AI-powered Document Processing and Automation Tool
2.3k 2026-04-13

icereed/paperless-gpt

An AI-powered utility that integrates with paperless-ngx to enhance document digitalization through LLM-enhanced OCR, automatic titling, tagging, and field extraction.

Core Features

LLM-Enhanced OCR for high-accuracy text extraction from scans.
Automatic generation of document titles, tags, correspondents, and custom fields.
Support for various AI OCR services including OpenAI, Ollama, Google Document AI, and Azure Document Intelligence.
Generation of searchable and selectable PDFs with transparent text layers.
Extensive customization of AI prompts and PDF processing via a unified web UI.

Detailed Introduction

paperless-gpt is an innovative open-source solution designed to significantly streamline document management by integrating advanced AI capabilities with paperless-ngx. It leverages Large Language Models (LLMs) and LLM Vision to supercharge OCR, transforming even low-quality scans into context-aware, high-fidelity text. Beyond superior text extraction, it automates the tedious tasks of generating document titles, tags, and custom fields, saving users countless hours of manual sorting. This tool offers robust customization, supports various AI backends, and simplifies deployment with Docker, making it an indispensable asset for efficient digital document organization.

OSS Alternative

Explore the best open source alternatives to commercial software.

© 2026 OSS Alternative. hotgithub.com - All rights reserved.