Skip to content

bartoszkozakiewicz/LatexAI

Repository files navigation

LatexAI

ABOUT

LatexAI is powered by Google's PaLM and is focusing on helping the writing process of technical and scientific articles. During ideation we have identified 3 core functionalities that could help our users boost both effectiveness and efficiency of their work. Those functionalities are:

  1. Live autocompletion working both for natural language (text) and LaTeX syntax.
  2. Suggestions for citations and assistance in creating a bibliography. (With a usage of arxiv search)
  3. Conducting a comprehensive review of the paper. We believe that by providing and improving those 3 functionalities we can provide a lot of value to our users.

Further planned features are:

  1. Interactive chat which will return latex syntax asked by user, for example: Table with space for user to fill with text.
  2. Spelling, grammar, and punctuation checking and correction for the text. Potentially with a usage of Grammarly API.
  3. ...

INTERFACE

Overall look

image



1. Autocomplete function

Image



2. Bibliography function



3. Review function (Example with properly written article)

Image



INSTALLATION PROCESS

1. Installing dependencies for server:

Install dependencies from requirements.txt

pip install -r requirements.txt

For configuring server, please follow instructions here: https://cloud.google.com/docs/authentication/provide-credentials-adc

2. Installing dependencies for client:

Install NodeJs: https://nodejs.org/en/download/package-manager

Run below:

npm i react-scripts

RUNNING APP

1. Start server:

From root of the GH project run command:

uvicorn app.main:app

2. Start client:

From root/client run command:

npm start