Handle e-commerce WhatsApp support with Whapi, WooCommerce, RAG and Gmail escalation
Needs changesWhat this workflow does
This AI workflow has 30 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Qdrant Vector Store, Google Drive, Embeddings OpenAI and OpenAI Chat Model and 5 more. It also calls qdranturl and gate.whapi.cloud over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Create collection (HTTP Request): calls qdranturl (POST)
- Refresh collection (HTTP Request): calls an HTTP API (POST)
- is Message? (If): checks a condition and branches into true / false
- Get folder (Google Drive): work with file folder
- Guardrails: uses Guardrails
- Only text avaiable (HTTP Request): calls gate.whapi.cloud (POST)
- Download Files (Google Drive): download
- E-Commerce Customer Support AI Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 8 tools (get_user, get_order, Calculator, get_orders…); memory: Window Buffer Memory
- Bad message (HTTP Request): calls gate.whapi.cloud (POST)
- Qdrant Vector Store: stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
…plus 2 more steps. See the full node list below.
Services it uses
HTTP calls to: qdranturl, gate.whapi.cloud
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 E-Commerce Customer Support AI Agent (v1.7): 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) E-Commerce Customer Support AI Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (19)
- Manual Trigger
n8n-nodes-base.manualTrigger - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - HTTP Request
n8n-nodes-base.httpRequest - Google Drive
n8n-nodes-base.googleDrive - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Guardrails
@n8n/n8n-nodes-langchain.guardrails - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Woo Commerce Tool
n8n-nodes-base.wooCommerceTool - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - AI Agent
@n8n/n8n-nodes-langchain.agent - Webhook
n8n-nodes-base.webhook - Gmail Tool
n8n-nodes-base.gmailTool - If
n8n-nodes-base.if - Code
n8n-nodes-base.code
From the author
This workflow is a complete AI-powered customer support automation for e-commerce businesses. The system allows customers to interact with an AI assistant directly through WhatsApp. This chatbot can: Answer customer questions in real time Retrieve order…