Seed a Supabase AI knowledge base from Notion with Ollama embeddings
Ready for 3.0What this workflow does
This AI workflow has 11 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Notion, Supabase Vector Store and Embeddings Ollama.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Remove Existing Embeddings (HTTP Request): calls an HTTP API (DELETE)
- Get Notion Pages (Notion): get many (database page)
- Fetch Page Blocks (Notion): get many (block)
- Aggregate Block Text (Code): runs custom JavaScript code
- Skip Empty Pages (If): checks a condition and branches into true / false
- Insert into Knowledge Store (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Generate Embeddings Ollama; document loader: Load Default Data
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Manual Trigger
n8n-nodes-base.manualTrigger - Notion
n8n-nodes-base.notion - Code
n8n-nodes-base.code - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Schedule Trigger
n8n-nodes-base.scheduleTrigger - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest
From the author
Quick overview This n8n template ingests your entire Notion database into a Supabase vector store, making every page searchable by an AI assistant or chatbot. It runs on a schedule to keep your knowledge base in sync automatically, and each run is safe to…