spaCy

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

What is spaCy?

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

Overview of spaCy

What it is

spaCy is a library for advanced Natural Language Processing in Python and Cython. The README states it is built on research and designed to be used in real products. It provides pretrained pipelines and supports tokenization and training for 70+ languages. Version 3.8 is noted as the current release. The project is described as commercial open-source software released under the MIT license.

Key features

  • Pretrained pipelines and tokenization/training support for 70+ languages.
  • Neural network models for tagging, parsing, named entity recognition, text classification, and more.
  • Multi-task learning with pretrained transformers such as BERT.
  • A production-ready training system with model packaging, deployment, and workflow management.
  • Documentation covering usage guides, project templates, API reference, GPU processing, models, large language model integration, and the spaCy ecosystem.
  • A VS Code extension for working with spaCy config files.

Use cases

spaCy is intended for advanced NLP in Python and Cython and for use in real products. Its features support tasks such as tokenization, tagging, parsing, named entity recognition, and text classification. The training system and model packaging support workflows for training, deploying, and managing models. The documentation also covers integrating large language models into spaCy pipelines.

Getting started

The README does not include install or quick-start commands. See the repository README and documentation for setup and usage guidance.

License and pricing

spaCy is released under the MIT license. The metadata lists the pricing type as open source; no pricing is stated in the README or metadata.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/explosionspacy.svg)](https://yunodb.com/tools/explosionspacy?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/explosionspacy?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/explosionspacy.svg" alt="Featured on YunoDB" height="20"></a>