Repository Index

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

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

• extract-data
• layout-analysis
• ocr
• parser

Code and documentation to train Stanford's Alpaca models, and generate the data.

• deep-learning
• instruction-following
• language-model

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

• nlp
• pre-trained-model
• unilm
• minilm

☁️ Build multimodal AI applications with cloud-native stack

• neural-search
• cloud-native
• deep-learning
• machine-learning

TranslatedSelf-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.

• tiktok
• douyin
• scraper
• crawler

Generate audiobooks from e-books, 50+ TTS engines with voice cloning and 1696 languages!

• audiobooks
• docker
• epub
• linux

Topic Modelling for Humans

• gensim
• topic-modeling
• information-retrieval
• machine-learning

TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version

• ocr
• ddddocr
• captcha

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

• api
• llm
• api-documentation
• chatgpt

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

• nlp
• embedding
• bert
• ernie

OCR & Document Extraction using vision models

• ocr
• pdf

Open source annotation tool for machine learning practitioners.

• natural-language-processing
• machine-learning
• annotation-tool
• python

Open Machine Learning Course

• machine-learning
• data-analysis
• data-science
• pandas

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

• yolox
• yolov3
• onnx
• tensorrt

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

• ai
• code-intelligence
• dead-code
• developer-tools

:house: Home Assistant configuration & Documentation for my Smart House. Write-ups, videos, part lists, and links throughout. Be sure to :star: it. Updated FREQUENTLY!

• home-assistant
• home-automation
• automation
• homeautomation

Module for automatic summarization of text documents and HTML pages.

• python
• lsa
• textteaser
• html-page

🛠 All-in-one web-based IDE specialized for machine learning and data science.

• machine-learning
• deep-learning
• data-science
• docker

Lightweight AI-friendly Docker Swarm management

• docker
• swarm
• management
• ui

An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

• agent
• llm-tools
• ocr
• vlm

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

• cli
• docker
• docker-compose
• llm

README file generator, powered by AI.

• readme-generator
• readme
• readme-md-generator
• ai

Deep neural network to extract intelligent information from invoice documents.

• invoice
• invoice-management
• invoices
• invoice-insight