Multi-format document processing for RAG chatbot with Google Drive & Supabase
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 16 nodes and runs on Google Drive events (file created). Along the way it connects Google Drive, Embeddings OpenAI and Supabase Vector Store.
How it runs
Trigger: On Google Drive events (file created).
- Set File ID (Edit Fields (Set)): sets 2 fields: file_id, file_type
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Switch: routes items into 6 branches
- Download File (Google Drive): download
- Extract PDF Text (Extract from File): extracts data from a file (pdf)
- Extract from Text File (Extract from File): extracts data from a file (text)
- Extract from Excel (Extract from File): extracts data from a file (xlsx)
- Convert to Google Doc (HTTP Request): calls an HTTP API (POST)
- Insert into Supabase Vectorstore (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Embeddings OpenAI; document loader: Enhanced Default Data Loader
- Aggregate: combines items into one
…plus 2 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 (13)
- Aggregate
n8n-nodes-base.aggregate - Summarize
n8n-nodes-base.summarize - Extract from File
n8n-nodes-base.extractFromFile - HTTP Request
n8n-nodes-base.httpRequest - Google Drive
n8n-nodes-base.googleDrive - Edit Fields (Set)
n8n-nodes-base.set - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Switch
n8n-nodes-base.switch - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase
From the author
This n8n workflow is the data ingestion pipeline for the "RAG System V2" chatbot. It automatically monitors a specific Google Drive folder for new files, processes them based on their type, and inserts their content into a Supabase vector database to make it…