AI PDF Parsing: Structure, TOC, HTML/Markdown

# Extract PDF structure with AI and convert to HTML/Markdown

This workflow automates PDF processing by extracting document structure, building a hierarchical table of contents using AI, and converting content into clean HTML and Markdown files with preserved heading hierarchy. Designed for developers, analysts, and teams working with technical documentation, reports, or standards.

## Who it´s for
- Developers automating technical documentation processing
- Analysts working with large PDF reports
- Companies needing to convert documents into structured digital formats
- Integrators using n8n for document workflows
- AI agents requiring structured access to PDF content

## What the automation does
- Accepts PDF via URL or from Google Drive through HTTP webhook
- Converts file to base64 and sends to Chunkr.ai for parsing
- Uses a LangChain agent powered by Google Gemini to analyze initial pages and build a hierarchical TOC
- Maps sections of TOC to full document content
- Returns each section individually or compiles into a single HTML/Markdown file
- Can be triggered via webhook, manually, or by internal event

## What´s included
- Ready-to-use n8n workflow
- Trigger logic (webhook, manual, internal execution)
- Integrations with Chunkr.ai, Google Drive, Google Gemini, and HTTP API
- Basic setup and adaptation guide

## Requirements for setup
- n8n instance with JavaScript node support
- Google Gemini API key
- Google Drive access (if used)
- Chunkr.ai API credentials
- Basic understanding of JSON, base64, and HTTP requests

## Benefits and outcomes
- Automatic generation of accurate TOC without manual analysis
- Preserved heading hierarchy in HTML/Markdown output
- Preparation of documents for websites, knowledge bases, or documentation systems
- Faster processing of complex PDFs (medical guidelines, reports, manuals)
- Integration with AI agents needing structured input
- Repeatable and scalable document processing

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat