How To Create A Deployment#

Introduction#

In this guide, you will learn how to create a new deployment for a trained model.

Deployments are used to unify the different components involved in making one or more trained models online and accessible to compute predictions on demand. For each deployment, there are four concepts to consider:

GUI#

Step 1: Create a deployment#

If you have at least one model already trained and saved in the Model Registry, navigate to the deployments page by clicking on the Deployments tab on the navigation menu on the left.

Once in the deployments page, you can create a new deployment by either clicking on New deployment (if there are no existing deployments) or on Create new deployment it the top-right corner. Both options will open the deployment creation form.

Step 2: Basic deployment configuration#

A simplified creation form will appear including the most common deployment fields from all available configurations. We provide default values for the rest of the fields, adjusted to the type of deployment you want to create.

In the simplified form, select the model framework used to train your model. Then, select the model you want to deploy from the list of available models under pick a model.

After selecting the model, the rest of fields are filled automatically. We pick the last model version and model artifact version available in the Model Registry. Moreover, we infer the deployment name from the model name.

If you prefer, change the name of the deployment, model version or artifact version. Then, click on Create new deployment to create the deployment for your model.

Step 3 (Optional): Advanced configuration#

Optionally, you can access and adjust other parameters of the deployment configuration by clicking on Advanced options.

You will be redirected to a full-page deployment creation form where you can see all the default configuration values we selected for your deployment and adjust them according to your use case. Apart from the aforementioned simplified configuration, in this form you can setup the following components:

Once you are done with the changes, click on Create new deployment at the bottom of the page to create the deployment for your model.

Step 4: Deployment creation#

Wait for the deployment creation process to finish.

Step 5: Deployment overview#

Once the deployment is created, you will be redirected to the list of all your existing deployments in the project. You can use the filters on the top of the page to easily locate your new deployment.

After that, click on the new deployment to access the overview page.

Code#

Step 1: Connect to Hopsworks#

import hopsworks

project = hopsworks.login()

# get Hopsworks Model Registry handle
mr = project.get_model_registry()

Step 2: Create deployment#

Retrieve the trained model you want to deploy.

my_model = mr.get_model("my_model", version=1)

Option A: Using the model object#

my_deployment = my_model.deploy()

Option B: Using the Model Serving handle#

# get Hopsworks Model Serving handle
ms = project.get_model_serving()

my_predictor = ms.create_predictor(my_model)
my_deployment = my_predictor.deploy()

# or
my_deployment = ms.create_deployment(my_predictor)
my_deployment.save()

API Reference#

Model Serving

Model Files#

Model files are the files exported when a specific version of a model is saved to the model registry (see Model Registry). These files are unique for each model version, but shared across model deployments created for the same version of the model.

Inside a model deployment, the local path to the model files is stored in the MODEL_FILES_PATH environment variable (see environment variables). Moreover, you can explore the model files under the /Models/<model-name>/<model-version>/Files directory using the File Browser.

Artifact Files#

Artifact files are files involved in the correct startup and running of the model deployment. The most important files are the predictor and transformer scripts. The former is used to load and run the model for making predictions. The latter is typically used to transform model inputs at inference time.

Every model deployment runs a specific version of the artifact files, commonly referred to as artifact version. One or more model deployments can use the same artifact version (i.e., same predictor and transformer scripts). Artifact versions are unique for the same model version.

When a new deployment is created, a new artifact version is generated in two cases:

• the artifact version in the predictor is set to CREATE (see Artifact Version)
• no model artifact with the same files has been created before.

Inside a model deployment, the local path to the artifact files is stored in the ARTIFACT_FILES_PATH environment variable (see environment variables). Moreover, you can explore the artifact files under the /Models/<model-name>/<model-version>/Artifacts/<artifact-version> directory using the File Browser.

Predictor#

Predictors are responsible for running the model server that loads the trained model, listens to inference requests and returns prediction results. To learn more about predictors, see the Predictor Guide

Transformer#

Transformers are used to apply transformations on the model inputs before sending them to the predictor for making predictions using the model. To learn more about transformers, see the Transformer Guide.