GithubHelp home page GithubHelp logo

spinsphere / talk2arxiv Goto Github PK

View Code? Open in Web Editor NEW

This project forked from evanhu1/talk2arxiv

0.0 0.0 0.0 1.25 MB

Talk to any ArXiv paper using ChatGPT

Home Page: https://talk2arxiv.com

License: Apache License 2.0

JavaScript 1.24% TypeScript 94.23% CSS 4.53%

talk2arxiv's Introduction

Prepend any arxiv.org link with 'talk2' to load the paper into a responsive RAG chat application (e.g. www.arxiv.org/pdf/1706.03762.pdf -> www.talk2arxiv.org/pdf/1706.03762.pdf).

Talk2Arxiv is an open-source RAG (Retrieval-Augmented Generation) system specially built for academic paper PDFs. Powered by talk2arxiv-server

Screenshot

Installation

Just run yarn and then yarn run dev.

Features

  • PDF Parsing: Utilizes GROBID for efficient text extraction from PDFs.
  • Chunking Algorithm: Custom-built algorithm for optimal text chunking. Chunks by logical section (intro, abstract, authors, etc.) and also utilizes recursive subdivision chunking (chunk at 512 characters, then 256, then 128...)
  • Text Embedding: Uses Cohere's EmbedV3 model for accurate text embeddings.
  • Vector Database Integration: Uses Qdrant for storing and querying embeddings. This also functions to cache research papers so a paper only ever needs to be embedded once.
  • Contextual Relevance: Employs a reranking process to select the most relevant content based on user input.

Technologies Used

Frontend: Developed using Typescript, ReactJS, TailwindCSS, and NextJS. Backend: Powered by talk2arxiv-server, which uses Flask, Gunicorn, and Nginx.

Roadmap

  • Improved chunking strategy
  • Switch to extracting source LaTeX code to increase retrieval effectiveness for symbolic math formulas and non standard text elements
  • Use visual understanding LLM models as well
  • Account based personalization

Known Issues

  • The backend is not built to handle any level of scale, with lots of concurrent requests it will stall as it single threadedly handles them

talk2arxiv's People

Contributors

evanhu1 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.