Index Notion pages as vector embeddings in Supabase with OpenAI
Loading workflow…
Workflow Description
Automated workflow that extracts Notion pages, splits them into manageable chunks, converts each chunk into numerical vectors using OpenAI embeddings, and stores them in Supabase for semantic search and rapid retrieval capabilities.
How it works
- 1.Trigger automatically when a Notion page is created or updated
- 2.Load page content and split it into smaller text segments using token-based splitting
- 3.Generate vector embeddings for each segment using OpenAI's embedding model
- 4.Store vectors and source metadata in Supabase vector database for querying
Use cases
- Build semantic search engine across Notion knowledge base documentation
- Enable AI-powered Q&A system for employees using company documentation
- Improve search relevance through semantic understanding rather than keyword matching
Requirements
- Connected Notion workspace with API access and page read permissions
- OpenAI API key with embedding model access
- Active Supabase project with vector storage tables configured
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (8)
Sticky Note
Sticky Note
Embeddings OpenAI
OpenAI
Token Splitter
Text Splitter Token Splitter
Notion - Page Added Trigger
Notion
Notion - Retrieve Page Content
Notion
Filter Non-Text Content
Filter
Summarize - Concatenate Notion's blocks content
Summarize
Create metadata and load content
Document Default Data Loader
Supabase Vector Store
Vector Store Supabase
Fresh workflows, straight to your inbox
Get newly published DROPIDEA workflows, a clear overview of what they do, and a link to explore them.
- New workflows
- Clear overviews
- Setup guides