# Deploying the package

> This page describes how to deploy an out-of-the-box Computer Vision ML package.

This page describes how to deploy an out-of-the-box Computer Vision ML package.

## Creating the ML package

To create a Computer Vision ML package, select the **AI Center** service from the left navigation bar, create a new project or access an existing one, and then select **ML Packages**.

### For offline installation

1. Select **Upload zip file**.
2. Under **Package name**, enter a package name.
3. Under **Upload package**, upload the Computer Vision ML package as a `.zip` file.

To do so, you need to download the `cv-ondemand.tar.gz` bundle. For further details, go [here](https://docs.uipath.com/automation-suite/automation-suite/2023.10/installation-guide/installation-packages-download-links#cv-ondemandtargz).
4. Under **Input type**, select **Json** from the drop-down menu.
5. Under **Language**, select the corresponding Python language from the drop-down menu.
6. Enable the **Recommend GPU** toggle button.
7. Select **Create**.

### For online installation

1. Select **Out of the box Packages**.
2. Select **UiPath Computer Vision**.
3. Select **ComputerVision**.
4. Under **Choose Package Version**, select a package version from the drop-down menu.
5. Select **Submit**.

## Creating the ML skill

In the same project that you created the ML package, you need to:

1. Go to **ML Skills**.
2. Select **Create new**.
3. Under **Name**, enter a name for the ML skill.
4. Under **Choose Package**, select the ML package you just created from the drop-down menu.
5. Under **Choose package major version**, select a major version from the drop-down menu.
6. Under **Choose package minor version**, select a minor version from the drop-down menu.
7. Enable the **Enable GPU** toggle button.
8. Enable the **Make ML Skill Public** toggle button.
9. Select **Create**.
10. Once the ML skill is available, this can take up to 30 minutes, select the ML skill and copy the **Url**.

## Changing the endpoints on activity level

On activity level in your UiPath Studio project, you need to change:

* the **URL** property value of the CV Screen Scope activity, and
* the **Endpoint** property value of the UiPath Screen OCR activity

to the URL of the ML skill.

## Changing the endpoints on project level

The default URLs can also be changed from the [Project Settings](https://docs.uipath.com/studio/standalone/2023.10/user-guide/about-automation-projects#adjusting-project-settings) page.

### Changing the endpoint for CV Screen Scope

To change the endpoint for CV Screen Scope, go to **UiPath Studio** > your project > **Project Settings** > **Computer Vision** > **CV Screen Scope** > **Server** > **Run value/Debug value** > change `https://cv.uipath.com` to the URL of the ML skill.

  ![docs image](https://dev-assets.cms.uipath.com/assets/images/ai-computer-vision/ai-computer-vision-docs-image-375713-cc184c50-4bb89706.webp)

When **Local Server** is set to **True**, the ML skill is over-written.

### Changing the endpoint for UiPath Screen OCR

To change the endpoint for UiPath Screen OCR, go to **UiPath Studio** > your project > **Project Settings** > **OCR** > **UiPath Screen OCR** > **Endpoint** > **Run value/Debug value** > change `https://ocr.uipath.com` to the URL of the ML skill.

  ![docs image](https://dev-assets.cms.uipath.com/assets/images/ai-computer-vision/ai-computer-vision-docs-image-375717-e23a74e4-f21f5d0c.webp)