# miso-belica/sumy

Module for automatic summarization of text documents and HTML pages.

Repository: https://github.com/miso-belica/sumy
Canonical: https://ross.abutalabs.com/products/sumy
Homepage: https://miso-belica.github.io/sumy/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: python, lsa, textteaser, html-page, summarizer, pagerank-algorithm, reduction, text-extraction, html-extraction, html-extractor, sumy, summarization, summary, nlp
Last push: 2026-08-14T19:17:56+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 73, longevity 100
- inputs: {"age_days": 4942, "days_push": 19, "days_rel": 21, "gap_med": 178, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3701, forks 539 (observed 2026-08-28T04:08:14.956678+00:00)

## What it is
Sumy is a Python library and command-line utility for automatic extractive summarization of plain text documents and HTML pages. It implements multiple summarization algorithms (LexRank, LSA, TextRank, Luhn, Edmundson) with multilingual tokenizer support and a simple evaluation framework.

## Use cases
- summarize long articles into key sentences
- extract summaries from HTML web pages
- summarize text in multiple languages
- evaluate summarization quality against reference summaries
- add extractive summarization to a Python application
- quickly condense a Wikipedia page from the command line

## When to choose
- you need lightweight extractive summarization without GPU or deep learning models
- you want a CLI tool for quick one-off summarization of URLs or text files
- you need support for many natural languages including Czech/Slovak
- you want a simple, dependency-light Python API for summarization

## When to avoid
- you need abstractive summaries that rewrite text in new sentences
- you need state-of-the-art neural summarization quality
- you need to summarize very long documents beyond its design scope

## Facets
- artifact type: library
- maturity: active
- function: nlp, parser, cli
- domain: developer-tools
- platform: python, cli, cross-platform
- tags: text-summarization, extractive-summarization, textrank, lexrank, lsa, html-extraction, natural-language-processing

## Member repositories
- miso-belica/sumy (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:14.956678+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:02.065791+00:00, confidence not recorded.
  - readme: https://github.com/miso-belica/sumy (fetched 2026-08-28T04:08:14.956678+00:00, sha 094c2c935fb0)
  - homepage: https://miso-belica.github.io/sumy/ (fetched 2026-08-29T09:24:38.799090+00:00, sha ebbdfbb87f21)
  - registry_pypi: https://pypi.org/pypi/sumy/json (fetched 2026-08-29T09:24:38.808407+00:00, sha 2f1ebb96cc7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.