Edit

Share via


Deploy a model and extract entities from text using the runtime API

Once you're satisfied with how your model performs, it's ready to be deployed and used to recognize entities in text. Deploying a model makes it available for use through the prediction API.

Prerequisites

For more information, see project development lifecycle.

Deploy model

After you review your model's performance and decided it can be used in your environment, you need to assign it to a deployment. Assigning the model to a deployment makes it available for use through the prediction API. We recommend that you create a deployment named production to which you assign the best model you built so far and use it in your system. You can create another deployment called staging to which you can assign the model you're currently working on to be able to test it. You can have a maximum of 10 deployments in your project.

For information on how to deploy your custom model in the Azure AI Foundry, see Deploy your fine-tuned model .

Swap deployments

After you're done testing a model assigned to one deployment and you want to assign this model to another deployment, you can swap these two deployments. Swapping deployments involves taking the model assigned to the first deployment, and assigning it to the second deployment. Then taking the model assigned to second deployment, and assigning it to the first deployment. You can use this process to swap your production and staging deployments when you want to take the model assigned to staging and assign it to production.

To replace a deployed model, you can exchange the deployed model with a different model in the same region:

  1. Select the model name under Name then select Deploy model.

  2. Select Swap model.

    The redeployment takes several minutes to complete. In the meantime, deployed model continues to be available for use with the Translator API until this process is complete.

Delete deployment

If you no longer need your project, you can delete it from the Azure AI Foundry.

  1. Navigate to the Azure AI Foundry home page. Initiate the authentication process by signing in, unless you already completed this step and your session is active.
  2. Select the project that you want to delete from the Keep building with Azure AI Foundry
  3. Select Management center.
  4. Select Delete project.

To delete the hub along with all its projects:

  1. Navigate to the Overview tab inn the Hub section.

  2. On the right, select Delete hub.

  3. The link opens the Azure portal for you to delete the hub.

Assign deployment resources

You can deploy your project to multiple regions by assigning different Language resources that exist in different regions.

For more information on how to deploy you custom model, see Deploy your fine-tuned model

Unassign deployment resources

To unassign or remove a deployment resource from a project, you also delete all the deployments for to that resource region.

If you no longer need your project, you can delete it from the Azure AI Foundry.

  1. Navigate to the Azure AI Foundry home page. Initiate the authentication process by signing in, unless you already completed this step and your session is active.
  2. Select the project that you want to delete from the Keep building with Azure AI Foundry
  3. Select Management center.
  4. Select Delete project.

To delete the hub along with all its projects:

  1. Navigate to the Overview tab inn the Hub section.

  2. On the right, select Delete hub.

  3. The link opens the Azure portal for you to delete the hub.

Next steps

After you have a deployment, you can use it to extract entities from text.