Azure

Setting up a Model in Azure AI Studio

Azure AI Studio lets you build, configure, tune and deploy the model within their environments.

Deployment Configuration

An Azure model is managed in the Azure AI studio and therefore won't be controlled within the Orq.ai panel. You can decide on which strategy to use for your model within the Azure AI Studio while building your model.

For instance, the region where your model will be available at is configured when creating your model.

To learn more about the model possibilities, please refer to the provider documentations, see the Azure Deployment Documentation .

Content Filtering

With your model running on Azure Cloud, the model configuration won't be available within Orq.ai's panel. However its configuration will influence the behaviour of your Deployment when called through Orq.ai.

Azure offers powerful customization for content filtering, letting you configure its parameters for Violent, Hate, Sexual, and Self-Harm content.

To learn more about Content filtering, see the Azure AI Studio Documentation

Onboarding Model to Orq.ai

Once your model is deployed and configured on Azure, you can import the model within the Orq.ai panel.

📘

If you have multiple models to import, note that you have to import each of them separately.

Getting the Deployment URL and Key from Azure AI Studio

To get started with getting the deployment URL, head to your Model Deployment and select Open in Playground.

Once in Playground, select the View Code button.

A modal will appear containing both the Deployment Endpoint and API Key used for importing your model in Orq.ai.

See also the following interactive walkthrough to get your deployment details:

Onboarding the model in your Model Garden

Head to the Model Garden in your panel and choose the Add Model button at the top-right of the screen.

Select the Azure option, this will open the following modal:

Once added, the model will be visible in the Model Garden. Once the model is Enabled it will be available in Playgrounds, Experiments and Deployments to be used.