explosion

💫 Industrial-strength Natural Language Processing (NLP) in Python

🔮 A refreshing functional take on deep learning, compatible with your favorite libraries

👩‍🏫 Advanced NLP with spaCy: A free online course

💫 Models for the spaCy Natural Language Processing (NLP) library

🦆 Contextually-keyed word vectors

🪐 End-to-end NLP workflows from prototype to production

🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

🦙 Integrating LLMs into structured NLP pipelines

📚 Process PDFs, Word documents and more with spaCy

🤖 A PyTorch library of curated Transformer models and their composable components

👑 spaCy building blocks and visualizers for Streamlit apps

💥 Use the latest Stanza (StanfordNLP) research models directly in spaCy

🍳 Recipes for the Prodigy, our fully scriptable annotation tool

🦉 Modern high-performance serialization utilities for Python (JSON, MessagePack, Pickle)

🍣 A lightweight console printing and formatting toolkit

💥 Cython memory pool for RAII-style memory management

displaCy.js: An open-source NLP visualiser for the modern web

🌓 Bringing pjreddie's DarkNet out of the shadows #yolo

✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3

💫 Jupyter notebooks for spaCy examples and tutorials

💫 REST microservices for various spaCy-related tasks

💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!

displaCy-ent.js: An open-source named entity visualiser for the modern web

Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/

Confection: the sweetest config system for Python

🧬 A JupyterLab extension for annotating data with Prodigy

Super lightweight function registries for your library

💙 Emoji handling and meta data for spaCy with custom extension attributes

🎡 Automated build repo for Python wheels and source packages

💫 Scripts, tools and resources for developing spaCy

📂 Additional lookup tables and data resources for spaCy

🕊️ Radically lightweight command-line interfaces

🧪 Cutting-edge experimental spaCy components and features

🍏 Make Thinc faster on macOS by calling into Apple's native Accelerate library

💥 Browser-based slides or PDFs of our talks and presentations

🦦 weasel: A small and easy workflow system

Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.

💥 Cython hash tables that assume keys are pre-hashed

💥 Use Hugging Face text and token classification pipelines directly in spaCy

☄️ Parallel and distributed training with spaCy and Ray