WhatsApp virtual agent with Gemini AI - handles text & voice with knowledge base
Ready for 3.0What this workflow does
This AI workflow has 15 nodes and runs on WhatsApp events (messages). Along the way it connects Google Gemini Chat Model, Vector Store Question Answer, Pinecone Vector Store and Embeddings Google Gemini and 1 more.
How it runs
Trigger: On WhatsApp events (messages).
- Audio/Message (Switch): routes items into 2 branches
- Get Audio URL (WhatsApp Business Cloud): media url get
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model; 1 tool (Answer questions with a vector store); memory: Simple Memory
- Audio Download (HTTP Request): calls an HTTP API
- Send message (WhatsApp Business Cloud): send
- Audio Convert (Code): runs custom JavaScript code
- Gemini speech to text (HTTP Request): calls an HTTP API (POST)
- Audio Prompt (Edit Fields (Set)): sets 1 field: candidates[0].content.parts[0].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 (12)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Switch
n8n-nodes-base.switch - Code
n8n-nodes-base.code
From the author
Overview This project is an AI-powered WhatsApp virtual agent built using n8n, designed to handle both text and voice-based customer messages automatically. The workflow integrates Google Gemini, Pinecone, and the WhatsApp Business API to provide intelligent,…