Setting Up an AI Server

Read this page if you'll host an AI server or perform inference with a local server.

Starting an AI Server

Use PySDK to configure and launch an AI server. The server runs on your host and processes inference requests from remote clients.

You can start the AI server in several ways:

• running AI server from a terminal directly on the host OS.

• running AI server as a Linux system service.

• running AI server with a Docker container.

Terminal

To run the PySDK AI server from a terminal, perform the following steps:

1

Install PySDK

Any device with PySDK installed can run an AI server. Refer to PySDK Installation for details on how to install PySDK.

2

Create a directory for the local model zoo

You'll need to create a directory to hold your models.

mkdir ~/degirum-model-zoo

3

Download or copy models to the local model zoo

After creating the model zoo directory, you'll need to populate it with models

To easily populate the model zoo, you can use the PySDK CLI tool for downloading models from the DeGirum AI Hub.

cd ~/degirum-model-zoo
degirum download-zoo

4

Start the AI server

Launch the server with the following command:

cd ~/degirum-model-zoo
degirum server

The server runs until you press ENTER in the terminal. By default, it listens on TCP port 8778. To specify a different port, use the --port argument:

degirum server --port <your_port>

Linux Service

To automatically start the server on boot, configure it as a Linux service:

1

Complete the terminal setup steps

Follow all steps in Starting AI Server from Terminal except for launching the server.

2

Create a systemd service configuration file

Create a file named degirum.service in the /etc/systemd/system directory. Use the following template:

[Unit]
Description=DeGirum AI Service

[Service]
WorkingDirectory=/home/<your_username>/
ExecStart=<path_to_python> -m degirum.server --zoo /home/<your_username>/zoo
Restart=always
RestartSec=10
SyslogIdentifier=degirum-ai-server
User=<your_username>

[Install]
WantedBy=multi-user.target

3

Start the service

Start the service using systemctl:

sudo systemctl start degirum.service

4

Check the service status

Check the service status using systemctl:

sudo systemctl status degirum.service

5

Enable the service on startup

Use systemctl to automatically enable the degirum service on startup:

sudo systemctl enable degirum.service

Docker Container

To run the AI server as a Docker container, follow these steps:

1

Ensure Docker is installed

Refer to the official Docker documentation for installation instructions

2

Prepare the local model zoo

If hosting models locally, create and populate a model zoo directory:

mkdir -p ~/degirum-model-zoo
cd ~/degirum-model-zoo
degirum download-zoo

3

Run the Docker container

When hosting models locally:

docker run --name aiserver -d -p 8778:8778 -v ~/degirum-model-zoo:/zoo --privileged degirum/aiserver:latest

When serving models only from AI Hub:

docker run --name aiserver -d -p 8778:8778 --privileged degirum/aiserver:latest

Rescanning Model Zoos

If you started your AI server in a terminal or as a Linux service, you can tell the AI server to rescan the local model zoo directory by executing the following command on the same host: degirum server rescan-zoo

If you started your AI server in the Docker container, then you should rescan the model zoo directory by restarting the container: docker restart aiserver