Automated PII Removal from Google Drive CSV Files

This n8n workflow automates the process of monitoring a specific Google Drive folder for new CSV files, extracting and analyzing their content to identify personally identifiable information (PII), removing sensitive columns, and then re-uploading the sanitized file back to Google Drive. The workflow starts with a Google Drive trigger that watches for new files in a designated folder. When triggered, it downloads the new file and extracts its filename and contents. An OpenAI model (GPT-4) is then used to analyze the data, specifically to identify columns containing PII. A custom JavaScript code node processes this output, removing the identified PII columns from the data. The cleaned data is converted back into CSV format with a new filename indicating it has been sanitized. Finally, the sanitized CSV file is uploaded to a different folder within Google Drive. This workflow is useful for data privacy compliance, especially when handling sensitive customer or user data, without manual intervention.