https://github.com/adam-mazur/gradientdigest

A Flask app for scraping the arXiv website and recommending new AI & ML research papers.
https://github.com/adam-mazur/gradientdigest

ai arxiv arxiv-api arxiv-papers flask flask-sqlalchemy machine-learning ml-papers

Last synced: 3 months ago
JSON representation

A Flask app for scraping the arXiv website and recommending new AI & ML research papers.

• Host: GitHub
• URL: https://github.com/adam-mazur/gradientdigest
• Owner: Adam-Mazur
• License: mit
• Created: 2023-08-31T17:19:53.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-02T14:47:10.000Z (about 1 year ago)
• Last Synced: 2025-01-15T12:13:06.562Z (5 months ago)
• Topics: ai, arxiv, arxiv-api, arxiv-papers, flask, flask-sqlalchemy, machine-learning, ml-papers
• Language: Python
• Homepage:
• Size: 761 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Overview

This is a simple vector space recommender system based on tf-idf that retrieves the most recent AI/machine learning papers from the arXiv website and sorts them by their similarity to the papers that you've liked. Project inspired by [Andrej Karpathy's](https://github.com/karpathy) [arxiv-sanity-lite](https://arxiv-sanity-lite.com/) and this [paper](https://users.ics.forth.gr/~potamias/mlnia/paper_6.pdf).

# Architecture

The profile vectors are computed from the PDFs of the papers rather than just their abstracts. The background scheduler sends requests to the arXiv API every 24 hours, bacause the review process operates in daily cycles. Users' profile vectors are updated with a fixed constant when a new paper is liked. The website is powered by Flask, and uses [scikit-learn](https://scikit-learn.org/stable/) for td-idf computations.   

# Upcoming updates

- Email newsletter

- Summarizing papers with generative AI

- Finding similar articles

- Reading lists

# Photos

### Home Page

![Home page](screen_shots/Screenshot_home_page.png)

### Search Page

![Search page](screen_shots/Screenshot_search.png)

### Login Page

![Login page](screen_shots/Screenshot_login.png)

### Sign Up Page

![Sign up page](screen_shots/Screenshot_sign_up.png)

### Interests Page

![Interests page](screen_shots/Screenshot_interests.png)