Deploy

Ai-APIᵀᴹ Engine: Deploy

Deploying Models Guide

Before starting to read this guide, it is recommended for you to read the Build Models Guide of the Ai-APIᵀᴹ Concept.

After building a newly trained model, comes the deploying stage.

Now this is the part where our Ai-APIᵀᴹ Engine comes into play. The sidebar at the left side of your screen has a menu button of Ai-APIᵀᴹ which will lead you to our Ai-APIᵀᴹ Engine.

Figure 1: Ai - Apiᵀᴹ Engine

Note:

The Ai-APIᵀᴹ Engine, on clicking, shows all the previous deployments you have done, or your organization has done (if you are an Organization Admin) after selecting a specific namespace of the deployments.

For deploying process, the steps are as following:

• Click on Create Ai-APIᵀᴹ and then select the model. Here we are selecting the model which we just created in the previous Guide.

Figure 2: Create Ai-Apiᵀᴹ

Figure 3: Select Trained Model

• Then comes the selection of namespace (only if you are a member of one).

Figure 4: Namespace Selection

• Third step is to select the location where you want to deploy it.

Figure 5: Select DataCenter

• If you selected an Edge Datacenter in the previous step, you have an additional step where you are given an option to choose whether you want your deployment to be created on the HUB or any SATELLITE Node.

Select HUB or SATELLITE NODE

• Name your Deployment and click on Create.

Figure 6: Name of Deployment

You will be redirected to our Ai-APIᵀᴹ Engine while the deployment is being done in the background. On successful deployment, the status of the deployment will change to DEPLOYED.

Note: On successful deployment, when the status is deployed, you are now given an option to monitor various performance metrics as highlighted in the images below.

Figure 7: Deployment Successful

Performance Monitoring