Discover explosion/spacy-ray Open Source project

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

28,700

thinc

👩‍🏫 Advanced NLP with spaCy: A free online course

2,777

spacy-course

🦆 Contextually-keyed word vectors

2,268

sense2vec

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

1,595

spacy-models

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

1,516

spacy-transformers

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

1,320

projects

🦙 Integrating LLMs into structured NLP pipelines

1,249

spacy-llm

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

950

curated-transformers

👑 spaCy building blocks and visualizers for Streamlit apps

837

spacy-streamlit

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

765

spacy-stanza

🍳 Recipes for the Prodigy, our fully scriptable annotation tool

715

prodigy-recipes

🍣 A lightweight console printing and formatting toolkit

464

wasabi

💥 Cython memory pool for RAII-style memory management

438

cymem

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

434

srsly

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

414

displacy

JavaScript

344

lightnet

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

319

prodigy-openai-recipes

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

💫 Jupyter notebooks for spaCy examples and tutorials

315

spacy-notebooks

💫 REST microservices for various spaCy-related tasks

284

spacy-services

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

239

cython-blis

209

displacy-ent

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

CSS

196

jupyterlab-prodigy

🧬 A JupyterLab extension for annotating data with Prodigy

TypeScript

187

tokenizations

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

Rust

179

spacymoji

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

🎡 Automated build repo for Python wheels and source packages

177

wheelwright

Super lightweight function registries for your library

173

catalogue

🍬 Confection: the sweetest config system for Python

170

confection

💫 Scripts, tools and resources for developing spaCy

165

spacy-dev-resources

🕊️ Radically lightweight command-line interfaces

125

radicli

🧪 Cutting-edge experimental spaCy components and features

spacy-experimental

📂 Additional lookup tables and data resources for spaCy

spacy-lookups-data

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

talks

JavaScript

thinc-apple-ops

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

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

healthsea

💥 Cython hash tables that assume keys are pre-hashed

preshed

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

spacy-huggingface-pipelines

🌊 Machine learning dataset loaders for testing and example scripts

ml-datasets

💥 Cython bindings for MurmurHash2

assets

💥 Explosion Assets

murmurhash

C++

weasel

🦦 weasel: A small and easy workflow system

🤗 Push your spaCy pipelines to the Hugging Face Hub

spacy-huggingface-hub

🧬 A VS Code extension for annotating data with Prodigy

vscode-prodigy

TypeScript

wikid

Generate a SQLite database from Wikipedia & Wikidata dumps.

💫 A spaCy package for Yohei Tamura's Rust tokenizations library

spacy-alignments

spaCy extension for Visual Studio Code

spacy-vscode

💫 Runtime performance comparison of spaCy against other NLP libraries

spacy-benchmarks

spaCy entry points for Curated Transformers

spacy-curated-transformers

Train huggingface models on top of Prodigy annotations

prodigy-hf

spacy-vectors-builder

🌸 Train floret vectors

Wrapper for the macOS signpost API

os-signpost

A Prodigy plugin for PDF annotation

prodigy-pdf

📟 Logging utilities for spaCy

spacy-loggers

🔎 A Prodigy plugin for evaluating spaCy pipelines

prodigy-evaluate

Select pixels in Prodigy via Facebook's Segment-Anything model.

prodigy-segment

Lightweight piece tokenization library

curated-tokenizers

A slightly cleaned up version of the scripts & data for the CoNLL 2012 Coreference task.

conll-2012

Code for our presentation in Princeton DH 2023 April.

thinc_gpu_ops

🔮 GPU kernels for Thinc

C++

princetondh

🕸️ Legacy architectures and other registered spaCy v3.x functions for backwards-compatibility

spacy-legacy

A Prodigy pluging for ANN techniques

prodigy-ann

Audio transcription with OpenAI's whisper model in the loop.

prodigy-whisper

ec2buildwheel

Materials for the aiGrunn 2023 talk on spaCy Transformer pipelines

aiGrunn-2023

📒 Repository used to build Binder images for the interactive spaCy code examples

spacy-io-binder

A Prodigy plugin for document search via LUNR

prodigy-lunr

:octocat: GitHub settings

.github

span-labeling-datasets

Loaders for various span labeling datasets