HumationHuman + Automation
Back to Catalog

E-commerce product fine-tuning with Bright Data and OpenAI

Daniel ShashkoDaniel Shashko
1374 views
2/3/2026
aws-s3sshwp-cliwordpressdata-export
Official Page

finetuning gpt4o.PNG

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

This workflow automates the process of scraping product data from e-commerce websites and using it to fine-tune a custom OpenAI GPT model for generating high-quality marketing copy and product descriptions.

Main Use Cases

  • Fine-tune OpenAI models with real product data from hundreds of supported e-commerce websites for marketing content generation.
  • Create custom AI models specialized in writing compelling product descriptions across different industries and platforms.
  • Automate the entire pipeline from data collection to model training using Bright Data's extensive scraper library.
  • Generate marketing copy using your custom-trained model via an interactive chat interface.

How it works

The workflow operates in two main phases: model training and model usage, organized into these stages:

  1. Data Collection & Processing

    • Manually triggered to start the fine-tuning process.
    • Uses Bright Data's web scraper to extract product information from any supported e-commerce platform (Amazon, eBay, Shopify stores, Walmart, Target, and hundreds of other websites).
    • Collects product titles, brands, features, descriptions, ratings, and availability status from your chosen platform.
    • Easily customizable to scrape from different websites by simply changing the dataset configuration and product URLs.

  2. Training Data Preparation

    • A Code node processes the scraped product data to create training examples in OpenAI's required JSONL format.
    • For each product, generates a complete training example with:
      • System message defining the AI's role as a marketing assistant.
      • User prompt containing specific product details (title, brand, features, original description snippet).
      • Assistant response providing an ideal marketing description template.
    • Compiles all training examples into a single JSONL file ready for OpenAI fine-tuning.

  3. Model Fine-Tuning

    • Uploads the training file to OpenAI using the OpenAI File Upload node.
    • Initiates a fine-tuning job via HTTP Request to OpenAI's fine-tuning API using the GPT-4o-mini model as the base.
    • The fine-tuning process runs on OpenAI's servers to create your custom model.

  4. Interactive Chat Interface

    • Provides a chat trigger that allows real-time interaction with your fine-tuned model.
    • An AI Agent node connects to your custom-trained OpenAI model.
    • Users can chat with the model to generate product descriptions, marketing copy, or other content based on the training.

  5. Custom Model Integration

    • The OpenAI Chat Model node is configured to use your specific fine-tuned model ID.
    • Delivers responses trained on your product data for consistent, high-quality marketing content.

Summary Flow:

Manual Trigger → Scrape E-commerce Products (Bright Data) → Process & Format Training Data (Code) → Upload Training File (OpenAI) → Start Fine-Tuning Job (HTTP Request) | Parallel: Chat Trigger → AI Agent → Custom Fine-Tuned Model Response

Benefits:

  • Fully automated pipeline from raw product data to trained AI model.
  • Works with hundreds of different e-commerce websites through Bright Data's extensive scraper library.
  • Creates specialized models trained on real e-commerce data for authentic marketing copy across various industries.
  • Scalable solution that can be adapted to different product categories, niches, or websites.
  • Interactive chat interface for immediate access to your custom-trained model.
  • Cost-effective fine-tuning using OpenAI's most efficient model (GPT-4o-mini).
  • Easily customizable with different websites, product URLs, training prompts, and model configurations.

Setup Requirements:

  • Bright Data API credentials for web scraping (supports hundreds of e-commerce websites).
  • OpenAI API key with fine-tuning access.
  • Replace placeholder credential IDs and model IDs with your actual values.
  • Customize the product URLs list and Bright Data dataset for your specific website and use case.
  • The workflow can be adapted for any e-commerce platform supported by Bright Data's scraping infrastructure.

E-commerce Product Fine-Tuning with Bright Data and OpenAI

This n8n workflow automates the process of enriching and fine-tuning e-commerce product data using web scraping (via Bright Data) and AI-powered text generation (via OpenAI). It's designed to help businesses refine product descriptions, features, and other attributes for better SEO, customer engagement, and overall data quality.

What it does

This workflow performs the following key steps:

  1. Triggers Manually: The workflow is initiated manually by clicking "Execute workflow".
  2. Scrapes Product Data (Bright Data): An HTTP Request node is configured to interact with the Bright Data API. It's intended to scrape specific product information from e-commerce websites.
  3. Processes Scraped Data: A Code node is used to process and transform the data received from Bright Data. This likely involves parsing the JSON response, extracting relevant fields, and preparing the data for the AI agent.
  4. Generates AI-Powered Enhancements (OpenAI): An AI Agent (Langchain) is employed to take the processed product data and generate refined content. This agent uses an OpenAI Chat Model to perform tasks like:
    • Rewriting product descriptions for clarity or SEO.
    • Extracting key features or benefits.
    • Generating marketing copy.
    • Fine-tuning product attributes based on specific instructions.
  5. Performs Additional OpenAI Actions (Optional/Future Expansion): An additional OpenAI node is present, suggesting potential for further AI-driven tasks such as image generation (DALL-E), audio transcription (Whisper), or more advanced assistant interactions. This node is currently not connected in the provided JSON but indicates potential for expansion.
  6. Provides a Chat Interface (Optional/Future Expansion): A "Chat Trigger" node is included, indicating a potential future integration for interactive fine-tuning or real-time product data requests via a chat interface. This node is currently not connected in the provided JSON.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance (cloud or self-hosted).
  • Bright Data Account: An active Bright Data account with access to their Web Scraper API. You will need API credentials (likely an API key or similar authentication).
  • OpenAI API Key: An OpenAI API key with access to their chat models (e.g., GPT-3.5, GPT-4).
  • Langchain Credentials (if applicable): Ensure your n8n instance is configured with the necessary Langchain credentials for the AI Agent and OpenAI Chat Model nodes.

Setup/Usage

  1. Import the Workflow:
    • Download the provided JSON file.
    • In your n8n instance, click "New" in the workflows section.
    • Select "Import from JSON" and upload the downloaded file.
  2. Configure Credentials:
    • HTTP Request (Bright Data):
      • Locate the "HTTP Request" node (ID: 19).
      • Edit the node and configure the URL, headers, and body to match your Bright Data API endpoint and scraping job requirements. You will likely need to add credentials for Bright Data here.
    • OpenAI Chat Model:
      • Locate the "OpenAI Chat Model" node (ID: 1153).
      • Edit the node and select or create an OpenAI API credential.
      • Configure the model (e.g., gpt-3.5-turbo, gpt-4) and any specific parameters for your fine-tuning task.
    • AI Agent:
      • Locate the "AI Agent" node (ID: 1119).
      • Ensure it is correctly linked to the OpenAI Chat Model.
      • Define the agent's prompt and tools based on the specific fine-tuning tasks you want it to perform (e.g., "You are an expert e-commerce product description writer. Refine the following product data...").
  3. Customize the Code Node:
    • Locate the "Code" node (ID: 834).
    • Edit the JavaScript code within this node to parse the specific output format from your Bright Data scraper and prepare it for the AI Agent. This might involve JSON.parse(), item.json.data.map(), etc.
  4. Test the Workflow:
    • Once configured, click "Execute Workflow" to run a test and ensure all steps are working as expected.
    • Review the output of each node to debug any issues.
  5. Activate the Workflow:
    • After successful testing, activate the workflow to make it ready for production use.

Note: The "OpenAI" node (ID: 1250) and "Chat Trigger" node (ID: 1247) are not connected in the provided JSON. They represent potential future enhancements or alternative starting points for the workflow. If you wish to use them, you will need to connect them appropriately and configure their settings.

Related Templates

Generate verified job offer letters with OpenAI, Gmail and Slack

📄 AI-Powered Verified Job Offer Letter Generator Description Creating job offer letters manually is time-consuming, error-prone, and difficult to scale. This AI-powered workflow automates the entire job offer letter process — from validating candidate emails to generating and delivering professional PDF offer letters. This intelligent workflow eliminates repetitive drafting, reduces human errors, and ensures offer letters are sent only to verified email addresses, helping HR teams move faster while maintaining professionalism and accuracy. --- What This Workflow Does Transforms manual offer letter creation into a seamless, automated HR process: 📝 Capture Candidate & Job Details – Receives candidate name, email, job role, salary, joining date, and company details via webhook or form. 📧 Email Verification – Validates the candidate’s email address before sending any communication to prevent delivery errors. 🧠 AI-Powered Offer Letter Generation – Uses AI to generate a clear, professional, and structured job offer letter. 📄 HTML Offer Letter Formatting – Converts the AI-generated content into a clean and readable HTML layout. 📑 PDF Generation – Automatically converts the offer letter into a professional PDF document. 📧 Offer Letter Delivery – Sends the PDF offer letter directly to the verified candidate email. 🗂️ Document Storage – Saves a copy of the offer letter for internal records and future reference. 🔁 Confirmation Response – Returns a success response confirming completion. --- Key Features 🤖 AI Offer Letter Writing – Generates professional, ready-to-send offer letters automatically. 📧 Email Verification Built-In – Ensures offer letters are only sent to valid email addresses. 📑 PDF Generation – Creates clean, official-looking offer letters. ⚙️ End-to-End Automation – No manual drafting, formatting, or sending required. 📂 Centralized Record Keeping – Keeps copies of all generated offer letters. 🔄 Flexible Triggering – Can be triggered from HR systems, forms, or internal tools. --- Perfect For 🏢 HR & Recruitment Teams – Automate offer letter creation and delivery. 🚀 Startups & Growing Companies – Send professional offer letters without extra admin work. 🏫 Staffing & Hiring Agencies – Generate offer letters quickly for multiple candidates. 💻 Remote & Distributed Teams – Ensure consistent communication across locations. 🧠 Operations Teams – Maintain accurate records and reduce manual errors. --- What You’ll Need Required Integrations 🌐 Webhook Trigger – Receives candidate and job details. 🤖 OpenAI – Generates offer letter content. 📧 VerifyEmail – Validates candidate email addresses. 📄 HTMLCSS to PDF – Converts HTML into PDF offer letters. 📧 Gmail – Sends the offer letter email. ☁️ Google Drive (optional) – Stores generated offer letters. --- Optional Enhancements 🎨 Brand Customization – Add company logo, colors, and formatting to offer letters. 🧾 HR System Integration – Connect with ATS or HR tools for automatic triggering. 🌍 Multilingual Offer Letters – Generate offer letters in different languages. 🔐 Approval Step – Add internal approval before sending offer letters. 📊 Audit Logging – Store offer letter data in Google Sheets or databases. 📎 Additional Attachments – Include policies or onboarding documents with the offer letter. --- Quick Start 1️⃣ Import the workflow template into your n8n workspace 2️⃣ Connect credentials for OpenAI, VerifyEmail, Gmail, and HTMLCSS to PDF 3️⃣ Send test candidate data to the webhook 4️⃣ Review the generated PDF offer letter 5️⃣ Activate the workflow and start sending offer letters automatically --- Customization Options 1️⃣ Offer Letter Tone – Adjust AI prompt for formal or friendly tone. 2️⃣ Company Branding – Customize HTML layout and styling. 3️⃣ Email Content – Modify subject line and email message. 4️⃣ PDF Layout – Adjust spacing, fonts, and structure. 5️⃣ Storage Location – Change where offer letters are saved. 6️⃣ Validation Rules – Extend email or input checks. --- Expected Results ⚡ Faster Hiring Process – Generate offer letters in minutes. 🤖 Consistent Quality – Every offer letter follows a professional format. 📧 Error-Free Delivery – Verified emails reduce failed communication. 🗂️ Organized Records – All offer letters stored automatically. 🏢 Professional Candidate Experience – Clean, official documents every time. --- Workflow Structure Visualization 📝 Candidate & Job Details ↓ 📧 Email Verification ↓ 🧠 AI Offer Letter Generation ↓ 📄 HTML Formatting ↓ 📑 PDF Conversion ↓ 📧 Email Delivery ↓ 🔁 Confirmation Response --- 🚀 Ready to Automate Job Offer Letters? Import this template today and let AI handle offer letter creation, verification, and delivery — so your team can focus on hiring the right talent faster. ✨ ---

Jitesh DugarBy Jitesh Dugar
5

Daily Magento 2 customer sync to Google Contacts & Sheets without duplicates

Automatically sync newly registered Magento 2 customers to Google Contacts and Google Sheets every 24 hours — with full duplication control and seamless automation. This workflow is a plug-and-play customer contact automation system designed for Magento 2 store owners, marketers, and CRM teams. It fetches customer records registered within the last 24 hours (from 00:00:00 to 23:59:59), checks against an existing Google Sheet to avoid reprocessing, and syncs only the new ones into Google Contacts. This ensures your contact list is always fresh and up to date — without clutter or duplicates. ✅ What This Workflow Does: Automates Customer Syncing Every day, it fetches newly registered Magento 2 customers via API based on the exact date range (midnight to midnight). Deduplicates Using Google Sheets A master Google Sheet tracks already-synced emails. Before adding a customer, the workflow checks this list and skips if already present. Creates Google Contacts Automatically For each unique customer, it creates a new contact in your Google Contacts, saving fields like first name, last name, and email. Logs New Entries to Google Sheets In Google Sheets, it even records magento 2 customer group, createdat, websiteid & store_id After syncing, it adds each new email to the tracking sheet, building a cumulative record of synced contacts. Fully Scheduled & Automated Can be scheduled with the Cron node to run daily (e.g., 12:05 AM) with no manual intervention required. 🔧 Modules Used: HTTP Request (Magento 2 API) Date & Time (for filtering registrations) Google Sheets (for reading/writing synced emails) Google Contacts (for contact creation) Set, IF, and Merge nodes (for control logic) Cron (for scheduling the automation) 💼 Use Cases: Keep your email marketing tools synced with Magento 2 customer data. Build a CRM-friendly contact base in Google Contacts without duplicates. Share customer data with sales or support teams through synced Google Sheets. Reduce manual work and human error in data transfer processes. 🔒 Credentials Required Magento 2 Bearer Auth: Set up as a credential in n8n using your Magento 2 API access token. Google API 📂 Category E-commerce → Magento 2 (Adobe Commerce) 💬 Need Help? 💡 Having trouble setting it up or want to customize this workflow further? Feel free to reach out — I’m happy to help with setup, customization, or Magento 2 API integration issues. Contact: Author 👤 Author Kanaka Kishore Kandregula Certified Magento 2 Developer https://gravatar.com/kmyprojects https://www.linkedin.com/in/kanakakishore

Kanaka Kishore KandregulaBy Kanaka Kishore Kandregula
163

Export WordPress posts with categories and tags to Google Sheets for SEO audits

Who’s it for This workflow is perfect for content managers, SEO specialists, and website owners who want to easily analyze their WordPress content structure. It automatically fetches posts, categories, and tags from a WordPress site and exports them into a Google Sheet for further review or optimization. What it does This automation connects to the WordPress REST API, collects data about posts, categories, and tags, and maps the category and tag names directly into each post. It then appends all this enriched data to a Google Sheet — providing a quick, clean way to audit your site’s content and taxonomy structure. How it works Form trigger: Start the workflow by submitting a form with your website URL and the number of posts to analyze. Fetch WordPress data: The workflow sends three API requests to collect posts, categories, and tags. Merge data: It combines all the data into one stream using the Merge node. Code transformation: A Code node replaces category and tag IDs with their actual names. Google Sheets export: Posts are appended to a Google Sheet with the following columns: URL Title Categories Tags Completion form: Once the list is created, you’ll get a confirmation message and a link to your sheet. If the WordPress API isn’t available, the workflow automatically displays an error message to help you troubleshoot. Requirements A WordPress site with the REST API enabled (/wp-json/wp/v2/). A Google account connected to n8n with access to Google Sheets. A Google Sheet containing the columns: URL, Title, Categories, Tags. How to set up Import this workflow into n8n. Connect your Google Sheets account under credentials. Make sure your WordPress site’s API is accessible publicly. Adjust the Post limit (per_page) in the form node if needed. Run the workflow and check your Google Sheet for results. How to customize Add additional WordPress endpoints (e.g., authors, comments) by duplicating and modifying HTTP Request nodes. Replace Google Sheets with another integration (like Airtable or Notion). Extend the Code node to include SEO metadata such as meta descriptions or featured images.

Piotr SikoraBy Piotr Sikora
86