Keyphrasetransformer: Extract Key Phrases from Text

Understand the project

Practical overview

Use it when a Python workflow needs candidate phrases or topics from text as an input to a later step such as indexing, review or analysis.

Before you choose

The repository identifies the project as open source and lists the MIT license.

The documented interface is a Python library, so it fits code-based workflows rather than a standalone document-management process.
The README describes automatic unigram, bigram or trigram extraction and internal chunking for long text.
The repository provides a Hugging Face Spaces demo link in addition to the package interface.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Use the documented library interface to pass a text document to KeyPhraseTransformer and receive extracted phrases.

Install the package with the command below.
Documented command
```
pip install keyphrasetransformer
```
Import KeyPhraseTransformer from keyphrasetransformer and create an instance.
Pass a text string to the instance's get_key_phrases method.

A list of extracted candidate phrases, as shown in the README example.

The documented example returns phrases; it does not describe a broader indexing or topic-analysis workflow.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 16 October 2026
Original website title: Shivanandroy/KeyPhraseTransformer · Official homepage title · retained in its source language