Exam AI-102 topic 1 question 2 discussion

Select the version 1.1 before exporting the model

Select v1.1 Export Run and mount

Select V1.1 of app1 → It’s trained, and it’s the most recent usable version. Export the model by using the Export for container (GZIP) option → Only this format works for containers (not JSON). Run a container and mount the model file → You mount the .gz model file into the container at runtime.

Step 1) Select v1.1 of app1 is CORRECT. Since version 1.1 is the latest version that has been trained, you need to select this version as the starting point. Step 2) Export the model by using the Export for containers (GZIP) option is CORRECT. This step allows you to export the model in a format suitable for container deployment. Using the "Export for containers (GZIP)" option ensures that the model is correctly packaged for running in a container. Step 3) Run a container and mount the model file is CORRECT. Finally, you need to run the container and mount the exported model file. This step ensures that the container uses the correct model version during its operation.

Answer 1. Select v1.1 2. Export as GZIP 3. Run and mount 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 Azure 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.

1. Select v1.1 2. Export as GZIP 3. Run and mount

Select v1.0 of app1. Export the model by using the Export for containers (GZIP) option. Run a container and mount the model file.

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.

1. Export as GZIP 2. Select v1.1 3. Run and mount

Final Anser: 1. Select v1.1 2. Export as GZIP 3.. Run and mount

Select v1.1 Export Run and mount

you have to select first and then export and run: Select v1.1 of app1: This step is necessary to ensure you are working with the correct version of the application that you intend to deploy. Export the model by using the Export for containers (GZIP) option: This action is crucial because deploying an app to a container requires the model to be in a format that is optimized for container deployment, which is typically a GZIP file that includes all necessary components of the Language Understanding model. Run a container and mount the model file: Once you have the model exported in the correct format, you run a container instance and mount the exported model file to it. This allows the container to use the Language Understanding model version 1.1 for processing natural language inputs.

hi, hope it helps someone looking for the comments section. From the documentation, using a LUIS container it's possible to mount a gzip VERSIONED (just trained model) or PUBLISHED (trained and published) model. In the question it says "latest deployable version", so the app version to export as GZIP is v1.1. So just trained model is deployable, but also deployed model is deployable in a LUIS contrainer

The Language Understanding (LUIS) container loads your trained or published

I checked the link https://learn.microsoft.com/en-us/azure/ai-services/luis/luis-container-howto?tabs=v3 and it says you can no longer create new LUIS resources. Wonder why it still appeared in the exam per acsoma's comment.

https://learn.microsoft.com/en-us/azure/ai-services/luis/luis-how-to-manage-versions#other-actions

Select v1.1 is not published a version. It should be Select v1.0