miso-belica/sumy ↗
Created Jan 2, 2021 · View the miso-belica/sumy repository page
Module for automatic summarization of text documents and HTML pages.
Want this for your repo?
Render a free sample of any GitHub repo in seconds.
Contributors
21
Lines of Code
958
From
Feb 20, 2013
To
Nov 21, 2020
About miso-belica/sumy
Sumy is a Python library and command-line tool for automatically summarizing text documents and HTML pages. It provides multiple summarization algorithms including LSA (Latent Semantic Analysis) and PageRank-based approaches, along with an evaluation framework for assessing summary quality. The tool supports numerous natural languages through its tokenizer infrastructure and can be used either as a standalone utility or imported as a library into other projects.
The package is designed to be accessible to users of varying technical levels. It offers a web-based interface through Hugging Face Spaces for quick browser testing, command-line utilities for direct document summarization, and a Python API for programmatic use. Installation is straightforward via pip or the recommended uv package manager, with the option to run it in a container. The documentation includes guides for adding support for new languages and references to alternative implementations in other programming languages.
Sumy has been adopted in several interesting downstream projects, including automatic question generation systems, video summarization tools, discussion thread summarizers, and automated TL;DR bots for social platforms like Lemmy. The project maintains an active development approach, requiring Python 3.8 or higher and welcoming community contributions.
