icereed/paperless-gpt

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

What it solves

paperless-gpt is an AI-powered companion for paperless-ngx, designed to automate the tedious manual sorting of documents. It solves the problem of manual naming, tagging, and data extraction from scanned documents, especially those with low-quality scans or complex layouts that traditional OCR often struggles with.

How it works

The tool integrates with paperless-ngx via API and uses Large Language Models (LLMs) and specialized OCR services to analyze document content. It can be configured to use various providers for both general LLM tasks (like naming) and specific OCR tasks (like text extraction).

  • OCR Providers: It supports LLM-based OCR (using vision-capable models like GPT-4o or MiniCPM-V), Azure Document Intelligence, Google Document AI, and self-hosted Docling servers.
  • Metadata Generation: The AI analyzes the extracted text to automatically generate document titles, tags, created dates, and correspondents.
  • Custom Field Extraction: It can extract specific data into custom fields using three write modes: Append, Update, or Replace.
  • PDF Enhancement: When using Google Document AI, it can generate searchable PDFs with transparent text layers over the original images.

Who it’s for

Users of paperless-ngx who want to automate their document management workflow, particularly those who handle a high volume of scanned documents or need high-accuracy text extraction from messy scans.

Highlights

  • LLM-Enhanced OCR: Uses vision LLMs to turn low-quality scans into context-aware text.
  • Automatic Organization: Generates titles, tags, dates, and correspondents automatically.
  • Customizable Prompts: Manage AI prompts for titles and tags directly via a Web UI.
  • Flexible OCR Options: Supports multiple enterprise and local providers (OpenAI, Ollama, Azure, Google, Docling).
  • Ad-hoc Analysis: Allows users to perform custom analysis or summaries on a selection of documents.
  • Searchable PDFs: Creates selectable text layers for PDFs (via Google Document AI).
  • Docker Deployment: Easy setup via Docker Compose alongside paperless-ngx.

Related

  • Project
    clusterzx/paperless-ai

    Paperless‑AI is an open‑source extension for the self‑hosted document manager Paperless‑ngx. It automatically classifies new documents, adds AI‑generated titles/tags, and builds a vector index so you can ask natural‑language questions across your whole archive (RAG chat). It works with any OpenAI‑compatible model—including local Ollama servers—and ships as a Docker image with a simple web UI for configuration and manual processing.

  • Project
    eikek/docspell

    Docspell is an open‑source personal document management system that organizes scanned papers, emails and other files. It uses Stanford CoreNLP to automatically suggest tags, dates and correspondents, runs OCR when needed, and provides full‑text search via a REST API and a mobile‑friendly Elm web UI. Installable via Docker, Debian packages, Nix or Helm, it is licensed under AGPL‑v3.

  • Project
    harshankur/officeParser

    A universal office document parser and generator that converts various file formats into a structured AST for easy conversion and RAG-ready chunking.

  • Project
    Future-Scholars/paperlib

    An open-source academic paper management tool that simplifies metadata scraping and organization, featuring LLM-powered summarization and semantic search.

  • Project
    drmingler/smart-llm-loader

    A Python package that converts documents and scanned images into clean, structured markdown chunks using OCR and LLM-powered semantic chunking for RAG systems.