See llms.txt for all machine-readable content.

Back to Templates

Sync WooCommerce products, blog, and Google Drive files to Pinecone with OpenAI

Created by

Created by: Stanislaw Chalupczak || zenmarkt
Stanislaw Chalupczak

Last update

Last update 2 days ago

Categories

Share

Quick overview

This workflow keeps a Pinecone knowledge base in sync with WooCommerce products and reviews, WordPress pages/posts, and files from a Google Drive folder by generating OpenAI embeddings, chunking content, and tracking sync state in an n8n Data Table.

How it works

  1. Runs on a manual trigger, daily schedules (blog at 4:00 AM and products at 5:00 AM), a Google Drive new-file trigger, or a WooCommerce webhook for product events.
  2. Validates required settings (store URL, Pinecone index details, embedding model/dimensions, chunking, and trigger-specific values like Drive folder ID or webhook secret) and routes execution to the matching lane.
  3. For WooCommerce product batch sync, fetches all published products, selects new/changed ones using the pinecone_sync_state table, removes vectors for unpublished/deleted products, and loads each product’s variations and latest reviews.
  4. For WooCommerce webhook events, verifies the WooCommerce HMAC signature, resolves the canonical product ID, deletes vectors for deleted/unpublished products, or fetches the product plus variations/reviews for updates.
  5. For WordPress blog sync, inventories published pages and posts via the WordPress REST API with pagination, removes vectors for deleted items, and fetches full content for new/changed entries.
  6. For Google Drive sync, lists files in a target folder, skips temp/unchanged files, extracts text per file type (Docs/Sheets/PDF with OCR fallback/Excel/images via OpenAI Vision/DOCX/PPTX/TXT), and removes vectors for files no longer present.
  7. Formats each item into clean text plus metadata, deletes old Pinecone vectors for the same fileId, splits the text into chunks, creates OpenAI embeddings, writes chunks to Pinecone, and upserts the item’s last modified timestamp into pinecone_sync_state.

Setup

  1. Add credentials for WooCommerce, Pinecone, OpenAI, Google Drive (OAuth2), and Gmail (for unsupported-format notifications).
  2. Create a Pinecone index and set its name, host, and namespace in the Settings node, ensuring the index dimension matches embeddingDimensions (default 1536 for text-embedding-3-small).
  3. Create an n8n Data Table named pinecone_sync_state with columns itemId, indexedAt, and dateModified.
  4. Update the Settings node with your WooCommerce base URL and currency, Google Drive folder ID, admin email, chunking limits, per-run caps, and the WooCommerce webhook secret.
  5. Configure the Google Drive trigger to watch the same folder ID used in Settings, and create WooCommerce webhooks (product created/updated/deleted) pointing to this workflow’s production webhook URL ending in /webhook/woo-product-events.