Voice AI customer support for WooCommerce using VAPI, GPT-4o & Gemini with RAG
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 20 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects Google Gemini Chat Model, Qdrant Vector Store, Embeddings OpenAI and WooCommerce and 1 more.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).
- Post-Sales Agent (AI Agent): runs an AI agent, with model: GPT 4o-mini; 5 tools (get_user, get_order, Calculator, get_orders…)
- Get tracking (HTTP Request): calls an HTTP API
- Question and Answer Chain: answers questions over your documents (RAG), with model: Google Gemini Chat Model; retriever: Vector Store Retriever
- Set response (Edit Fields (Set)): sets 1 field: message
- Set tracking code (Edit Fields (Set)): sets 3 fields: tracking_code, carrier_url, pick_up
- Send RAG response to VAPI (Respond to Webhook): sends the response back to the webhook caller
- Send response to VAPI (Respond to Webhook): sends the response back to the webhook caller
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Post-Sales Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Post-Sales Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (15)
- Question and Answer Chain
@n8n/n8n-nodes-langchain.chainRetrievalQa - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Vector Store Retriever
@n8n/n8n-nodes-langchain.retrieverVectorStore - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Webhook
n8n-nodes-base.webhook - Woo Commerce Tool
n8n-nodes-base.wooCommerceTool - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Respond to Webhook
n8n-nodes-base.respondToWebhook
From the author
This workflow integrates a Retrieval-Augmented Generation (RAG) system with a post-sales AI agent for WooCommerce. It combines vector-based search (Qdrant + OpenAI embeddings) with LLMs (Google Gemini and GPT-4o-mini) to provide accurate and contextual…