Answer product queries via WhatsApp using OpenAI GPT-4o and PDF knowledge base
Needs changesWhat this workflow does
This AI workflow has 18 nodes and runs on WhatsApp events (messages) (plus 1 other trigger). Along the way it connects WhatsApp Business Cloud, OpenAI Chat Model, Vector Store Question Answer and Embeddings OpenAI. It also calls usa.yamaha.com over HTTP.
How it runs
Trigger: On WhatsApp events (messages) (plus 1 other trigger).
- Handle Message Types (Switch): routes items into 2 branches
- get Product Brochure (HTTP Request): calls usa.yamaha.com
- AI Sales Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Vector Store Tool); memory: Window Buffer Memory
- Reply To User (WhatsApp Business Cloud): send
- Extract from File: extracts data from a file (pdf)
- Reply To User (WhatsApp Business Cloud): send
- Create Product Catalogue (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
Services it uses
HTTP calls to: usa.yamaha.com
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 AI Sales Agent (v1.6): 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) AI Sales Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (14)
- WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Manual Trigger
n8n-nodes-base.manualTrigger - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Extract from File
n8n-nodes-base.extractFromFile - HTTP Request
n8n-nodes-base.httpRequest - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
WhatsApp AI Sales Agent using PDF Vector Store This workflow turns your WhatsApp number into an intelligent AI-powered Sales Agent that answers product queries using real data extracted from a PDF brochure. It loads a product brochure via HTTP Request,…