{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/3"},{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/4"}],"enrichment":{"capability":"KeyBERT extracts keywords and keyphrases from documents by computing BERT embeddings and finding n-grams most similar to the document as a whole using cosine similarity.","skillfed_tags":["nlp","embeddings","information-extraction"],"use_cases":["Extract single-word keywords from research papers or articles to build document summaries or search indices.","Generate multi-word keyphrases from product descriptions or customer feedback to identify key topics.","Diversify keyword results using maximal marginal relevance to avoid redundant or near-duplicate extractions.","Build a document tagger by extracting keywords and using them to label or categorize incoming text.","Integrate semantic keyword extraction into a content recommendation system to match documents by extracted terms."],"what_it_does":"KeyBERT is a lightweight keyword extraction library that uses pre-trained BERT embeddings to identify the words and phrases in a document that best represent its semantic content. It works by computing a document-level embedding, then embedding candidate n-grams, and ranking them by cosine similarity to the document. The library requires four runtime dependencies: numpy and scikit-learn for numerical operations, sentence-transformers to load and run embedding models, and rich for output formatting.\n\nThe package is designed for minimal setup. It supports multiple extraction strategies, configurable n-gram ranges, and pluggable embedding backends. It is actively maintained, supports Python 3.8, 3.9, 3.10, 3.11, and 3.12, and has no known security vulnerabilities.","worth_installing":"Yes. KeyBERT is worth installing for semantic keyword extraction tasks. It has low install friction, active maintenance, permissive licensing, no known vulnerabilities, and a straightforward API. The main consideration is that sentence-transformers downloads a transformer model on first use; verify that the model can be pre-cached and that extraction latency meets your needs."},"id":"keybert","links":{"html":"https://skillfed.io/packages/keybert","md":"https://skillfed.io/packages/keybert.md","pypi":"https://pypi.org/project/keybert/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2025-02-07","license_spdx":null,"license_treatment":"permissive","name":"keybert","python_support":"supports_current","summary":"KeyBERT performs keyword extraction with state-of-the-art transformer models."},"popularity":{"monthly_downloads":720941,"position":5232,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.9.0"}