Remove Personally Identifiable Information (PII) from CSV Files with OpenAI
Last edited 39 days ago
What this workflow does
- Monitors Google Drive: The workflow triggers whenever a new CSV file is uploaded.
- Uses AI to Identify PII Columns: The OpenAI node analyzes the data and identifies PII-containing columns (e.g., name, email, phone).
- Removes PII: The workflow filters out these columns from the dataset.
- Uploads Cleaned File: The sanitized file is renamed and re-uploaded to Google Drive, ensuring the original data remains intact.
How to customize this workflow to your needs
- Adjust PII Identification: Modify the prompt in the OpenAI node to align with your specific data compliance requirements.
- Include/Exclude File Types: Adjust the Google Drive Trigger settings to monitor specific file types (e.g., CSV only).
- Output Destination: Change the folder in Google Drive where the sanitized file is uploaded.
Setup
Prerequisites:
- A Google Drive account.
- An OpenAI API key.
Workflow Configuration:
- Configure the Google Drive Trigger to monitor a folder for new files.
- Configure the OpenAI Node to connect with your API
- Set the Google Drive Upload folder to a different location than the Trigger folder to prevent workflow loops.
You may also like
New to n8n?
Need help building new n8n workflows? Process automation for you or your company will save you time and money, and it's completely free!