 873.6068151028411,
"content": "# Load data into database
Fetch file from **Telegram**, split it into chunks and insert into **Pinecone** index, a message from **Telegram** will be sent just to let the user know that the process finished"
},
"typeVersion": 1
},
{
"id": "dd3b9d8b-5771-4a09-8c1b-794cb8737d5d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-878.769,
400
],
"parameters": {
"color": 7,
"width": 1344.7918019808176,
"height": 806.8716167324012,
"content": "# Chat with Database
1. **Receive** the incoming chat message.
2. **Retrieve** relevant chunks from the _vector store_.
3. **Pass** these chunks to the model.
The model will use the retrieved information to **formulate a precise response**.
"
},
"typeVersion": 1
},
{
"id": "9aaf575a-5e40-407c-951c-10b1d16e5d3c",
"name": "Check If is a document",
"type": "n8n-nodes-base.if",
"position": [
220,
240
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8839993b-9fe7-4e1e-a1cc-fe5de6b0bb62",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.document }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2
},
{
"id": "c1edb6bf-ba95-4a5f-9626-add673274086",
"name": "Change to application/pdf",
"type": "n8n-nodes-base.code",
"position": [
700,
220
],
"parameters": {
"jsCode": "// Função para modificar os metadados do arquivo binário
function modifyBinaryMetadata(items) {
for (const item of items) {
if (item.binary && item.binary.data) {
// Modifica o tipo MIME
item.binary.data.mimeType = 'application/pdf';
// Garante que o nome do arquivo termine com .pdf
if (!item.binary.data.fileName.toLowerCase().endsWith('.pdf')) {
item.binary.data.fileName += '.pdf';
}
// Atualiza o contentType no fileType (se existir)
if (item.binary.data.fileType) {
item.binary.data.fileType.contentType = 'application/pdf';
}
}
}
return items;
}
// Aplica a modificação e retorna os itens atualizados
return modifyBinaryMetadata($input.all());"
},
"typeVersion": 2
},
{
"id": "ea4d4e74-8954-47f0-a3a0-662d47ea2298",
"name": "Telegram get File",
"type": "n8n-nodes-base.telegram",
"position": [
520,
220
],
"parameters": {
"fileId": "={{ $json.message.document.file_id }}",
"resource": "file"
},
"credentials": {
"telegramApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "cf548bee-d5d5-4f1a-a059-932ea163e155",
"name": "Embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-100,
1080
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "e3bd4759-80cc-42bb-ba53-f9e88e9ba916",
"name": "Telegram Response",
"type": "n8n-nodes-base.telegram",
"onError": "continueErrorOutput",
"position": [
160,
560
],
"parameters": {
"text": "={{ $json.response.text }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "e478df48-9e6d-4a84-89be-beb569914ae3",
"name": "Telegram Response about Database",
"type": "n8n-nodes-base.telegram",
"onError": "continueErrorOutput",
"position": [
1400,
220
],
"parameters": {
"text": "={{ $json.metadata.pdf.totalPages }} pages saved on Pinecone",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "5be7a321-1be6-4173-83de-3d569666718d",
"name": "Stop and Error1",
"type": "n8n-nodes-base.stopAndError",
"position": [
1400,
580
],
"parameters": {
"errorMessage": "An error occurred."
},
"typeVersion": 1
},
{
"id": "aae26861-f34d-4b59-bd99-3662fbd6676c",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
880,
220
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "telegram",
"cachedResultName": "telegram"
}
},
"credentials": {
"pineconeApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "312fb807-4225-4630-ab32-aa12fe07c127",
"name": "Limit to 1",
"type": "n8n-nodes-base.limit",
"position": [
1220,
220
],
"parameters": {},
"typeVersion": 1
}
],
"active": true,
"pinData": {},
"settings": {
"timezone": "America/Sao_Paulo",
"callerPolicy": "workflowsFromSameOwner",
"executionOrder": "v1",
"saveManualExecutions": true
},
"versionId": "03612d23-6630-4ec6-8738-1dae593c8d23",
"connections": {
"Embeddings": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Limit to 1": {
"main": [
[
{
"node": "Telegram Response about Database",
"type": "main",
"index": 0
}
]
]
},
"Groq Chat Model": {
"ai_languageModel": [
[
{
"node": "Question and Answer Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Check If is a document",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Telegram Response": {
"main": [
[],
[
{
"node": "Stop and Error",
"type": "main",
"index": 0
}
]
]
},
"Telegram get File": {
"main": [
[
{
"node": "Change to application/pdf",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Pinecone Vector Store": {
"main": [
[
{
"node": "Limit to 1",
"type": "main",
"index": 0
}
]
]
},
"Check If is a document": {
"main": [
[
{
"node": "Telegram get File",
"type": "main",
"index": 0
}
],
[
{
"node": "Question and Answer Chain",
"type": "main",
"index": 0
}
]
]
},
"Pinecone Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Retriever",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Vector Store Retriever": {
"ai_retriever": [
[
{
"node": "Question and Answer Chain",
"type": "ai_retriever",
"index": 0
}
]
]
},
"Change to application/pdf": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Question and Answer Chain": {
"main": [
[
{
"node": "Telegram Response",
"type": "main",
"index": 0
}
]
]
},
"Telegram Response about Database": {
"main": [
[],
[
{
"node": "Stop and Error1",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"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
- Telegramtrigger
- @N8N/N8N Nodes Langchain.Embeddingsopenai
- @N8N/N8N Nodes Langchain.Documentdefaultdataloader
- @N8N/N8N Nodes Langchain.Textsplitterrecursivecharactertextsplitter
- Stopanderror
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