PapersChat is an agentic AI application that allows you to chat with your papers and gather also information from papers on ArXiv and on PubMed. It is powered by LlamaIndex, Qdrant and Mistral AI.
The installation of the application is a unique process, you simply have to clone the GitHub repository:
git clone https://github.com/AstraBert/PapersChat.git
cd PapersChat/To launch the app, you can follow two paths:
1. Docker (recommended)
Required: Docker and docker compose
- Add the
mistral_api_key,phoenix_api_keyandllamacloud_api_keyvariables in the.env.examplefile and modify the name of the file to.env. Get these keys:
# modify your access token, e.g. hf_token="hf_abcdefg1234567"
mv .env.example .env- Launch the docker application:
# If you are on Linux/macOS
bash start_services.sh
# If you are on Windows
.\start_services.ps1You will see the application running on http://localhost:7860 and you will be able to use it. Depending on your connection and on your hardware, the set up might take some time (up to 30 mins to set up) - but this is only for the first time your run it!
2. Source code
Required: Docker, docker compose and conda
- Add the
mistral_api_key,phoenix_api_keyandllamacloud_api_keyvariables in the.env.examplefile and modify the name of the file to.env. Get these keys:
mv .env.example .env
# modify the variables, e.g.:
# llamacloud_api_key="llx-000-abc"
# mistral_api_key="01234abc"
# phoenix_api_key="56789def"- Set up PapersChat using the dedicated script:
# For MacOs/Linux users
bash local_setup.sh
# For Windows users
.\local_setup.ps1- Or you can do it manually, if you prefer:
docker compose up db -d
conda env create -f environment.yml
conda activate papers-chat
python3 scripts/app.py
conda deactivateContributions are always welcome! Follow the contributions guidelines reported here.
The software is provided under MIT license.