WhatsApp RAG chatbot with Supabase, Gemini 2.5 Flash, and OpenAI embeddings

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 for semantic search, and Gemini 2.5 Flash LLM for generating high-quality responses.

Use cases are many: Turn your WhatsApp into a knowledge assistant for FAQs, customer support, or internal company documents — all without coding.

---

Good to know

- The workflow uses OpenAI embeddings for both document embeddings and query embeddings, ensuring accurate semantic search. - Gemini 2.5 Flash LLM is used to generate user-friendly answers from the retrieved context. - Messages are processed in real-time and sent back directly to WhatsApp. - Workflow is modular — you can split document ingestion and query handling for large-scale setups. - Supabase and WhatsApp API credentials must be configured before running.

---

How it works