AIrXiv
1.0.0
AIrXiv is a prototype for an LLM-powered ArXiv research assistant. It is an Electron app with a Flask backend powered by the OpenAI API. AIrXiv relies on a user-facing OpenAI API Key.
k = 3
by default) from a FAISS vector store. k
can be set in config.yml
, along with the chunk size and stride length of chunks (512 and 384 by default).static
, and backend elements are in util
and main.py
.Please open an Issue if you are having problems with installation.
cd
into the repo:git clone https://github.com/smsharma/AIrXiv.git
cd AIrXiv
conda env create -f environment.yml
conda activate airxiv
npm install
Run the Electron app with
npm run dev
which launches the Python/Flask backend (python main.py
or npm run start-flask
) as well as the frontend (npm start
). If this fails, try running the two commands separately. Add an arXiv ID or two, enter your OpenAI API Key in the text box towards the bottom, and start asking questions!
Usage notes:
gpt-3.5-turbo
or gpt-4
can be selected in the app settings. gpt-4
is significantly better in particular at implementing code, but is about an order of magnitude more expensive (~$0.02/1000 tokens) compared gpt-3.5-turbo
, and additionally API access is subject to a waitlist.AIrXiv is licensed under the MIT License.