Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / Chatbots & Messaging Bots

Chatbots & Messaging Bots

Run WhatsApp Sales Chatbot Backed By Product Catalog Vector Store

Answers WhatsApp customer text messages as a sales agent using a product brochure loaded into an in-memory vector store. Triggers on each incoming message.

What it does

## Try It Out! ### This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions. * This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. * A product brochure is imported via HTTP request node and its text contents extracted. * The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot. * A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. * The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool. * The Agent's response is sent back to the user via the WhatsApp node. ### Need Help? Join the [Discord]({{ $env.WEBHOOK_URL }} or ask in the [Forum]({{ $env.WEBHOOK_URL }}

The steps

  1. WhatsApp Trigger
  2. OpenAI Chat Model
  3. Window Buffer Memory
  4. Vector Store Tool
  5. Embeddings OpenAI
  6. OpenAI Chat Model1
  7. When clicking ‘Test workflow’
  8. Embeddings OpenAI1
  9. Default Data Loader
  10. Recursive Character Text Splitter
  11. Extract from File
  12. get Product Brochure
  13. Reply To User
  14. Reply To User1

18 steps in total.

Similar automations