Deploying an AI model
Navigator's Canvas is a great tool to test out your AI Flows and quickly iterate on them. Running a flow is coupled to the Navigator application though, which means that the moment you close Navigator or shut down your machine, any flow that might still be running will be stopped.
In an actual production setup you will probably want to decouple running a flow from Navigator. This can be achieved via "Deployments", a feature that allows you to assign flows to a set of computers and input devices.
Where do my Deployments run?
Navigator is the interactive UI that allows you to create and manage your AI Flows, as well as deploy them to a given Hardware-setup. The execution of these Flows is handled by the webAI Runtime Agent. Within your local network, one of these Agents takes the role of the Controller. For as long as this Controller is running, the Flows are being executed.
Currently, your Navigator installation will start Runtime for you in the background and default to Controller, which in turn means that Deployments are coupled to the lifetime of Navigator. We will soon give you the tools to set this up specifically to your needs.
How to create a Deployment?
Designing your Flow
In order to create a Deployment, you start by designing your AI Flow on Canvas. Canvas will automatically provision and assign your computer and your local camera to any Element you pull onto Canvas, to provide a local test environment.
Saving a Version of your Flow
Once you are happy with your Flow and it is ready to be deployed, you need to save a Version of it. A Flow Version is a snapshot of the Flow in its current configuration that you can refer to later on when creating Deployments.
-
Click on the context menu of your project on the left (three dots) and then select "Save Version for Deployment".
-
You can review all Versions you saved when clicking on the context menu of the project and then selecting "Show Flow Versions".
-
You can also rename and delete previously saved Versions in the Versions Panel.
Setting up your Devices
As mentioned above, Navigator will auto-assign your computer and your camera to all Elements pulled onto it. For a Deployment, you will likely want to use different Devices to deploy your AI Flow to. In order to make the Devices available for Deployments, as well as for Canvas, you need to provision them on the Devices page.
Navigator differentiates between two kinds of Devices, Input Devices and Computers. Input Devices are currently limited to Cameras, but will soon be extended with additional options. Computers are computing devices that run the webAI Runtime Agent to power your AI Flows.
To provision your Devices, click on the Button with the same name in Navigator. Provisioned Devices are available to all Projects you are working on.
Creating a Deployment
Deployments are associated with the currently selected Project. This means, all Deployments you create will be organized within that Project and have access to the Flow Versions of that Project only. You can access the Deployments screen by clicking on the drop-down menu next to the run button. This allows you to toggle between Canvas and Deployments.
-
To create a new Deployment, click on the Create button.
-
In the process you can give a name and a description, and you will have to select a Version that you would like to deploy.
-
Based on this Version, you need to assign a set of provisioned Devices to the Elements that are part of the Flow. Input types like "Camera" require a provisioned Input Device, Elements like "Person Detector" require a provisioned Computer to run on.
-
Once you have assigned all Elements to their corresponding provisioned Devices, you can "Build" the Deployment.
All currently running Deployments are listed in the table along with their current status. It is possible to rename, delete, stop, and restart them. You can also perform these actions in bulk by selecting multiple Deployments.