"Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance." same document also lists Azure Key Vault as a requirement:
https://docs.microsoft.com/en-us/azure/search/search-security-overview#data-protection

Reference:
https://docs.microsoft.com/en-us/rest/api/deviceupdate/resourcemanager/accounts/create
https://www.analyticsvidhya.com/blog/2020/12/microsoft-azure-cognitive-services-api-for-ai-development/

Step 1: Export the model using the Export for containers (GZIP) option.
Export versioned app's package from LUIS portal
The versioned app's package is available from the Versions list page.
* Sign on to the LUIS portal.
* Select the app in the list.
* Select Manage in the app's navigation bar.
* Select Versions in the left navigation bar.
* Select the checkbox to the left of the version name in the list.
* Select the Export item from the contextual toolbar above the list.
* Select Export for container (GZIP).
* The package is downloaded from the browser.

Step 2: Select v1.1 of app1.
A trained or published app packaged as a mounted input to the container with its associated App ID.
Step 3: Run a contain and mount the model file.
Run the container, with the required input mount and billing settings.
nce:
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-container-howto

The model need to be extended and retrained.
Note: Smart Labeler to generate suggested tags for images. This lets you label a large number of images more quickly when training a Custom Vision model.