Multi-format document processing for RAG chatbot with Google Drive & Supabase

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 searchable for the RAG agent.

Key Features & Workflow:

Google Drive Trigger: The workflow starts automatically when a new file is created in a designated folder (named "DOCUMENTS" in this template).

Smart File Handling: A Switch node routes the file based on its MIME type (e.g., PDF, Excel, Google Doc, Word Doc) for correct processing.

Multi-Format Extraction:

PDF: Text is extracted directly using the Extract PDF Text node.

Google Docs: Files are downloaded and converted to plain text (text/plain) and processed by the Extract from Text File node.

Excel: Data is extracted, aggregated, and concatenated into a single text block for embedding.