AI Agents

Convert Notion pages to vector embeddings and store in Supabase

9 nodes 316 128 Automatic trigger
Download

Workflow Description

Automates extraction of Notion pages, splits content into manageable chunks, generates vector embeddings using OpenAI, and stores them in Supabase for semantic search and AI-powered retrieval without manual data pipelines.

How it works

  1. 1.Trigger on Notion page creation or update
  2. 2.Load and retrieve full page content from Notion
  3. 3.Split text into chunks using token-based segmentation
  4. 4.Generate vector embeddings via OpenAI API
  5. 5.Store embeddings and original text in Supabase vector store

Use cases

  • Build semantic search over company documentation and internal wikis
  • Create retrieval-augmented generation (RAG) systems powered by your knowledge base
  • Automate indexing of constantly updated Notion workspaces for AI assistants

Requirements

  • Notion workspace with database access via API key
  • OpenAI API key with sufficient credits
  • Supabase project configured with pgvector extension enabled

Service Value

Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.

Apps Used

OpenAI Text Splitter Notion Document Default Data Loader Vector Store

Details

Trigger Automatic trigger
Nodes 9
Apps 5
Views 316
Downloads 128

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (9)

Sticky Note

Sticky Note

#1

Embeddings OpenAI

OpenAI

#2

Token Splitter

Text Splitter Token Splitter

#3

Notion - Page Added Trigger

Notion

#4

Notion - Retrieve Page Content

Notion

#5

Filter Non-Text Content

Filter

#6

Summarize - Concatenate Notion's blocks content

Summarize

#7

Create metadata and load content

Document Default Data Loader

#8

Supabase Vector Store

Vector Store Supabase

#9