n8n Workflow: Extract Google Drive Files to Google Sheets

Turn Google Drive files into structured Google Sheets rows—automatically

This n8n workflow extracts the contents of every file in a specified Google Drive folder, converts them to text (via an imported converter sub-workflow), and writes one structured row per file into Google Sheets—including automatic schema creation with a Groq LLM.

What this workflow does

• Starts manually or runs when triggered by another workflow, reading configuration values such as the Google Drive folder ID and Google Sheets spreadsheet ID.
• Fetches the target Google Sheets tab and checks whether a schema tab exists. If it doesn’t, it uses Groq (LLM chain) to generate a per-column schema and writes it to a new schema sheet.
• Ensures the data sheet includes helper headers: source_file, Text_to_interpret, and extraction_status.
• Lists all files in the specified Google Drive folder and builds extraction instructions from the schema.
• Optionally filters files (include/exclude rules, limit, size rules) and skips files already processed successfully to support resumable runs.
• Downloads each file and calls the imported any-file2json-converter sub-workflow to extract text or JSON-like field output.
• Writes results back to Google Sheets, appending or updating the row that matches source_file, recording success or failure details in extraction_status.
• Produces a run summary at the end and can fail execution if any files failed so you can trigger an error workflow.

Use cases

• Extract information from documents stored in Drive and maintain a searchable spreadsheet.
• Run scheduled “ingestion” pipelines that avoid reprocessing already successful files.
• Create a dynamic extraction layout by generating a schema with Groq when a schema tab is missing.

Technical details

• Integrations: Google Drive, Google Sheets
• LLM: Groq (LLM chain for schema generation)
• Key n8n nodes/components: if, set, code, wait, and workflow imported any-file2json-converter, plus Google Drive nodes