# INESCTEC/yake

Single-document unsupervised keyword extraction

Repository: https://github.com/INESCTEC/yake
Canonical: https://ross.abutalabs.com/products/yake
Homepage: https://inesctec.github.io/yake
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: keyword-extraction, unsupervised-approach, corpus-independent, domain-and-language-independent, single-document, ai
Last push: 2026-02-11T17:48:40+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 37, longevity 100
- inputs: {"age_days": 2847, "days_push": 203, "days_rel": 205, "gap_med": 224, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1877, forks 247 (observed 2026-08-28T04:05:47.807207+00:00)

## What it is
YAKE! is a lightweight unsupervised keyword extraction library that ranks the most important keywords of a single document using text statistical features. It requires no training data, corpora, or dictionaries, and supports 25+ languages via a Python API and a command-line interface.

## Use cases
- extract keywords from a single document
- get keyphrases from text without training data
- multilingual keyword extraction
- find top n-grams in an article
- tag documents automatically with keywords
- extract keywords from a text file from the command line

## When to choose
- you need corpus- and dictionary-free keyword extraction that works out of the box
- you process single documents in many languages or domains
- you want a lightweight, fast statistical method rather than a heavy ML model

## When to avoid
- you need state-of-the-art semantic keyphrase extraction from large trained models
- you need topic modeling or keyword extraction across an entire corpus
- you require a license other than LGPLv3

## Facets
- artifact type: library
- maturity: stable
- function: nlp, parser
- domain: machine-learning, developer-tools
- platform: python, cli, cross-platform
- tags: keyword-extraction, unsupervised, multilingual, single-document, keyphrase-extraction, natural-language-processing

## Member repositories
- INESCTEC/yake (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:47.807207+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 2026-08-30T03:14:40.489798+00:00, confidence not recorded.
  - readme: https://github.com/INESCTEC/yake (fetched 2026-08-28T04:05:47.807207+00:00, sha 68d549ebc20d)
  - homepage: https://inesctec.github.io/yake (fetched 2026-08-29T10:53:32.362790+00:00, sha 98c93b119921)
  - site_page: https://oss.inesctec.pt/yake/docs/-getting-started (fetched 2026-08-29T10:53:32.371780+00:00, sha e8897bff0a27)
  - site_page: https://oss.inesctec.pt/yake/docs/--home (fetched 2026-08-29T10:53:32.373969+00:00, sha 866ed97925e6)
  - registry_pypi: https://pypi.org/pypi/yake/json (fetched 2026-08-29T10:53:32.375698+00:00, sha 28ad0597bb7a)
- Data as of 2026-08-30T08:39:29.467469+00:00.