---
title: Deploy external models
description: How to deploy external models by registering and deploying a model package or by uploading training data for the external model directly.

---

# Deploy external models {: #deploy-external-models }

To monitor models making predictions on external infrastructure, you can deploy external (remote) models using either of the following methods:

* [Deploy an external model package](#deploy-an-external-model-package).
* [Deploy an external model by uploading historical training data](#deploy-an-external-model-by-uploading-training-data).

After you deploy, you can use the [monitoring agent](mlops-agent/index) to monitor the external deployment.

## Deploy a registered external model {: #deploy-a-registered-external-model }

This section outlines how to deploy a registered external (remote) model. Before proceeding, make sure you have [registered your external model package](reg-external-models) in the **Model Registry**.

!!! important
    To send predictions, first configure the [monitoring agent](mlops-agent/index). Reference the agent's internal documentation for configuration information.

You can deploy a registered external model at any time from the **Registered Models** page. To do that, you must open a registered model version:

1. On the **Registered Models** page, click the [registered external model](reg-external-models) containing the model version you want to deploy.

2. To open the registered model version, do either of the following:

    ![](images/reg-select-deploy-ext-model.png)

    * To open the version in the current tab, click the row for the version you want to access.
    
    * To open the version in a new tab, click the open icon (![](images/icon-open.png)) next to the **Type** column for the version you want to access.

3. In the version header, click **Deploy**, and then [configure the deployment settings](add-deploy-info).

    ![](images/reg-deploy-ext-model.png)

4. Click **Deploy model**.

## Deploy an external model by uploading training data {: #deploy-an-external-model-by-uploading-training-data }

This section explains how to upload the training data for a model that made predictions in the past. Uploading the historical predictions directly to the deployment inventory enables you to analyze data drift and accuracy statistics in the past. Instrument the external deployment with the [monitoring agent](mlops-agent/index) to monitor future predictions and [add additional historical prediction data](add-prediction-data-post-deploy) after deployment.

To create a deployment with training data:

1. Navigate to **Deployments** and click the **+ Add deployment** link.

    ![](images/add-deploy-1.png)

2. Under the **Add a training dataset** header, select **browse** and select **Local File** to upload your XLSX, CSV, or TXT formatted training data. You can also select training data from the **AI Catalog**.

    ![](images/add-deploy-2.png)

3. After selecting your training dataset, provide information about the model that used the training data. Once completed, select **Continue to deployment details** to further configure the deployment.

    ![](images/add-deploy-13.png)

4. Add [deployment information and complete the deployment](add-deploy-info).

## Configure an external deployment {: #configure-an-external-deployment }

After you create an external deployment, there are two options for additional configuration. You can:

* [Upload historical prediction data](add-prediction-data-post-deploy) to the deployment to analyze data drift and accuracy in the past.

* [Configure the deployment with the monitoring agent](mlops-agent/index) using the monitoring code snippet from the [**Predictions > Monitoring** tab](code-py#monitoring-snippet) to monitor future predictions.

## Configure prediction data for time series scoring {: #configure-prediction-data-for-time-series-scoring }

For time series predictions, if you add prediction data for scoring in the **Predictions** tab, you must include the following required features in the prediction dataset:

| Feature                | Description                                              |
|------------------------|----------------------------------------------------------|
| `Forecast Distance`    | Supplied by DataRobot when you download the .mlpkg file. |
| `dr_forecast_point`    | Supplied by DataRobot when you download the .mlpkg file. |
| `Datetime_column_name` | Defines the date/time feature to use for time-stamping prediction rows. |
| `Series_column_name`   | Defines the feature (series ID) used for multiseries deployments (if applicable). |
