Represent, send, store and search multimodal data

Given a scholarly PDF, extract figures, tables, captions, and section titles.

The powerful framework for building documentation sites in Next.js.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Official implementation of Character Region Awareness for Text Detection (CRAFT)

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

A Python framework for high performance GPU simulation and graphics

The ioquake3 community effort to continue supporting/developing id's Quake III Arena

OCR, layout analysis, reading order, line detection in 90+ languages

AI Powered Image search tool offers content-based, text, and visual similarity system-wide search.

YOLOv10: Real-Time End-to-End Object Detection

A single API for all your integrations.

A massively parallel, high-level programming language

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

A GPU-based hydro code

An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Automate browser-based workflows with LLMs and Computer Vision

An open-source & self-hostable Heroku / Netlify / Vercel alternative.

Slouching tracker that rewards you for keeping your back straight

Convert PDF to markdown quickly with high accuracy

A ready-to-use landing page template made with TypeScript, React, Next.js, and TailwindCSS.

A machine learning software for extracting information from scholarly documents

Twitter data scraping, embedding based image search and more.

The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

✨✨Latest Advances on Multimodal Large Language Models

LLM training in simple, raw C/CUDA