OpenAI Personal Shopper with RAG and WooCommerce n8n Workflow Template

n8n workflow template · 21 nodes · OpenAI

OpenAI Personal Shopper with RAG and WooCommerce is a free n8n workflow template that starts when a chat message is received and works with OpenAI, Qdrant, WooCommerce and Google Drive. It has 21 nodes, 15 of them AI nodes (Chat Trigger, Window Buffer Memory, Calculator Tool and OpenAI Chat Model). The notes inside the workflow say: “The Information Extractor tries to understand if the request is related to products and if so, it extracts the useful information to filter the products available on WooCommerce by calling the "personal_shopper".” To run it, you add your own credentials for Google Drive OAuth2, HTTP Header Auth, OpenAI API, Qdrant API and WooCommerce API.

Download JSON How to import into n8n

At a glance

Trigger
Chat Trigger (When chat message received)
Nodes
21
Apps
OpenAI, Qdrant, WooCommerce and Google Drive
AI nodes
15
Credentials
5 types
Category
E-commerce and payments

Apps and integrations

  • OpenAI
  • Qdrant
  • WooCommerce
  • Google Drive

Node types used

  • Chat Trigger
  • Window Buffer Memory
  • Calculator Tool
  • Edit Fields (Set)
  • OpenAI Chat Model
  • Vector Store Question Answer Tool
  • Qdrant Vector Store
  • OpenAI Embeddings
  • WooCommerce Tool
  • Information Extractor
  • Google Drive
  • Default Data Loader
  • Token Splitter
  • Manual Trigger
  • HTTP Request
  • AI Agent

How it works

The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.

Step 2

The Information Extractor tries to understand if the request is related to products and if so, it extracts the useful information to filter the products available on WooCommerce by calling the "personal_shopper". If it is a general question, the RAG system is called

Setup notes

The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.

Step 1

Create a collectiopn on your Qdrant instance. Then create a basic RAG system with documents uploaded to Google Drive and embedded in the Qdrant vector database

Replace the URL and Collection name with your own

Step 1

Create a basic RAG system with documents uploaded to Google Drive and embedded in the Qdrant vector database

Nodes in this workflow

The 21 nodes in file order (sticky notes excluded). Branches and connections determine execution order in n8n:

  1. When chat message received (Chat Trigger)
  2. Window Buffer Memory (Window Buffer Memory)
  3. Calculator (Calculator Tool)
  4. Edit Fields (Edit Fields (Set))
  5. OpenAI Chat Model (OpenAI Chat Model)
  6. RAG (Vector Store Question Answer Tool)
  7. Qdrant Vector Store (Qdrant Vector Store)
  8. Embeddings OpenAI (OpenAI Embeddings)
  9. OpenAI Chat Model1 (OpenAI Chat Model)
  10. personal_shopper (WooCommerce Tool)
  11. Information Extractor (Information Extractor)
  12. OpenAI Chat Model2 (OpenAI Chat Model)
  13. Google Drive2 (Google Drive)
  14. Google Drive1 (Google Drive)
  15. Embeddings OpenAI3 (OpenAI Embeddings)
  16. Default Data Loader2 (Default Data Loader)
  17. Token Splitter1 (Token Splitter)
  18. When clicking ‘Test workflow’ (Manual Trigger)
  19. HTTP Request (HTTP Request)
  20. Qdrant Vector Store1 (Qdrant Vector Store)
  21. AI Agent (AI Agent)

Credentials you need

  • Google Drive OAuth2 – used by Google Drive1 and Google Drive2
  • HTTP Header Auth – used by HTTP Request
  • OpenAI API – used by Embeddings OpenAI, Embeddings OpenAI3, OpenAI Chat Model and OpenAI Chat Model1 and others
  • Qdrant API – used by Qdrant Vector Store and Qdrant Vector Store1
  • WooCommerce API – used by personal_shopper

Configure your own credentials after importing. Create each credential in n8n, then select it in the node.

How to import into n8n

  1. Download the JSON file with the button above.
  2. In n8n, open a new workflow, select the ... menu and choose Import from File. You can also paste the JSON straight into the editor canvas.
  3. Open each node that shows a warning and select or create its credential.
  4. Read the notes on the canvas, test the workflow with sample data, then activate it.

Do you need somewhere to run it? Read our guide to self-hosted n8n.

Need this customised?

We can adapt this workflow to your apps, data and process, then deploy and support it.

Contact Us