AI WhatsApp bot with memory for business

# AI assistant for WhatsApp with chat memory and knowledge base via Gemini & Pinecone

This automation template creates an intelligent AI assistant for WhatsApp that replies to customer messages, remembers conversation history, and leverages up-to-date information from an external knowledge base. Built on n8n, LangChain, Google Gemini, and vector memory in Pinecone.

## Who it´s for
- Business owners using WhatsApp for client communication
- Support teams needing fast responses without losing context
- Personal assistants aiming to automate messaging
- Teams integrating AI agents with corporate knowledge bases

## What the automation does
- Receives incoming WhatsApp messages via webhook (WAMM.pro)
- Triggers a LangChain agent powered by Google Gemini
- Retrieves context from two Pinecone indexes: general knowledge and user-specific chat history
- Sends generated replies back to WhatsApp via WAMM
- Stores full conversations as vector embeddings in Pinecone for persistent memory

## What´s included
- Ready-to-use n8n workflow
- Webhook handling and AI agent logic
- Integrations with WAMM.pro, Pinecone, Google Gemini API, OpenAI API
- Basic text instructions for setup and adaptation

## Requirements for setup
- n8n instance with workflow editing access
- WAMM.pro account with configured webhook
- Google Cloud project with Gemini API enabled
- Pinecone access with two indexes: knowledge_base and chat_history
- OpenAI API key for embedding generation

## Benefits and outcomes
- Personalized replies based on chat history
- Automatic use of updated knowledge base content
- Reduced workload for support operators
- Continuous bot learning through stored conversations

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat