n8n-universal-document-parser

Universal document parser workflow for n8n that converts multiple document formats into plain text using the Google Drive API.

This workflow eliminates the need for separate parsing nodes for each file type (PDF, DOCX, TXT, etc.) by leveraging Google's document conversion engine.

---

Supported Input Formats

The workflow can process:

• PDF
• DOCX
• DOC
• Google Docs
• TXT

---

How It Works

1. Input file ID is provided from Google Drive.
2. The workflow calls the Google Drive API to create a converted copy of the file as a Google Doc.
3. Google Docs automatically converts the file content.
4. The workflow retrieves the document using the exportLinks[text/plain] endpoint.
5. Final output is clean plain text, ready for:
   • AI processing
   • summarization
   • embeddings
   • vector databases
   • automation workflows

---

Workflow Architecture

Main steps:

1. Manual Trigger
2. Set File ID
3. Google Drive API – Copy with Convert
4. Export Converted Document as Plain Text

---

Example Use Cases

• AI document summarization
• RAG pipelines
• Knowledge base ingestion
• Resume parsing
• Contract analysis
• Email/document automation

---

Requirements

• n8n
• Google Drive API access
• Google OAuth credentials configured in n8n

---

Setup

1. Import the workflow JSON into n8n
2. Configure Google OAuth credentials
3. Update the file_id field
4. Run the workflow

---

Files Included

• workflow.json – n8n workflow
• workflow.png – visual workflow architecture

---

Author

Sanket Gawankar
AI Automation | n8n | Communication Platforms | Cisco | Zoom