Explosion

All

77 repositories

murmurhash
Public
💥 Cython bindings for MurmurHash2
cython murmurhash murmurhash2
C++
•
MIT License
•21•44•1•0•Updated Sep 15, 2025Sep 15, 2025
radicli
Public
🕊️ Radically lightweight command-line interfaces
python cli command-line argparse command-line-interface
Python
•
MIT License
•6•106•2•0•Updated Sep 9, 2025Sep 9, 2025
prodigy-pdf
Public
A Prodigy plugin for PDF annotation
Python
•
MIT License
•5•35•0•0•Updated Aug 11, 2025Aug 11, 2025
spacy-pkuseg
Public
pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation
Python
•
MIT License
•985•62•0•0•Updated Jul 14, 2025Jul 14, 2025
thinc
Public
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
machine-learning natural-language-processing ai mxnet functional-programming tensorflow pytorch artificial-intelligence machine-learning-library type-checking
Python
•
MIT License
•283•2.9k•16•6•Updated Jul 11, 2025Jul 11, 2025
thinc-apple-ops
Public
🍏 Make Thinc faster on macOS by calling into Apple's native Accelerate library
apple spacy thinc
Cython
•
MIT License
•8•101•0•0•Updated Jun 30, 2025Jun 30, 2025
cython-blis
Public
💥 Fast matrix-multiplication as a self-contained Python library – no system dependencies!
neural-network numpy cython linear-algebra matrix-multiplication neural-networks blas openblas blas-libraries blis
C
•
Other
•42•226•15•5•Updated Jun 9, 2025Jun 9, 2025
spacy-lookups-data
Public
📂 Additional lookup tables and data resources for spaCy
nlp machine-learning natural-language-processing spacy lemmatization
Python
•
MIT License
•54•108•0•2•Updated Jun 4, 2025Jun 4, 2025
spacy-alignments
Public
💫 A spaCy package for Yohei Tamura's Rust tokenizations library
Python
•
MIT License
•5•32•0•0•Updated Jun 3, 2025Jun 3, 2025
spaCy
Public
💫 Industrial-strength Natural Language Processing (NLP) in Python
data-science machine-learning ai deep-learning neural-network text-classification cython artificial-intelligence named-entity-recognition neural-networks
Python
•
MIT License
•4.6k•33k•171•33•Updated May 28, 2025May 28, 2025
spacy-curated-transformers
Public
spaCy entry points for Curated Transformers
Python
•
MIT License
•6•32•0•1•Updated May 28, 2025May 28, 2025
cymem
Public
💥 Cython memory pool for RAII-style memory management
cython python
Cython
•
MIT License
•31•458•2•3•Updated May 28, 2025May 28, 2025
spacy-models
Public
💫 Models for the spaCy Natural Language Processing (NLP) library
machine-learning natural-language-processing models statistical-models machine-learning-models nlp spacy spacy-models
Python
•309•1.8k•0•0•Updated May 27, 2025May 27, 2025
spacy-transformers
Public
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
nlp machine-learning natural-language-processing google openai transfer-learning language-model natural-language-understanding spacy-pipeline spacy-extension
Python
•
MIT License
•173•1.4k•0•1•Updated May 26, 2025May 26, 2025
preshed
Public
💥 Cython hash tables that assume keys are pre-hashed
hashing cython hash-table hash-tables python
Cython
•
MIT License
•19•85•2•0•Updated May 26, 2025May 26, 2025
floret
Public
🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy
word-embeddings spacy fasttext word-vectors fasttext-embeddings subword-embeddings
C++
•
MIT License
•4.8k•321•3•1•Updated Apr 25, 2025Apr 25, 2025
sense2vec
Public
🦆 Contextually-keyed word vectors
python nlp machine-learning natural-language-processing word2vec spacy gensim sense2vec gensim-word2vec
Python
•
MIT License
•241•1.7k•23•0•Updated Apr 23, 2025Apr 23, 2025
confection
Public
🍬 Confection: the sweetest config system for Python
Python
•
MIT License
•12•190•6•3•Updated Apr 11, 2025Apr 11, 2025
spacy-vscode
Public
spaCy extension for Visual Studio Code
Python
•
MIT License
•7•32•2•0•Updated Mar 10, 2025Mar 10, 2025
spacy-layout
Public
📚 Process PDFs, Word documents and more with spaCy
nlp pdf natural-language-processing pdf-converter spacy docx document-layout document-layout-analysis rag generative-ai
Python
•
MIT License
•55•752•18•6•Updated Mar 8, 2025Mar 8, 2025
spacy-course
Public
👩‍🏫 Advanced NLP with spaCy: A free online course
machine-learning natural-language-processing course jupyter named-entity-recognition online-course dependency-parsing gatsbyjs word-vectors part-of-speech-tagging
Python
•
MIT License
•377•2.4k•14•0•Updated Feb 7, 2025Feb 7, 2025
srsly
Public
🦉 Modern high-performance serialization utilities for Python (JSON, MessagePack, Pickle)
python serialization json msgpack python-3 python-2 ujson yaml pickle
Python
•
MIT License
•34•473•5•4•Updated Jan 16, 2025Jan 16, 2025
blis
Public
BLAS-like Library Instantiation Software Framework
C
•
Other
•392•1•0•1•Updated Jan 10, 2025Jan 10, 2025
spacy-llm
Public
🦙 Integrating LLMs into structured NLP pipelines
nlp machine-learning natural-language-processing text-classification spacy falcon named-entity-recognition openai llama claude
Python
•
MIT License
•102•1.3k•37•9•Updated Jan 8, 2025Jan 8, 2025
projects
Public
🪐 End-to-end NLP workflows from prototype to production
nlp natural-language-processing annotations datasets prodigy spacy
Python
•
MIT License
•467•1.4k•2•4•Updated Oct 15, 2024Oct 15, 2024
prodigy-lunr
Public
A Prodigy plugin for document search via LUNR
Python
•
MIT License
•0•3•0•0•Updated Aug 27, 2024Aug 27, 2024
spacy-stanza
Public
💥 Use the latest Stanza (StanfordNLP) research models directly in spaCy
nlp data-science machine-learning natural-language-processing stanford-corenlp stanford-nlp stanza corenlp stanford-machine-learning spacy-pipeline
Python
•
MIT License
•62•739•8•6•Updated Aug 15, 2024Aug 15, 2024
prodigy-recipes
Public
🍳 Recipes for the Prodigy, our fully scriptable annotation tool
nlp data-science machine-learning natural-language-processing computer-vision annotation artificial-intelligence spacy prodigy active-learning
Jupyter Notebook
•114•502•0•6•Updated Aug 4, 2024Aug 4, 2024
spacy-streamlit
Public
👑 spaCy building blocks and visualizers for Streamlit apps
nlp machine-learning natural-language-processing text-classification visualizer named-entity-recognition ner dependency-parsing tokenization word-vectors
Python
•
MIT License
•118•844•7•2•Updated Jul 29, 2024Jul 29, 2024
weasel
Public
🦦 weasel: A small and easy workflow system
python
Python
•
MIT License
•12•85•9•5•Updated Jun 28, 2024Jun 28, 2024