Rowfill is an open-source platform designed to help knowledge workers extract, analyze, and process data from unstructured documents like PDFs and images using AI. It offers advanced OCR, auto-schema generation, and custom workflow capabilities, with a strong emphasis on privacy through local LLM support and secure data handling.

How It Works

Rowfill leverages advanced OCR and AI models to extract text, tables, and handwriting from various document formats. It automatically infers document structures to generate schemas, enabling custom workflow creation for tailored data processing tasks. The platform supports local LLMs (e.g., Llama, Mistral) and OpenAI vision models, prioritizing data privacy.

Quick Start & Requirements

• Install via Docker Compose.
• Configure environment variables using the provided mockenv file.
• Requires Docker.

Highlighted Details

• Advanced OCR for text, tables, and handwriting extraction.
• Auto-schema generation for document structure adaptation.
• Support for local LLMs (Llama, Mistral) and OpenAI vision models.
• Local data processing for enhanced privacy.

Maintenance & Community

• Active development, noted as a work in progress.
• Community support via Discord and GitHub Issues.
• Email support available.
• A cloud version (Alpha) is live; contact for access.

Licensing & Compatibility

• Licensed under AGPLv3.
• AGPLv3 is a strong copyleft license, requiring derivative works to also be open-sourced under AGPLv3. This may restrict commercial use or integration into closed-source products without careful consideration.

Limitations & Caveats

The project is explicitly stated as a work in progress and not yet ready for production use.