RRepoGEO

REPOGEO REPORT · LITE

MaartenGr/KeyBERT

Default branch master · commit 4d3230bb · scanned 5/27/2026, 9:42:29 PM

GitHub: 4,178 stars · 383 forks

AI VISIBILITY SCORE
92 /100
Healthy
Category recall
2 / 2
Avg rank #1.0 when recommended
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface MaartenGr/KeyBERT, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Refine README's opening sentence to clarify specific niche

    Why:

    CURRENT
    KeyBERT is a minimal and easy-to-use keyword extraction technique that leverages BERT embeddings to create keywords and keyphrases that are most similar to a document.
    COPY-PASTE FIX
    KeyBERT is a focused and easy-to-use Python library for semantic keyword and keyphrase extraction, leveraging BERT embeddings to identify the most relevant terms in a document.
  • mediumtopics#2
    Add `python` and `nlp-library` to topics

    Why:

    CURRENT
    bert, keyphrase-extraction, keyword-extraction, mmr
    COPY-PASTE FIX
    bert, keyphrase-extraction, keyword-extraction, mmr, python, nlp-library
  • mediumreadme#3
    Add a 'Comparison to other NLP tools' section in README

    Why:

    CURRENT
    The README mentions 'many methods available for keyword generation (e.g., Rake, YAKE!, TF-IDF, etc.)' but lacks a structured comparison with broader NLP tools.
    COPY-PASTE FIX
    Add a new section, e.g., `## KeyBERT's Niche: Beyond General NLP & Embeddings`, explaining that while KeyBERT leverages tools like Sentence-BERT for embeddings, it is a specialized library for keyword extraction, distinct from general NLP frameworks (like SpaCy) or raw embedding libraries. Briefly highlight its focus on semantic keyword extraction.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
2 / 2
100% of queries surface MaartenGr/KeyBERT
Avg rank
#1.0
Lower is better. #1 = top recommendation.
Share of voice
15%
Of all named tools, what % are you?
Top rival
YAKE! (Yet Another Keyword Extractor)
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. YAKE! (Yet Another Keyword Extractor) · recommended 1×
  2. SpaCy · recommended 1×
  3. Sentence-BERT · recommended 1×
  4. sentence-transformers · recommended 1×
  5. Gensim · recommended 1×
  • CATEGORY QUERY
    How to extract relevant keywords and keyphrases from text using BERT embeddings?
    you: #1
    AI recommended (in order):
    1. KeyBERT ← you
    2. YAKE! (Yet Another Keyword Extractor)
    3. SpaCy
    4. Sentence-BERT
    5. sentence-transformers
    6. Gensim
    7. Hugging Face Transformers
    Show full AI answer
  • CATEGORY QUERY
    Looking for a simple, powerful library to generate keywords from documents beyond TF-IDF.
    you: #1
    AI recommended (in order):
    1. KeyBERT ← you
    2. YAKE
    3. RAKE
    4. sumy
    5. textacy
    6. spaCy
    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of MaartenGr/KeyBERT?
    pass
    AI named MaartenGr/KeyBERT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts MaartenGr/KeyBERT in production, what risks or prerequisites should they evaluate first?
    pass
    AI named MaartenGr/KeyBERT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo MaartenGr/KeyBERT solve, and who is the primary audience?
    pass
    AI named MaartenGr/KeyBERT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of MaartenGr/KeyBERT. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/MaartenGr/KeyBERT.svg)](https://repogeo.com/en/r/MaartenGr/KeyBERT)
HTML
<a href="https://repogeo.com/en/r/MaartenGr/KeyBERT"><img src="https://repogeo.com/badge/MaartenGr/KeyBERT.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

MaartenGr/KeyBERT — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite