explosion/spaCy

Project overview

A Python library providing Natural Language Processing capabilities including tagging, parsing, named entity recognition, and text classification. It includes pretrained pipelines for over 70 languages and a training system designed for real products.

Project type

Document Processing · Data Processing

Use cases

Data Analysis

Deployment

Refer to project documentation

License

MIT

Best for

• Developers, data teams, and researchers who need to process text and train models for tagging, parsing, named entity recognition, and text classification.

Key capabilities

• Provides pretrained pipelines supporting tokenization and training for over 70 languages.
• Features neural network models for tagging, parsing, named entity recognition, and text classification.
• Supports multi-task learning with pretrained transformers like BERT.
• Provides a production-ready training system with easy model packaging, deployment, and workflow management.

Limitations and risks

• Model downloading may fail in environments without pip on PATH.

Getting started

• Requires installing the Python library and potentially downloading specific pretrained pipelines or models.

Evidence and sources

• README: spaCy is a library for **advanced Natural Language Processing** in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real prod…
• GitHub project description: 💫 Industrial-strength Natural Language Processing (NLP) in Python
• Release: v3.8.14: Bug fix for model downloading in environments without pip on PATH
• README: spaCy is commercial open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).

Reviewed at: 2026-07-15T02:18:56Z