# Setting Up an AI 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:

{% stepper %}
{% step %}
**Install PySDK**

Any device with PySDK installed can run an AI server. Refer to [PySDK Installation](https://docs.degirum.com/pysdk/installation) for details on how to install PySDK.
{% endstep %}

{% step %}
**Create a directory for the local model zoo**

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

{% code overflow="wrap" %}

```bash
mkdir ~/degirum-model-zoo
```

{% endcode %}
{% endstep %}

{% step %}
**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 ](https://docs.degirum.com/pysdk/command-line-interface#download-model-zoo)for downloading models from the DeGirum AI Hub.

{% code overflow="wrap" %}

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

{% endcode %}
{% endstep %}

{% step %}
**Start the AI server**

Launch the server with the following command:

{% code overflow="wrap" %}

```bash
cd ~/degirum-model-zoo
degirum server
```

{% endcode %}

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:

{% code overflow="wrap" %}

```bash
degirum server --port <your_port>
```

{% endcode %}
{% endstep %}
{% endstepper %}

### Linux Service

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

{% stepper %}
{% step %}
**Complete the terminal setup steps**

Follow all steps in [Starting AI Server from Terminal](#terminal) except for launching the server.
{% endstep %}

{% step %}
**Create a systemd service configuration file**

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

{% code overflow="wrap" %}

```ini
[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
```

{% endcode %}
{% endstep %}

{% step %}
**Start the service**

Start the service using `systemctl`:

{% code overflow="wrap" %}

```bash
sudo systemctl start degirum.service
```

{% endcode %}
{% endstep %}

{% step %}
**Check the service status**

Check the service status using `systemctl`:

{% code overflow="wrap" %}

```bash
sudo systemctl status degirum.service
```

{% endcode %}
{% endstep %}

{% step %}
**Enable the service on startup**

Use `systemctl` to automatically enable the degirum service on startup:

{% code overflow="wrap" %}

```bash
sudo systemctl enable degirum.service
```

{% endcode %}
{% endstep %}
{% endstepper %}

### Docker Container

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

{% stepper %}
{% step %}
**Ensure Docker is installed**

Refer to the [official Docker documentation](https://docs.docker.com/engine/install/) for installation instructions
{% endstep %}

{% step %}
**Prepare the local model zoo**

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

{% code overflow="wrap" %}

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

{% endcode %}
{% endstep %}

{% step %}
**Run the Docker container**

When hosting models locally:

{% code overflow="wrap" %}

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

{% endcode %}

When serving models only from AI Hub:

{% code overflow="wrap" %}

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

{% endcode %}
{% endstep %}
{% endstepper %}

## 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`