Skip to main content
Version: 1.52

Tutorials

In this section, you can find quick and easy video tutorials to get you started on using Deeploy.

Organize your Git repository for models & explainers​

In this step-by-step tutorial, you'll learn to prepare your Git repository so you can deploy AI models and explainers in Deeploy.

UI​

The UI tutorials guide you step by step on how to work with Deeploy through its interface.

Deploy your first model & explainer​

Learn how to get your first model and explainer up and running in Deeploy.

Explore organizations​

Explore the functionalities for admins of an organization in Deeploy: The model registry overview, logs, configuration of integrations, user management, and billing.

Explore Workspaces​

Explore the functionalities of a Workspace: Overview of deployments, repositories, use cases, compliance templates, credentials, Workspace member management, environment variables, and job schedules.

Manage your Deployments​

Explore the functionalities of a Deployment: Dashboard, monitoring, alerts, compliance documentation, details, version history, prediction history, events, container logs, code snippets, authentication and testing features.

Onboard your external models​

In this tutorial, we show you how to connect a model deployed on another platform, like an OpenAI GPT-4o model on Azure, to Deeploy as an external Deployment. You’ll learn how to bring your externally hosted models into Deeploy to use its governance and monitoring features with minimal setup.

Python client​

The Python client tutorials guide you step by step on how to work with Deeploy through the Deeploy Python client.

Deploy models & explainers with the Deeploy Python client​

In this tutorial, you’ll learn how to deploy a model and explainer from a prepared Git repository to Deeploy using the Deeploy Python Client.

Make predictions & explanations with the Deeploy Python client​

In this tutorial, you’ll learn how to use the Deeploy Python Client to generate predictions and explanations from your deployment in Deeploy.

We’ll walk you through:

  • Sending prediction requests to your deployed model
  • Retrieving model explanations for transparency
  • Using the client to streamline testing and validation

Submit actuals & evaluations with the Deeploy Python client​

In this tutorial, you’ll learn how to use the Deeploy Python client to submit actuals and evaluations to your deployment in Deeploy.

We’ll cover how to:

  • Send actual outcomes to your deployment
  • Log evaluations for performance tracking
  • Close the loop between model predictions and real-world results