Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…

The fastest way to create an HTML app

logfmt (key=value) logger and parser

😱 Falsehoods Programmers Believe in

pyaddress is an address parsing library, taking the guesswork out of using addresses in your applications. We use it as part of our apartment search and apartment spider applications.

📯 Parse, normalize and render postal addresses.

natural language classification engine for geocoding

an open source geocoder for openstreetmap data

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

Learning embeddings for classification, retrieval and ranking.

A library for efficient similarity search and clustering of dense vectors.

Easily compute clip embeddings and build a clip retrieval system with them

An open source implementation of CLIP.

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

A Gradio web UI for Large Language Models with support for multiple inference backends.

🙌 OpenHands: Code Less, Make More

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

CoreNet: A library for training deep neural networks

Zuul is a gateway service that provides dynamic routing, monitoring, resiliency, security, and more.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Detect file content types with deep learning

New Godot bindings for Swift

Train transformer language models with reinforcement learning.

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Simple Have I Been Pwned checker for KeePass

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""