Agent Milvus tool
工作流概述
这是一个包含21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": "A5R7XYSzrCJKlw9k",
"meta": {
"instanceId": "2c4c1e23e7b067270c08aab616bada21d0c384d16f212b23cf1143c6baa09219",
"templateCredsSetupCompleted": true
},
"name": "Agent Milvus tool",
"tags": [
{
"id": "msnDWKHQmwMDxWQH",
"name": "Milvus",
"createdAt": "2025-04-16T12:48:14.539Z",
"updatedAt": "2025-04-16T12:48:14.539Z"
},
{
"id": "tnCpo8hq8uKrdASK",
"name": "AI",
"createdAt": "2025-04-16T12:47:57.976Z",
"updatedAt": "2025-04-16T12:47:57.976Z"
}
],
"nodes": [
{
"id": "cfe6264a-2be1-4d1e-974b-ee05ca8ae9ab",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-280,
-40
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c0665cc9-2bce-48db-a3bc-15baac68e569",
"name": "Fetch Essay List",
"type": "n8n-nodes-base.httpRequest",
"position": [
-20,
-40
],
"parameters": {
"url": "http://www.paulgraham.com/articles.html",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "00bcdc0b-eb6d-41eb-ac0d-a6710d6232e4",
"name": "Extract essay names",
"type": "n8n-nodes-base.html",
"position": [
180,
-40
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "essay",
"attribute": "href",
"cssSelector": "table table a",
"returnArray": true,
"returnValue": "attribute"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "523c319e-d1c7-4214-a725-dc557f6471a2",
"name": "Split out into items",
"type": "n8n-nodes-base.splitOut",
"position": [
380,
-40
],
"parameters": {
"options": {},
"fieldToSplitOut": "essay"
},
"typeVersion": 1
},
{
"id": "be155368-99f5-43b3-ba6c-50cccf2b72d2",
"name": "Fetch essay texts",
"type": "n8n-nodes-base.httpRequest",
"position": [
780,
-40
],
"parameters": {
"url": "=http://www.paulgraham.com/{{ $json.essay }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "92af113c-dd71-4ddd-b50a-f5932392ed82",
"name": "Limit to first 3",
"type": "n8n-nodes-base.limit",
"position": [
580,
-40
],
"parameters": {
"maxItems": 3
},
"typeVersion": 1
},
{
"id": "1a1893c4-e8b2-454a-b49f-a0b0f3c01aca",
"name": "Extract Text Only",
"type": "n8n-nodes-base.html",
"position": [
1100,
-40
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "data",
"cssSelector": "body",
"skipSelectors": "img,nav"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "d14ae606-f002-4fde-a896-bf1c7fa675b2",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-100,
-160
],
"parameters": {
"width": 1071.752021563343,
"height": 285.66037735849045,
"content": "## Scrape latest Paul Graham essays"
},
"typeVersion": 1
},
{
"id": "dfb0cb32-9d7c-4588-b75e-0b79231eb72a",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1020,
-160
],
"parameters": {
"width": 625,
"height": 607,
"content": "## Load into Milvus vector database"
},
"typeVersion": 1
},
{
"id": "862a1a02-50e2-42af-9fa9-eb3a4f2ca463",
"name": "Recursive Character Text Splitter1",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1440,
300
],
"parameters": {
"options": {},
"chunkSize": 6000
},
"typeVersion": 1
},
{
"id": "91ac110a-57db-44b1-b22f-d2a63f22f173",
"name": "Milvus Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
"position": [
1320,
-40
],
"parameters": {
"mode": "insert",
"options": {
"clearCollection": true
},
"milvusCollection": {
"__rl": true,
"mode": "list",
"value": "n8n_test",
"cachedResultName": "n8n_test"
}
},
"credentials": {
"milvusApi": {
"id": "8tMHHoLiWXIAXa7S",
"name": "Milvus account"
}
},
"typeVersion": 1.1
},
{
"id": "456e917f-d466-4ec8-8df9-3774ba58151d",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
60,
360
],
"parameters": {
"options": {}
},
"typeVersion": 1.9
},
{
"id": "a5c5f308-097d-4fe0-92be-d717fd1e0b74",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-280,
360
],
"webhookId": "cd2703a7-f912-46fe-8787-3fb83ea116ab",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "dc352f07-335f-47cb-8270-32a4a0b87df7",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-460,
-200
],
"parameters": {
"width": 280,
"height": 180,
"content": "## Step 1
1. Set up a Milvus server based on [this guide](https://milvus.io/docs/install_standalone-docker-compose.md). And then create a collection named `n8n_test`.
2. Click this workflow to load scrape and load Paul Graham essays to Milvus collection.
"
},
"typeVersion": 1
},
{
"id": "5c9e9871-c9c1-458e-b35c-eab87ac5ca26",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1360,
180
],
"parameters": {
"options": {},
"jsonData": "={{ $('Extract Text Only').item.json.data }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "5b202001-525c-4481-a263-56b69c9b1bd8",
"name": "Milvus Vector Store as tool",
"type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
"position": [
180,
560
],
"parameters": {
"mode": "retrieve-as-tool",
"toolName": "milvus_knowledge_base",
"toolDescription": "useful when you need to retrieve information",
"milvusCollection": {
"__rl": true,
"mode": "list",
"value": "n8n_test",
"cachedResultName": "n8n_test"
}
},
"credentials": {
"milvusApi": {
"id": "8tMHHoLiWXIAXa7S",
"name": "Milvus account"
}
},
"typeVersion": 1.1
},
{
"id": "6b5b95c7-dde2-4c3f-952b-97a8f5c267c9",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-460,
260
],
"parameters": {
"width": 280,
"height": 120,
"content": "## Step 2
Start to chat with the AI Agent with Milvus tool"
},
"typeVersion": 1
},
{
"id": "5ccfe636-2bb3-4026-98f0-57ba8d5780f0",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1220,
200
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "982622e9-af05-4ee2-ae7d-166c47f75ce9",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
20,
560
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "abd97878-cce6-44a0-8bae-91536ea48b6b",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
200,
740
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "00d49aab-3200-44fc-a0fc-8f7f22998617",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
300
],
"parameters": {
"color": 7,
"width": 574,
"height": 629,
"content": ""
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "8e6f0bb5-1fb5-48fc-8a1f-488362be4ef7",
"connections": {
"Fetch Essay List": {
"main": [
[
{
"node": "Extract essay names",
"type": "main",
"index": 0
}
]
]
},
"Limit to first 3": {
"main": [
[
{
"node": "Fetch essay texts",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Milvus Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract Text Only": {
"main": [
[
{
"node": "Milvus Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Fetch essay texts": {
"main": [
[
{
"node": "Extract Text Only",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Milvus Vector Store as tool",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Milvus Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Extract essay names": {
"main": [
[
{
"node": "Split out into items",
"type": "main",
"index": 0
}
]
]
},
"Split out into items": {
"main": [
[
{
"node": "Limit to first 3",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Milvus Vector Store as tool": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "Fetch Essay List",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter1": {
"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
- Manualtrigger
- Httprequest
- Html
- Splitout
- Limit
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