n8n templatesn8n templates

OpenAI Personal Shopper with RAG and WooCommerce

This workflow combines intelligent chat models, vector retrieval technology, and e-commerce platforms to provide users with personalized shopping assistant services. It can automatically identify users' shopping needs, accurately extract product search information, and query inventory in real-time to recommend suitable products. Additionally, for inquiries about store information, the system can also provide intelligent responses, supporting context management for multi-turn conversations, thereby enhancing the user shopping experience and satisfaction.

Workflow Diagram
OpenAI Personal Shopper with RAG and WooCommerce Workflow diagram

Workflow Name

OpenAI Personal Shopper with RAG and WooCommerce

Key Features and Highlights

This workflow integrates OpenAI’s intelligent chat models, Retrieval-Augmented Generation (RAG) technology with vector search, and the WooCommerce e-commerce platform to create a smart personal shopping assistant. It can intelligently understand user chat requests, accurately extract product search parameters such as keywords, price range, SKU, and category, and perform real-time inventory queries on WooCommerce to recommend products that meet the user’s needs. For general store information inquiries (e.g., business hours, address), it leverages a RAG system built on Google Drive documents and the Qdrant vector database to provide intelligent responses. The workflow also supports conversation memory management to ensure continuity and contextual understanding across multi-turn dialogues.

Core Problems Addressed

  • Automatically identifying whether the user is searching for specific products to avoid misclassification
  • Precisely extracting product search parameters (keywords, price range, SKU, category) from natural language input
  • Real-time querying of WooCommerce APIs for product inventory and details to enable personalized recommendations
  • Utilizing the RAG system to intelligently answer non-product-related store information queries
  • Supporting multi-turn conversation memory to enhance user interaction experience

Application Scenarios

  • Intelligent customer service or shopping advisor on e-commerce websites
  • Online consultation and sales assistance for retail stores in apparel, footwear, bags, etc.
  • Scenarios requiring intelligent Q&A combining knowledge bases (e.g., store information documents) with product data
  • Personalized recommendation systems aimed at improving shopping efficiency and customer satisfaction

Main Workflow Steps

  1. Receive Chat Message: Capture user input via the LangChain chatTrigger node.
  2. Edit Fields: Extract and organize conversation ID and user input text.
  3. Information Extraction: Use the Information Extractor node to determine user intent and extract search keywords, price range, SKU, and category information.
  4. Intelligent Decision and Routing: The AI Agent node decides whether to invoke the personal shopper tool or the RAG knowledge retrieval tool based on the user’s request.
  5. Product Search: The personal shopper calls the WooCommerce node to query the e-commerce API for products matching the criteria.
  6. Knowledge Base Q&A: The RAG node uses the Qdrant vector database and store information documents stored on Google Drive, combined with OpenAI models, to answer user queries related to store information.
  7. Multi-turn Conversation Memory: The Window Buffer Memory node manages conversation context to support continuous dialogue.
  8. Return Results: Deliver product recommendations or knowledge base answers back to the user.

Involved Systems and Services

  • OpenAI: For language understanding, generation, and embeddings creation.
  • WooCommerce: For product inventory querying and retrieval.
  • Qdrant: Vector database storing vectors of the store knowledge base.
  • Google Drive: Storage for store-related document data.
  • n8n LangChain Node Integration: Implements chat triggers, information extraction, tool invocation, and memory caching functionalities.

Target Users and Value

  • E-commerce platform operators, especially retailers in apparel, footwear, and bags, aiming to enhance customer shopping experience.
  • Enterprises or developers seeking to implement AI-powered intelligent customer service and personalized recommendations.
  • Technical teams building intelligent Q&A systems that combine knowledge bases and product data.
  • Marketing and customer service managers focused on improving customer satisfaction and sales conversion rates.

By seamlessly integrating advanced AI technologies with e-commerce systems, this workflow delivers intelligent, efficient, and personalized shopping consultation services, significantly enhancing user interaction experience and business efficiency.