Forked from https://github.com/h2oai/h2ogpt. The intention of this fork is to be a bit more prescriptive and "turn-key" for less technical users.
Ensure docker installed and ready (requires sudo), can skip if system is already capable of running nvidia containers. Example here is for Ubuntu, see NVIDIA Containers for more examples.
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
&& curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit-base
sudo apt install -y nvidia-container-runtime
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart dockerConfirm runs nvidia-smi from within docker without errors:
sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smiThis will allow you to scan the data outside of your docker image.
You essentially want to create symbolic links to the /data_sources folder
You can skip this if not running in WSL. I mount this so I can back it up off my Windows machine.
The run-time level changes can be made here. This script contains everything from this repository you need to launch the software.
This will allow launch the code. The first load will take a very long time if you have a lot of data to index.
You should be able to interact with your data at this point