Microsoft AI-102 Based on Real Exam Environment

You might want to manage the translation and localization for the language understanding content for your bot independently.

Translate command in the @microsoft/bf-lu library takes advantage of the Microsoft text translation API to automatically machine translate .lu files to one or more than 60+ languages supported by the Microsoft text translation cognitive service.

What is translated?

An .lu file and optionally translate Comments in the lu file

LU reference link texts

List of .lu files under a specific path.

To deploy the bot to Azure, you should run the following three Azure CLI commands in sequence:

az deployment group create This command will create the Azure resources for your bot using an ARM template and a parameters file. You need to specify the resource group name, the template file path, and the parameters file path. For example:

az deployment group create --resource-group myResourceGroup --template-file “deploymentTemplates\template-with-preexisting-rg.json” --parameters “deploymentTemplates\parameters-for-template-BotApp-with-rg.json”

This command will also output the app ID and password of your bot, which you will need for the next command1.

az webapp deployment source config-zip This command will deploy your bot code to the app service that you created in the previous step. You need to specify the resource group name, the app service name, and the zip file path of your bot code. For example:

az webapp deployment source config-zip --resource-group myResourceGroup --name myBotAppService --src “code.zip”

This command will also output the URL of your bot endpoint, which you will need for the next command2.

az ad app update This command will update your bot registration with the endpoint URL of your bot. You need to specify the app ID of your bot and the endpoint URL. For example:

az ad app update --id myBotAppId --set

This command will complete the deployment process and make your bot ready to be tested3.

Video Indexer supports multiple Person models per account. Once a model is created, you can use it by providing the model ID of a specific Person model when uploading/indexing or reindexing a video. Training a new face for a video updates the specific custom model that the video was associated with.

Note: Video Indexer supports face detection and celebrity recognition for video content. The celebrity recognition feature covers about one million faces based on commonly requested data source such as IMDB, Wikipedia, and top LinkedIn influencers. Faces that aren't recognized by the celebrity recognition feature are detected but left unnamed. Once you label a face with a name, the face and name get added to your account's Person model. Video Indexer will then recognize this face in your future videos and past videos.