Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
47,133 repositories indexed
1–24 of 31 · Most stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
Translated100+ Chinese Word Vectors
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A Python scikit for building and analyzing recommender systems
A Python implementation of LightFM, a hybrid recommendation algorithm.
On-device wake word detection powered by deep learning
Turn any script into viral, multi-style animated stickman videos for Faceless YouTube Channels. Automate visuals, voiceover, captions & SFX. 100% Free & Open-Source.
Fast Python Collaborative Filtering for Implicit Feedback Datasets
Module for automatic summarization of text documents and HTML pages.
Python library for portfolio optimization, factor model construction, and risk management built on scikit-learn
A curated list of community detection research papers with implementations.
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
TranslatedImage-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser. Image-driven 3D scene generation system
fastFM: A Library for Factorization Machines
Upscale an image by a factor of 4, while generating photo-realistic details.
Scalable, event-driven, deep-learning-friendly backtesting library
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018