Build a WhatsApp AI shopping bot with virtual try-on using Gemini and GPT
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 70 nodes and runs on WhatsApp events (messages). Along the way it connects Redis, WhatsApp Business Cloud, OpenAI Chat Model and MongoDB and 5 more. It also calls generativelanguage.googleapis.com over HTTP.
How it runs
Trigger: On WhatsApp events (messages).
- Check if message is button or image (If): checks a condition and branches into true / false
- Route interactive vs image message (Switch): routes items into 2 branches
- Validate incoming message (Code): runs custom JavaScript code
- Parse button and user data (Code): runs custom JavaScript code
- Get VTO context from Redis (Redis): get
- Pass valid messages, block invalid (If): checks a condition and branches into true / false
- Route VTO vs order button tap (Switch): routes items into 2 branches
- Is VTO product ID stored in Redis? (If): checks a condition and branches into true / false
- Get user session from Redis (Redis): get
- Send validation error to user (WhatsApp Business Cloud): send
…plus 51 more steps. See the full node list below.
Services it uses
HTTP calls to: generativelanguage.googleapis.com
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 (23)
- Redis
n8n-nodes-base.redis - Code
n8n-nodes-base.code - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Mongo Db Tool
n8n-nodes-base.mongoDbTool - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - MongoDB Atlas Vector Store
@n8n/n8n-nodes-langchain.vectorStoreMongoDBAtlas - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - MongoDB
n8n-nodes-base.mongoDb - Edit Image
n8n-nodes-base.editImage - Extract from File
n8n-nodes-base.extractFromFile - HTTP Request
n8n-nodes-base.httpRequest - Google Drive
n8n-nodes-base.googleDrive - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Convert to File
n8n-nodes-base.convertToFile - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - If
n8n-nodes-base.if - Switch
n8n-nodes-base.switch - Merge
n8n-nodes-base.merge - Aggregate
n8n-nodes-base.aggregate - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
From the author
Build a WhatsApp AI shopping bot with virtual try-on using Gemini --- 📌 Overview This workflow fully automates your T-shirt store's WhatsApp shopping experience using GPT for intent detection, MongoDB Atlas for vector-based product search, Redis for session…