Index Google Drive files into a Supabase vector store with OpenAI embeddings

Description

📺 Full walkthrough video: https://youtu.be/r5kN_la0O7I

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 database — supporting RAG (retrieval-augmented generation) pipelines or semantic search applications.

How it works

One-time setup: A chat trigger runs SQL queries to create the required Postgres tables (documents, document_metadata, document_rows) and the vector similarity match function in Supabase/Postgres.
Trigger: Two Google Drive triggers detect newly created or updated files in a watched folder and pass them into a batch loop.
Clean old data: For each file, stale document rows and vector embeddings are deleted from Supabase before re-processing.
Metadata upsert & download: Document metadata (ID, title, URL) is upserted into Postgres, then the file binary is downloaded from Google Drive.
Route by file type: A Switch node directs each file to the correct extractor — PDF, Word/Office document, Excel spreadsheet, or CSV.
Tabular data storage: Excel and CSV rows are inserted as raw JSONB records into Postgres and aggregated into a summary.
Embedding & storage: All extracted text (documents, PDFs, tabular summaries) is chunked with a character text splitter, embedded via OpenAI, and inserted into the Supabase vector store.

How to set up

[ ] Connect Google Drive OAuth2 credentials to the two trigger nodes and the download node
[ ] Add Supabase credentials to the delete and vector store insert nodes
[ ] Add Postgres credentials to all Postgres nodes (table creation, metadata upsert, schema update, row insert)
[ ] Set your OpenAI API key in the OpenAI Embeddings node
[ ] Run the setup flow once via the chat trigger to create all database tables and the vector match function
[ ] Set the Google Drive folder ID to watch in both trigger nodes
[ ] Tune the Character Text Splitter chunk size and overlap to fit your document sizes

Requirements

Google Drive account (OAuth2)
Supabase project with pgvector extension enabled
Postgres database (can be the Supabase Postgres instance)
OpenAI API key

How to customize

Add file types:** Extend the Switch node with additional branches (e.g., PowerPoint, plain text) and pair each with an appropriate extractor.
Swap the embedding model:** Replace text-embedding-3-small with a larger OpenAI model or an alternative provider (e.g., Cohere, Mistral) in the embeddings node.
Connect a RAG chatbot:** Pipe the Supabase vector store into an AI Agent or chain node to build a document Q&A assistant on top of the ingested files.