Pipeline

75

Custom pipeline components and extensions

amrlib

A python library that makes AMR parsing, generation and visualization simple.

Asent

Fast, flexible and transparent sentiment analysis

Bagpipes spaCy

A bag of custom spaCy pipes for various NLP tasks.

Classy Classification

Have you ever struggled with needing a spaCy TextCategorizer but didn't have the time to train one from scratch? Classy Classification is the way to go!

concepCy

A multilingual knowledge graph in spaCy

Concise Concepts

Concise Concepts uses few-shot NER based on word embedding similarity to get you going with easy!

Contextual Spell Check

Contextual spell correction using BERT (bidirectional representations)

Coreferee

Coreference resolution for multiple languages

VA COVID-19 NLP BSV

spaCy pipeline for COVID-19 surveillance.

Crosslingual Coreference

One multi-lingual coreference model to rule them all!

DaCy

An efficient Pipeline for Danish NLP

Date spaCy

Effortless Date Recognition in Text with spaCy

Dframcy

Dataframe Integration with spaCy NLP

EDS-NLP

spaCy components to extract information from clinical notes written in French.

eng_spacysentiment

Simple sentiment analysis using spaCy pipelines

Forte

Forte is a toolkit for building Natural Language Processing pipelines, featuring cross-task interaction, adaptable data-model interfaces and composable pipelines.

GLiNER spaCy Wrapper

Integrating GLiNER's Advanced NER with spaCy

greCy

Ancient Greek pipelines for spaCy

Healthsea

Healthsea: an end-to-end spaCy pipeline for exploring health supplement effects

Hammurabi

Python Rule Processing Engine 🏺

Hobbit spaCy

NLP for Middle Earth

Holmes

Information extraction from English and German texts based on predicate logic

Klayers

spaCy as a AWS Lambda Layer

LatinCy

Synthetic trained spaCy pipelines for Latin NLP

lemminflect

A Python module for English lemmatization and inflection

Lemmy

A Danish lemmatizer

negspaCy

spaCy pipeline object for negating concepts in text based on the NegEx algorithm.

Number spaCy

Enhancing Numeric Entity Recognition in Text with spaCy

OdyCy

General-purpose language pipelines for premodern Greek.

phruzz-matcher

Phrase matcher using RapidFuzz

presque

Normalizer for contemporary French

PyATE

Python Automated Term Extraction

pyInflect

A Python module for word inflections

quelquhui

Tokenizer for contemporary French

A spaCy Package for Romanian Legal Document Processing

rolegal: a spaCy Package for Noisy Romanian Legal Document Processing

ruTS

A library for statistics extraction from texts in Russian

scrubadub_spacy

Remove personally identifiable information from text using spaCy.

Berkeley Neural Parser

Constituency Parsing with a Self-Attentive Encoder (ACL 2018)

sense2vec

Use NLP to go beyond vanilla word2vec

English Interpretation Sentence Pattern

English interpretation for accurate translation from English to Japanese

Sentimental Onix

Use onnx for sentiment models

skweak

Weak supervision for NLP

solipCysme

spaCy pipeline for french fictions and first person point of view texts.

spaCy-CLD

Add language detection to your spaCy pipeline using CLD2

Spacy FastLang

Language detection done fast

spacy_readability

Add text readability meta data to Doc objects

Spacy Syllables

Multilingual syllable annotations

spacy-clausie

Implementation of the ClausIE information extraction system for Python+spaCy

spacy_conll

Parsing from and to CoNLL-U format with `spacy`, `spacy-stanza` and `spacy-udpipe`

DBpedia Spotlight for SpaCy

Use DBpedia Spotlight to link entities inside SpaCy

spacy-huggingface-hub

Push your spaCy pipelines to the Hugging Face Hub

spacy-iwnlp

German lemmatization with IWNLP

spacy-layout

Process PDFs, Word documents and more with spaCy

spacy-lefff

POS and French lemmatization with Lefff

spaCy - Partial Tagger

Sequence Tagger for Partially Annotated Dataset in spaCy

PyTextRank

Py impl of TextRank for lightweight phrase extraction

spaCy-PyThaiNLP

PyThaiNLP for spaCy

spaCy - sentence-transformers

Pipelines for pretrained sentence-transformers (BERT, RoBERTa, XLM-RoBERTa & Co.) directly within spaCy

spacy-sentiws

German sentiment scores with SentiWS

spacy-stanza

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

spacytextblob

A TextBlob sentiment analysis pipeline component for spaCy.

spacy-transformers

spaCy pipelines for pretrained BERT, XLNet and GPT-2

spacy-udpipe

Use the latest UDPipe models directly in spaCy

spaCy - Universal Sentence Encoder

Make use of Google's Universal Sentence Encoder directly within spaCy

spacy-wordnet

WordNet meets spaCy

spaCy-wrap

For Wrapping fine-tuned transformers in spaCy pipelines

spaCy fishing

Named entity disambiguation and linking on Wikidata in spaCy with Entity-Fishing.

spacymoji

Emoji handling and meta data as a spaCy pipeline component

spaCyOpenTapioca

Named entity linking on Wikidata in spaCy via OpenTapioca

spacypdfreader

Easy PDF to text to spaCy text extraction in Python.

spaCy-SetFit

An an easy and intuitive approach to use SetFit in combination with spaCy.

spaczz

Fuzzy matching and more for spaCy.

SpanMarker

Effortless state-of-the-art NER in spaCy

TextDescriptives

Extraction of descriptive stats, readability, and syntactic complexity measures

tokenwiser

Connect vowpal-wabbit & scikit-learn models to spaCy to run simple classification benchmarks. Comes with many utility functions for spaCy pipelines.

Found a mistake or something isn't working?

If you've come across a universe project that isn't working or is incompatible with the reported spaCy version, let us know by opening a discussion thread.

Submit your project

If you have a project that you want the spaCy community to make use of, you can suggest it by submitting a pull request to the spaCy website repository. The Universe database is open-source and collected in a simple JSON file. For more details on the formats and available fields, see the documentation. Looking for inspiration your own spaCy plugin or extension? Check out the project idea section in Discussions.

Read the docs JSON source