miso-belica/sumy

Module for automatic summarization of text documents and HTML pages.

What it solves

It provides a way to automatically extract summaries from HTML pages or plain text documents, supporting multiple languages and providing tools to evaluate the quality of those summaries.

How it works

The library uses various summarization methods (such as LexRank, LSA, Luhn, and Edmundson) to process text parsed from URLs or files. It utilizes tokenizers and stemmers to handle different natural languages and can be used either as a command-line utility or as a Python API.

Who it’s for

Developers who need to integrate text summarization into their applications or users who want a quick command-line tool for condensing long documents.

Highlights

  • Multi-language support with an easy path to add new languages.
  • Supports both HTML and plain text inputs.
  • Includes a built-in evaluation framework for testing summary quality.
  • Available as a Python library, CLI tool, and Docker container.

Related

  • Project
    steipete/summarize

    A tool for extracting clean text from web pages, documents, and multimedia files to generate AI-powered summaries via a CLI or browser extension.

  • Project
    deanmalmgren/textract

    A Python library that provides a unified interface to extract text from various document formats, simplifying the data preparation process for text analysis.

  • Project
    dw-dengwei/daily-arXiv-ai-enhanced

    An automated tool that crawls daily arXiv papers and uses AI to generate summaries, deploying entirely via GitHub Actions and Pages.

  • Project
    zh-plus/openlrc

    A Python library that transcribes audio using faster-whisper and uses LLMs to translate and polish the text into synchronized .lrc subtitles.

  • Project
    goodmami/wn

    A Python library for exploring and querying multilingual wordnets, providing tools for semantic similarity, taxonomic exploration, and lemmatization.