SGLang is a fast serving framework for large language models and vision language models.

Toolkit for linearizing PDFs for LLM datasets/training

📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.

QGIS Pip Manager plugin allows users to manage Python packages within their QGIS environment

Get your documents ready for gen AI

Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.

Proxmox VE Helper-Scripts (Community Edition)

Tailscale Docker Proxy

GloVe and BERT language models re-trained using geoscientific text.

OCR, layout analysis, reading order, table recognition in 90+ languages

A curated list of resources around PDF files

A curated list of resources for Document Understanding (DU) topic

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website …

Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part of the native OS, including Nautilus integration.

Web interface for recognizing text, proofreading OCR, and creating fully-digitized documents.

🤖 Just a command runner

Kolmogorov Arnold Networks

Rust task runner and build tool.

Your CLI home video recorder 📼

A more powerful alternative to sysctl(8) with a terminal user interface 🐧

This is simple python macro script for LibreOffice to help you generate content from selected words/sentences with OpenAI & Google AI

Python bindings for libimagequant

The definitive Web UI for local AI, with powerful features and easy setup.

LLM inference in C/C++

PDF OCR Application, adds an OCR text layer to scanned PDF files, allowing them to be copied and searched.

A Qiqqa Test Library / Test Corpus which contains various PDF document samples, etc. collected from live Qiqqa libraries to showcase issues and check regressions in the software.

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

A carefully-designed OCR pipeline for universal boarded table recognition and reconstruction.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities