miso-belica/sumy

Module for automatic summarization of text documents and HTML pages.

83
/ 100
Verified

Implements multiple extractive summarization algorithms (LSA, LexRank, Luhn, Edmundson) with multilingual tokenizer support across 50+ languages, enabling language-agnostic text processing. Provides both a Python API and CLI interface with built-in evaluation framework for comparing summaries against reference texts. Handles diverse input formats including HTML pages, plain text, and URLs with configurable output lengths.

3,665 stars and 165,186 monthly downloads. Used by 3 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.

Maintenance 13 / 25
Adoption 23 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

3,665

Forks

541

Language

Python

License

Apache-2.0

Last pushed

Feb 14, 2026

Monthly downloads

165,186

Commits (30d)

1

Dependencies

7

Reverse dependents

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/miso-belica/sumy"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.