n8n Workflow: Clean & Deduplicate Supplier Data w/ Groq

Automatically clean and deduplicate your supplier master data with n8n + Groq

This scheduled n8n workflow scans supplier and item master data in Google Sheets, detects duplicate suppliers, uses Groq (via a LangChain agent) to generate a short merge justification, and then updates your sheets with an auditable MASTER/MERGED/ACTIVE status—plus an email alert for recorded auto-merges.

What this workflow does

• Runs daily on a schedule and reads supplier and item master data from your connected Google Sheets.
• Combines and normalizes data by standardizing supplier names into a lowercase, trimmed field and removing exact duplicates based on the normalized name.
• Detects potential duplicate suppliers by comparing supplier pairs using custom matching rules, producing a confidence score.
• Filters to high-confidence matches and sends the candidate pair details to Groq to generate a short merge justification.
• Creates an auto-merge record, appends a merge audit entry to a designated Google Sheets audit tab, and generates a supplier status mapping (MASTER/MERGED/ACTIVE).
• Updates Google Sheets with merge status and master-supplier references for the full supplier list.
• Sends a Gmail notification whenever an auto-merge is recorded.

Use cases

• Keep supplier records consistent when multiple entries exist due to spelling differences (e.g., punctuation or casing changes).
• Reduce duplicate supplier IDs in a SaaS ops workflow by automatically reconciling masters and merges.
• Operational audits: maintain a clear, sheet-based merge log for governance and review.

Technical details

• Schedule: daily run
• Data source: Google Sheets (supplier, item, and audit tabs)
• Logic nodes: if, set, code
• LLM integration: Groq via a LangChain agent
• Notifications: Gmail merge alert emails
• Notes: sticky note elements included for workflow clarity

Setup requirements

• Connect Google Sheets credentials and configure the correct spreadsheet and sheet tabs.
• Ensure your supplier sheet has columns such as supplier_name, merge_status, and master_supplier, and that your audit sheet contains the defined audit column(s).