RAG & Knowledge Basesfree

WhatsApp RAG Chatbot with Supabase, Gemini 2.5 Flash, and OpenAI Embeddings

by Manav DesaiUpdated Aug 2026

RequiresOpenAIGoogle Gemini

1/5

STEPS · 11

Starts on a Whats App event

On a WhatsApp message, retrieves context from a Supabase vector store using OpenAI embeddings and replies via Google Gemini.

WhatsApp RAG Assistant

On a WhatsApp message, an OpenAI agent answers using an in-memory vector store with conversation memory and replies via WhatsApp.

When files are added to Google Drive, embeds them into Pinecone with Gemini, letting a chat agent answer questions over the documents.

When files are added to Google Drive, indexes them into Milvus with Cohere embeddings so an OpenAI chat agent answers questions.