Two-Stage RAG Chatbot: OpenAI & Supabase Vector Search

A multi-stage retrieval chatbot that filters files by description before precise vector search, enhancing AI response accuracy for large document sets.

This n8n workflow builds a sophisticated two-stage document retrieval system integrated with OpenAI and Supabase vector store. It starts by querying file metadata descriptions via a Supabase RPC function to identify the most relevant files based on user input similarity scores. Only these top-matching files are then used for deeper vector similarity searches on document chunks, drastically reducing noise and improving retrieval precision. The benefits include optimized performance for handling
Platform
n8n
Category
Website Building
Price
$22.99
Creator
QualityWorkflows

How to import this workflow into n8n

  1. 1Purchase or download the workflow to get the n8n workflow JSON file.
  2. 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
  3. 3Open each node marked with a credential warning and connect your own accounts and API keys.
  4. 4Run the workflow once manually to verify the data flow, then toggle it to Active.

Related Website Building workflows

More from QualityWorkflows

Need this deployed? We'll set it up for you.

Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.