HF KeyBERT

HF KeyBERT

Pulls keywords out of text with KeyBERT in a Streamlit page, for researchers, students and developers who want to try keyword extraction without writing code.

Made by Hellisotherpeople on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: HF KeyBERT is a Streamlit app that, by its name, extracts keywords from text with KeyBERT. KeyBERT is a keyword extraction method built on BERT-style models. The record names the DebateSum dataset as its data.

Who it suits: It suits researchers, students and writers who want the key terms of a text, and developers who want a small Streamlit example. The record has no usage notes, so expect to learn the page by clicking through it.

Industry | Who uses it | How they use it | Example
Research | Text analysts | Pull the main terms from documents | Paste a passage and read the keywords
Education | Students and teachers | See which terms stand out in a text | Compare keywords from two passages
Software | Python developers | Read a small keyword extraction app | Open app.py and follow how the page is built

You can skip it if you need a tested pipeline for production data.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Python 3.12 on Windows, macOS or Linux, from a downloaded copy

Use case | Who | What they get back
Find key terms in a text | Analysts and students | A list of keywords for the text
Teach keyword extraction | Teachers | A hands-on page to click through
Reuse the app as a base | Developers | A small Streamlit app to adapt

How to set it up:

• Nothing at all if you use the online Space
• Python 3.12 on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install Streamlit and the listed requirements.
4. Start the app with Streamlit.

pip install -U huggingface_hub
hf download Hellisotherpeople/HF-KeyBERT --repo-type space --local-dir HF-KeyBERT
cd HF-KeyBERT
pip install streamlit
pip install -r requirements.txt
streamlit run app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file with Streamlit from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

streamlit run app.py

Example: You open the Space and give it a passage of text, or use the data it names. The app returns the keywords it finds in that text. The record shows no sample output, so check the page.

For newcomers and experts: Keyword extraction picks the words or short phrases that best sum up a text. Start by opening the Space and trying one short passage, then see whether the keywords match what you would pick.

If you know the field, KeyBERT ranks candidate phrases by how close their embeddings sit to the whole text. Results therefore depend on the model and settings, and the record gives no parameters or accuracy figures.

You give the app a text
The app finds candidate words and phrases
It compares each one with the whole text
The page shows the best matches

Good to know:

• License: MIT, as listed on the Space
• Cost to run: none named
• Data it reaches: the text you provide and the DebateSum dataset it names
• Not for: the record names no exclusions, and it gives no accuracy figures

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: streamlit
• License: mit

Links

• Space: https://huggingface.co/spaces/Hellisotherpeople/HF-KeyBERT
• Files: https://huggingface.co/spaces/Hellisotherpeople/HF-KeyBERT/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.