Checkr is a minimalistic UI for grammar correction and text improvements with self-hosted LLMs.
You can run the application in a Docker container using the provided docker-compose.yml
file or run it natively.
Clone the repo.
git clone https://github.com/meiniKi/Checkr.git
Important
On the first text processing, the LLM model is automatically downloaded. This may take a long time, depending on your internet connection. Please be patient.
Create a virtual environment, activate it, and install the requirements.
cd <repo path>
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Start the application.
streamlit run app.py
You can now access the Web UI via 0.0.0.0:8501
, i.e., the <IP>:8501
if you are accessing remotely.
Make sure all necessary drivers and NVIDIA/CUDA tools are installed on your system. You may want to take a look at this and this pages. Then, restart the docker.
sudo apt install -y nvidia-cuda-toolkit
sudo apt install -y nvidia-open
sudo systemctl restart docker
You can build the containers and start them.
docker compose up --build -d
You should now be able to access the Web UI via IP and port.