RAG Q&A from Documents: Supabase, OpenAI & Cohere Reranker
Build AI agents that answer questions from your documents using RAG with Supabase vector store, OpenAI models, and Cohere reranking for precise, context-rich responses.
This advanced RAG (Retrieval Augmented Generation) workflow empowers AI agents to provide accurate answers to user queries by retrieving relevant information from your own documents. It leverages Supabase as a vector database to store metadata-rich embeddings, OpenAI for generating embeddings (e.g., text-embedding-3-small) and responses via GPT models, and Cohere Reranker to boost relevance by re-ranking retrieved chunks. The pipeline includes PDF extraction, metadata enrichment via a dedicated
Platform
n8n
Category
Real Estate
Price
$24.99
Creator
Maxim Luong
RAG
Retrieval Augmented Generation
Supabase
OpenAI
Cohere Reranker
Vector Store
AI Chatbot
Document Q&A
Embeddings
Real Estate
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.