Notion to Vector Embeddings (Supabase)

Inside this workflow

Overview

Extract Notion pages, split into chunks, generate OpenAI embeddings, and store vectors in Supabase. Enables semantic search and RAG over your Notion database. Perfect for building AI chatbots trained on Notion knowledge bases or knowledge base search. Nodes & apps: Webhook trigger, Filter node, Summarize, OpenAI Embeddings, LangChain Text Splitter. Credentials needed: 1. Notion API key 2. OpenAI API key (for embeddings) 3. Supabase API key Setup steps: 1. Connect Notion API and select database 2. Configure text splitting (chunk size, overlap) 3. Set OpenAI embedding model 4. Map Supabase vector table schema 5. Configure metadata storage (page titles, URLs) 6. Test with sample Notion pages 7. Build semantic search endpoint 8. Deploy RAG chatbot or knowledge base search Difficulty: High | Setup time: 20 minutes | Price: $36 | Nodes: 9 | Source: felipfr/awesome-n8n-workflows

What's included

Quickstart

1. 01

   Download the JSON

   With an active Library Pass, download the workflow file right from this page or your dashboard.

2. 02

   Import into n8n

   Choose Import from File and select the downloaded JSON. The full agent graph appears, ready to configure.

3. 03

   Plug in credentials

   Each integration node prompts for credentials on first run. The setup guide lists every credential the agent expects.

4. 04

   Activate and test

   Run once with sample input, confirm the expected output, then flip the activate toggle.

Sign in to leave a review.