Exam AI-100 topic 5 question 27 discussion

Actual exam question from Microsoft's AI-100

Question #: 27
Topic #: 5

You are developing a bot for an ecommerce application. The bot will support five languages.
The bot will use Language Understanding (LUIS) to detect the language of the customer, and QnA Maker to answer common customer questions. LUIS supports all the languages.
You need to determine the minimum number of Azure resources that you must create for the bot.
You create one instance of QnA Maker and five instances Language Understanding (LUIS).
Does this action accomplish your objective?

A. Yes, it does
B. No, it does not

Show Suggested Answer

Suggested Answer: B 🗳️
You need to have a new QnA Maker resource for each language.
If LUIS supports all the languages, you develop a LUIS app for each language. Each LUIS app has a unique app ID, and endpoint log. If you need to provide language understanding for a language LUIS does not support, you can use Microsoft Translator API to translate the utterance into a supported language, submit the utterance to the LUIS endpoint, and receive the resulting scores.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/language-support https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-language-support

by rveney at June 22, 2023, 9:39 p.m.

Comments

Submit Cancel

rveney

2 years ago

B. No, it does not. While creating one instance of QnA Maker can handle the common customer questions across different languages, creating separate instances of Language Understanding (LUIS) for each language is not necessary. LUIS supports multiple languages within a single instance. Therefore, you can create a single instance of LUIS that supports all five languages, rather than creating five separate instances. This would help minimize the number of Azure resources required for the bot.

upvoted 1 times

...