Deploy

Installation

First install the docker and the nvidia-container-toolkit.

Then you can install the Pody server from pip:

pip install "pody[server]"

Start the server

The server stores the data in $PODY_HOME directory, which is by default ~/.pody.

To start the server:

pody-server --port 8799

Then by setting appropriate environment variables, you can use the pody-cli to interact with the server.

Managements

Users

To manage users:

pody-user ...

Please refer to --help for more information.

Configurations

The server configuration is stored in $PODY_HOME/config.toml file. There are comments in the file to help you understand the options.

This command opens the configuration file in your default editor:

pody-util config

For example, to manage images, you should first pull or build the image, then specify the images to expose to the client by editing the [[images]] section in the $PODY_HOME/config.toml file.

Start on boot

To start the server on boot, you can use the pody-util systemd-unit helper command to generate a systemd service content:

pody-util systemd-unit --port 8799

This will load the current environment variable settings, generate a systemd unit file for the Pody server using current user, and print the content to the standard output. Should put the output to global systemd unit directory, e.g.

pody-util systemd-unit | sudo tee /etc/systemd/system/pody.service

and enable it with:

sudo systemctl daemon-reload && \
sudo systemctl enable pody.service && \
sudo systemctl start pody.service