Recommend Similar Papers

Recommend Similar Papers

Suggests research papers that are similar to one you already know, using a paper recommendation dataset, in a Gradio app that runs on CPU hardware.

Made by librarian-bots 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: Recommend Similar Papers is a Gradio app from the librarian-bots group that points you to papers related to a paper you give it. It names the dataset librarian-bots/paper-recommendations-v2 as its data. It runs on the cpu-upgrade hardware setting at Hugging Face and carries an MCP label.

Who it suits: Researchers and students who find a useful paper and want more reading along the same lines.

Industry | Who uses it | How they use it | Example
Research | Academics | Find related work for a literature search | Start from one paper and read its suggestions
Education | Students | Widen reading on a topic | Look up papers near a course reading
Software | Developers of research tools | Study a small recommender app | Read app.py
Library services | Librarians | Point readers to related papers | Share suggestions with a reader

People who need a full paper search engine with filters can skip it, since this app focuses on similar papers.

Where to use it:

• A browser, by visiting the Space on Hugging Face
• A computer of your own that runs Windows, macOS or Linux and has Python 3.13
• An MCP client, since the Space carries the MCP label, although the source gives no connection steps

Use case | Who | What they get back
Find similar papers | Researchers | A list of papers related to the one you give
Study the code | Developers | A short Gradio app in a single file

How to set it up:

• Python 3.13 and pip on Windows, macOS or Linux
• The Python packages in requirements.txt
• Gradio 6.30.0, the version the Space uses

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the new folder.
4. Install gradio at the version the Space uses, then the listed packages.
5. Start the app with Python.

pip install -U huggingface_hub
hf download librarian-bots/recommend_similar_papers --repo-type space --local-dir recommend_similar_papers
cd recommend_similar_papers
pip install gradio==6.30.0
pip install -r requirements.txt
python app.py

How to use it: Online, visit the Space on Hugging Face, identify a paper and read the recommendations that come back. On your own computer, run the start command and open the local page Gradio serves.

python app.py

Tool | What it does
app.py | Starts the Gradio interface
requirements.txt | Lists the pinned Python packages
requirements.in | Holds the top-level package list

Example: You enter a paper you liked and look at the list that returns. You then open the related papers that match your topic.

For newcomers and experts: If you are new, start with one paper you know well and read the suggestions that come back. That shows you how close the recommendations feel to your own reading.

If you know the field, the Space names the librarian-bots/paper-recommendations-v2 dataset and uses a pinned requirements.txt generated from requirements.in. It runs on Python 3.13 with Gradio 6.30.0. The source gives few details on how similarity is computed, so check the app for how it ranks results.

You give the app a paper
It looks up the recommendations dataset
It picks related papers
You read the suggestions

Good to know:

• Hardware: the Space is set to cpu-upgrade, so no GPU is named
• Detail: the source says little about how similarity is judged
• MCP: the Space carries the MCP label
• License: mit
• Cost to run: none named
• Data it reaches: the librarian-bots/paper-recommendations-v2 dataset on Hugging Face

On Hugging Face, 13 November 2026

• Likes: 201
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/librarian-bots/recommend_similar_papers
• Files: https://huggingface.co/spaces/librarian-bots/recommend_similar_papers/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.