Sync Notion knowledge base with Vapi assistants and Pinecone using OpenAI
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 25 nodes and runs on a schedule (every day at 02:00). Along the way it connects Notion, Pinecone Vector Store and Embeddings OpenAI. It also calls api.vapi.ai over HTTP.
How it runs
Trigger: On a schedule (every day at 02:00).
- Remove Old Vectors from Pinecone (HTTP Request): calls an HTTP API (POST)
- Wait: waits 15 seconds
- Load Notion Services Data (Notion): get many (database page)
- Load Notion FAQ Data (Notion): get many (database page)
- Load Notion Qualification Script (Notion): get many (database page)
- Load Notion Dialogue Tree (Notion): get many (database page)
- Load Notion Objection Handling (Notion): get many (database page)
- Load Notion Disclaimers (Notion): get many (database page)
- Merge Notion Content (Code): runs custom JavaScript code
- Upsert Documents to Pinecone (Pinecone Vector Store): stores documents in the Pinecone vector store, with embeddings: Generate OpenAI Embeddings; document loader: Load Documents for Upsert
…plus 11 more steps. See the full node list below.
Services it uses
HTTP calls to: api.vapi.ai
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 (9)
- Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Wait
n8n-nodes-base.wait - Notion
n8n-nodes-base.notion - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
From the author
Quick overview This workflow runs daily to pull knowledge base content from Notion, generate OpenAI embeddings, upsert the documents into Pinecone, and upload two language-specific text knowledge files to Vapi so your voice assistant’s query tool and…