WhatsApp RAG Chatbot with Supabase, Gemini & OpenAI Embeddings
Build a WhatsApp AI chatbot using RAG with Supabase storage, OpenAI embeddings for semantic search, and Gemini 2.5 Flash for responses. Handles queries and document uploads in real-time.
This n8n workflow creates a powerful WhatsApp-based RAG (Retrieval-Augmented Generation) chatbot. It triggers on incoming WhatsApp messages via webhook, checks if it's a query or document upload, processes files by extracting text, generating OpenAI embeddings, and storing them in Supabase for vector search. For queries, it embeds the user input, retrieves relevant documents from Supabase, and uses Gemini 2.5 Flash LLM to generate contextual, accurate responses sent back instantly to WhatsApp.
Platform
n8n
Category
Crypto & Blockchain
Price
$24.99
Creator
QualityWorkflows
whatsapp
rag
chatbot
supabase
gemini
openai
embeddings
ai
semantic-search
customer-support
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.