Index Google Drive files into a Supabase vector store with OpenAI embeddings
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 26 nodes and runs when a chat message arrives (plus 2 other triggers). Along the way it connects Embeddings OpenAI, Google Drive, Supabase and Supabase Vector Store and 1 more.
How it runs
Trigger: When a chat message arrives (plus 2 other triggers).
- Create Docs Table and Match Fn (Postgres): run a query
- Loop Over Drive Files (Loop Over Items (Split in Batches)): loops over the items in batches
- Create Document Metadata Table (Postgres): run a query
- Set File Metadata Fields (Edit Fields (Set)): sets 4 fields: file_id, file_type, file_title…
- Create Document Rows Table (Postgres): run a query
- Delete Old Doc Rows in Supabase (Supabase): delete
- Delete Old Data Rows in Supabase (Supabase): delete
- Insert Document Metadata to DB (Postgres): create or update
- Download File from Drive (Google Drive): download
- Route by File Type (Switch): routes items into 4 branches
…plus 10 more steps. See the full node list below.
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 (15)
- Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Google Drive
n8n-nodes-base.googleDrive - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Extract from File
n8n-nodes-base.extractFromFile - Supabase
n8n-nodes-base.supabase - Edit Fields (Set)
n8n-nodes-base.set - Aggregate
n8n-nodes-base.aggregate - Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter - Summarize
n8n-nodes-base.summarize - Switch
n8n-nodes-base.switch - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Postgres
n8n-nodes-base.postgres - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger
From the author
📺 Full walkthrough video: https://youtu.be/r5kNla0O7I Author: Cole Medin Who it's for This workflow is for developers, data engineers, and knowledge management teams who need to automatically ingest documents stored in Google Drive into a searchable vector…