docker running:
- Check if your GPU is ready to use by running:
docker run --rm -it --gpus=all nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -gpu -benchmark
If the GPU is not available, update the Docker Compose YAML file accordingly. Otherwise, continue. - docker-compose up
Local running:
- docker-compose up --build chromadb
- python -m venv venv
- source venv/Scripts/activate
- cd flask-backend
- pip install -r requirements.txt
- flask run
- cd ../react-frontend
- npm install
- npm start
Change Model:
- Change Model in docker-compose.yaml file
- Add "ollama pull [modelname]" in the entrypoint.sh to download the desired model in ollama