Store Notion's Pages as Vector Documents into Supabase with OpenAI
工作流概述
这是一个包含9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": "DvP6IHWymTIVg8Up",
"meta": {
"instanceId": "b9faf72fe0d7c3be94b3ebff0778790b50b135c336412d28fd4fca2cbbf8d1f5",
"templateCredsSetupCompleted": true
},
"name": "Store Notion's Pages as Vector Documents into Supabase with OpenAI",
"tags": [],
"nodes": [
{
"id": "495609cd-4ca0-426d-8413-69e771398188",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
400
],
"parameters": {
"width": 637.1327972412109,
"height": 1113.7434387207031,
"content": "## Store Notion's Pages as Vector Documents into Supabase
**This workflow assumes you have a Supabase project with a table that has a vector column. If you don't have it, follow the instructions here:** [Supabase Vector Columns Guide](https://supabase.com/docs/guides/ai/vector-columns)
## Workflow Description
This workflow automates the process of storing Notion pages as vector documents in a Supabase database with a vector column. The steps are as follows:
1. **Notion Page Added Trigger**:
- Monitors a specified Notion database for newly added pages. You can create a specific Notion database where you copy the pages you want to store in Supabase.
- Node: `Page Added in Notion Database`
2. **Retrieve Page Content**:
- Fetches all block content from the newly added Notion page.
- Node: `Get Blocks Content`
3. **Filter Non-Text Content**:
- Excludes blocks of type \"image\" and \"video\" to focus on textual content.
- Node: `Filter - Exclude Media Content`
4. **Summarize Content**:
- Concatenates the Notion blocks content to create a single text for embedding.
- Node: `Summarize - Concatenate Notion's blocks content`
5. **Store in Supabase**:
- Stores the processed documents and their embeddings into a Supabase table with a vector column.
- Node: `Store Documents in Supabase`
6. **Generate Embeddings**:
- Utilizes OpenAI's API to generate embeddings for the textual content.
- Node: `Generate Text Embeddings`
7. **Create Metadata and Load Content**:
- Loads the block content and creates associated metadata, such as page ID and block ID.
- Node: `Load Block Content & Create Metadata`
8. **Split Content into Chunks**:
- Divides the text into smaller chunks for easier processing and embedding generation.
- Node: `Token Splitter`
"
},
"typeVersion": 1
},
{
"id": "3f3e65dc-2b26-407c-87e5-52ba3b315fed",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
2200,
760
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "6d2579b8-376f-44c3-82e8-9dc608efd98b",
"name": "Token Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"position": [
2340,
960
],
"parameters": {
"chunkSize": 256,
"chunkOverlap": 30
},
"typeVersion": 1
},
{
"id": "79b3c147-08ca-4db4-9116-958a868cbfd9",
"name": "Notion - Page Added Trigger",
"type": "n8n-nodes-base.notionTrigger",
"position": [
1180,
520
],
"parameters": {
"simple": false,
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"databaseId": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "",
"cachedResultName": ""
}
},
"typeVersion": 1
},
{
"id": "e4a6f524-e3f5-4d02-949a-8523f2d21965",
"name": "Notion - Retrieve Page Content",
"type": "n8n-nodes-base.notion",
"position": [
1400,
520
],
"parameters": {
"blockId": {
"__rl": true,
"mode": "url",
"value": "={{ $json.url }}"
},
"resource": "block",
"operation": "getAll",
"returnAll": true
},
"typeVersion": 2.2
},
{
"id": "bfebc173-8d4b-4f8f-a625-4622949dd545",
"name": "Filter Non-Text Content",
"type": "n8n-nodes-base.filter",
"position": [
1620,
520
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "e5b605e5-6d05-4bca-8f19-a859e474620f",
"operator": {
"type": "string",
"operation": "notEquals"
},
"leftValue": "={{ $json.type }}",
"rightValue": "image"
},
{
"id": "c7415859-5ffd-4c78-b497-91a3d6303b6f",
"operator": {
"type": "string",
"operation": "notEquals"
},
"leftValue": "={{ $json.type }}",
"rightValue": "video"
}
]
}
},
"typeVersion": 2
},
{
"id": "b04939f9-355a-430b-a069-b11800066313",
"name": "Summarize - Concatenate Notion's blocks content",
"type": "n8n-nodes-base.summarize",
"position": [
1920,
520
],
"parameters": {
"options": {
"outputFormat": "separateItems"
},
"fieldsToSummarize": {
"values": [
{
"field": "content",
"separateBy": "
",
"aggregation": "concatenate"
}
]
}
},
"typeVersion": 1
},
{
"id": "0e64dbb5-20c1-4b90-b818-a1726aaf5112",
"name": "Create metadata and load content",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
2320,
760
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "pageId",
"value": "={{ $('Notion - Page Added Trigger').item.json.id }}"
},
{
"name": "createdTime",
"value": "={{ $('Notion - Page Added Trigger').item.json.created_time }}"
},
{
"name": "pageTitle",
"value": "={{ $('Notion - Page Added Trigger').item.json.properties.Page.title[0].text.content }}"
}
]
}
},
"jsonData": "={{ $('Summarize - Concatenate Notion's blocks content').item.json.concatenated_content }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "187aba6f-eaed-4427-8d40-b9da025fb37d",
"name": "Supabase Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
2200,
520
],
"parameters": {
"mode": "insert",
"options": {},
"tableName": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultName": ""
}
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "77f6b6f7-d699-4a7e-b3e7-fe8a60bde7ba",
"connections": {
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Create metadata and load content",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Filter Non-Text Content": {
"main": [
[
{
"node": "Summarize - Concatenate Notion's blocks content",
"type": "main",
"index": 0
}
]
]
},
"Notion - Page Added Trigger": {
"main": [
[
{
"node": "Notion - Retrieve Page Content",
"type": "main",
"index": 0
}
]
]
},
"Notion - Retrieve Page Content": {
"main": [
[
{
"node": "Filter Non-Text Content",
"type": "main",
"index": 0
}
]
]
},
"Create metadata and load content": {
"ai_document": [
[
{
"node": "Supabase Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Summarize - Concatenate Notion's blocks content": {
"main": [
[
{
"node": "Supabase Vector Store",
"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
- Stickynote
- @N8N/N8N Nodes Langchain.Embeddingsopenai
- @N8N/N8N Nodes Langchain.Textsplittertokensplitter
- Notiontrigger
- Notion
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