WhatsApp RAG chatbot with Supabase, Gemini 2.5 Flash, and OpenAI embeddings
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 11 nodes and runs on WhatsApp events (messages). Along the way it connects Supabase Vector Store, WhatsApp Business Cloud, Embeddings OpenAI and Google Gemini Chat Model.
How it runs
Trigger: On WhatsApp events (messages).
- Check if Query or Document (Switch): routes items into 2 branches
- RAG Query Agent (AI Agent): runs an AI agent, with model: Google Gemini LLM; 1 tool (Retrieve Context from Supabase)
- Get Document URL (WhatsApp Business Cloud): media url get
- Send WhatsApp Reply (WhatsApp Business Cloud): send
- Download WhatsApp Document (HTTP Request): calls an HTTP API
- Store Embeddings in Supabase (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Generate OpenAI Embeddings; document loader: Convert File to Text
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (9)
- Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Switch
n8n-nodes-base.switch - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - AI Agent
@n8n/n8n-nodes-langchain.agent - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - HTTP Request
n8n-nodes-base.httpRequest
From the author
WhatsApp RAG Chatbot with Supabase, Gemini 2.5 Flash, and OpenAI Embeddings This n8n template demonstrates how to build a WhatsApp-based AI chatbot that answers user questions using document retrieval (RAG) powered by Supabase for storage, OpenAI embeddings…