KeyBERT is a minimal and easy-to-use Python library that leverages BERT embeddings and cosine similarity to extract keywords and keyphrases from documents. It supports multiple embedding backends including sentence-transformers, Flair, and spaCy, with built-in diversity algorithms like Max Sum Similarity and Maximal Marginal Relevance.
36 stars
0 votes
0 copies
2 views
Added June 8, 2026
ai-agentspythongogitbackendsecurity
Security analysis
A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies
Installs into .claude/skills of the current project.
Are you the author of Keybert Keyword Extraction Bert?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/agentskillexchange-keybert-keyword-extraction-bert)
---
name: "KeyBERT Minimal Keyword Extraction with BERT Embeddings"
slug: "keybert-keyword-extraction-bert"
description: "KeyBERT is a minimal and easy-to-use Python library that leverages BERT embeddings and cosine similarity to extract keywords and keyphrases from documents. It supports multiple embedding backends including sentence-transformers, Flair, and spaCy, with built-in diversity algorithms like Max Sum Similarity and Maximal Marginal Relevance."
github_stars: 4143
verification: "security_reviewed"
source: "https://github.com/MaartenGr/KeyBERT"
category: "Content Writing & SEO"
framework: "Custom Agents"
tool_ecosystem:
github_repo: "MaartenGr/KeyBERT"
github_stars: 4143
---
# KeyBERT Minimal Keyword Extraction with BERT Embeddings
KeyBERT is a minimal and easy-to-use Python library that leverages BERT embeddings and cosine similarity to extract keywords and keyphrases from documents. It supports multiple embedding backends including sentence-transformers, Flair, and spaCy, with built-in diversity algorithms like Max Sum Similarity and Maximal Marginal Relevance.
## Installation
Use the upstream install or setup path that matches your environment:
- pip install keybert
- pip install keybert[flair]
- pip install keybert[gensim]
- pip install keybert[spacy]
Requirements and caveats from upstream:
- [](https://pypi.org/project/keybert/)
- python
Basic usage or getting-started notes:
- [Getting Started](#gettingstarted)
- 2.2. [Basic Usage](#usage)
- Thus, the goal was a pip install keybert and at most 3 lines of code in usage.
- Source: https://github.com/MaartenGr/KeyBERT
- Extracted from upstream docs: https://raw.githubusercontent.com/MaartenGr/KeyBERT/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/keybert-keyword-extraction-bert/)
