Skip to content

A document digitization stack where **Scanservjs** captures documents → **Paperless-ngx** processes them with OCR and organizes in a database → **n8n** automates workflows for document processing → **Ollama** provides AI models for intelligent analysis and decision-making.

License

Notifications You must be signed in to change notification settings

aliuosio/papercuts-no-more

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

71 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Papercuts No More

Document Management Docker License

A comprehensive document digitization stack combining Scanservjs for scanning, Paperless-ngx for OCR processing, n8n for workflow automation, and Ollama for AI-powered analysis. An n8n workflow with an ai agent to discuss with your documents is installed on first run of the setup. works completely offline using ollama with Qwen3 as AI.

🚀 Quick Start

Prerequisites

  • Docker and Docker Compose
  • Optional: Scanner hardware, NVIDIA GPU

Installation

git clone https://github.com/aliuosio/papercuts-no-more
cd papercuts-no-more

Launch (GPU recommended)

docker compose --profile nvidia up -d

Launch (CPU-only)

docker compose up -d

Access Services

🏗️ Core Components

Component Function Port Technology
Paperless-ngx Document management & OCR 8010 Django + PostgreSQL
n8n Workflow automation & AI chat 5678 Node.js
Ollama Local AI models 11434 Go + CUDA/CPU
Scanservjs Document scanning 8080 Node.js
PostgreSQL Data storage 5432 PostgreSQL
Redis Caching & messaging 6379 Redis

💡 Key Features

  • 🔍 Intelligent Search: Natural language queries via AI chat interface
  • ⚡ GPU Acceleration: Up to 500% faster AI processing
  • 🔄 Automated Workflows: n8n-powered document processing pipelines
  • 📄 Multi-format Support: PDF, images, office documents, scanned images
  • 🏷️ Smart Categorization: Automatic OCR and tagging
  • 🔒 Secure Architecture: Containerized services with authentication
  • 🌐 German Language Support: Optimized for German document processing

📖 Documentation

🎯 Document Workflow

  1. Scan → Use web scanner interface at port 8080
  2. Process → Automatic OCR and metadata extraction
  3. Organize → Tag, categorize, and search documents
  4. Automate → Set up n8n workflows for processing
  5. Query → Use AI chat for natural language search

🤖 AI Features

  • Local AI Processing: Privacy-focused with Ollama
  • Natural Language Chat: Ask questions like "Show me contracts from October"
  • Document Analysis: AI-powered content understanding and summarization
  • Smart Classification: Automated document tagging and routing

🔧 Configuration

Environment variables are managed via .env file. Key settings:

# AI Configuration
OLLAMA_MODEL=qwen3:8b
PAPERLESS_OCR_LANGUAGE=deu

# Authentication
PAPERLESS_ADMIN_USER=admin
PAPERLESS_ADMIN_PASSWORD=admin123

See Setup Guide for complete configuration options.

🛠️ Development

# Development setup
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d

# Run tests
docker compose exec webserver python manage.py test

See Deployment Guide for contribution guidelines and development workflow.

🏷️ Tags & Categories

  • Personal Use: Document organization, receipt management, archiving
  • Business Use: Invoice processing, contract management, compliance
  • Research: Academic paper management, citation tracking
  • Legal: Contract analysis, document versioning, audit trails

📊 Status & Health

Monitor system health:

docker compose ps                    # Service status
docker compose logs -f webserver    # Application logs
curl http://localhost:8010/api/health/  # Health check

📋 Version Information

  • Paperless-ngx: v2.11.4
  • n8n: v1.60.1
  • Ollama: v0.3.12
  • AI Model: qwen3:8b

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Built on amazing open-source technologies:

About

A document digitization stack where **Scanservjs** captures documents → **Paperless-ngx** processes them with OCR and organizes in a database → **n8n** automates workflows for document processing → **Ollama** provides AI models for intelligent analysis and decision-making.

Resources

License

Stars

Watchers

Forks