Designing and Implementing a Microsoft Azure AI Solution
Question
The LUIS container loads your trained or published Language Understanding model.
It provides access to the query predictions from the container's API endpoints.
You plan to use them in your environment to comply with your organization's security and compliance requirements.
As a prerequisite, you have a docker engine installed and configured on your host computer.
It is also connected to Azure for billing purposes.
You also have an Azure Cognitive Services resource and trained or published LUIS app packaged as a mounted input to the container.
Review the steps given below and sequence them to get the container image and use it on your host computer: Step 1: Query the container's prediction endpoint Step 2: Use the LUIS portal to export the trained or published application package Step 3: Move package file into the required input directory on the host computer Step 4: Run the container, with the required input mount and billing settings Step 5: Get the docker image using docker pull Step 6: Import the endpoint logs for active learning Step 7: Log user queries to enable active learning.
Answers
Explanations
Click on the arrows to vote for the correct answer
A. B. C. D.Correct Answer: B
The correct sequence of steps is as given below:
To learn more about installing and running containers for LUIS, use the link given below:
The correct sequence of steps to get the LUIS container image and use it on the host computer is:
B. Step 5 -> Step 2 -> Step 3 -> Step 4 -> Step 1 -> Step 6 -> Step 7
Here is a detailed explanation of each step:
Step 5: Get the docker image using docker pull Before running the container, we need to download the LUIS container image using the docker pull command. This command pulls the latest LUIS container image from the Azure Container Registry to the local Docker environment.
Step 2: Use the LUIS portal to export the trained or published application package Export the LUIS app package from the LUIS portal. This app package contains the LUIS model, which is required to load into the LUIS container.
Step 3: Move package file into the required input directory on the host computer Copy the exported LUIS app package into the required input directory on the host computer. This directory will be mounted as input to the LUIS container when running.
Step 4: Run the container, with the required input mount and billing settings Run the LUIS container with the mounted input directory and billing settings using the docker run command. This will start the container and make it ready to serve the LUIS prediction API requests.
Step 1: Query the container's prediction endpoint Query the LUIS container's prediction endpoint with the prediction requests to get the predicted intent and entities.
Step 6: Import the endpoint logs for active learning After querying the prediction endpoint, import the endpoint logs to the LUIS portal. This will allow us to review the endpoint logs and use them to improve the LUIS model for better predictions.
Step 7: Log user queries to enable active learning Log user queries to the LUIS endpoint to enable active learning. This will help improve the LUIS model by providing real-time user feedback.
In summary, we need to pull the LUIS container image, export the LUIS app package, copy it into the required input directory, run the container, query the prediction endpoint, import the endpoint logs, and log user queries to enable active learning. The correct sequence of these steps is B. Step 5 -> Step 2 -> Step 3 -> Step 4 -> Step 1 -> Step 6 -> Step 7.
