Exam AI-102 topic 1 question 59 discussion

1. Provision the Language service resource in Azure. This step involves creating the Azure Language service resource, which will provide you with the necessary credentials and endpoint URL to use the Sentiment Analysis API. 2. Deploy a Docker container to an on-premises server. By deploying a Docker container on-premises, you can run the Sentiment Analysis API locally, ensuring that the feedback data does not leave your internal network. 3. Run the container and query the prediction endpoint. Once the container is running on your on-premises server, you can start sending feedback data to the Sentiment Analysis API by querying the prediction endpoint provided by the Language service.

Provision the Language service resource in Azure. Deploy a Docker container to an on-premises server. Identify the Language service endpoint URL and query the prediction endpoint.

https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers Prerequisites You must meet the following prerequisites before using Sentiment Analysis containers. If you don't have an Azure subscription, create a free account before you begin. Docker installed on a host computer. Docker must be configured to allow the containers to connect with and send billing data to Azure. On Windows, Docker must also be configured to support Linux containers. You should have a basic understanding of Docker concepts. A Language resource with the free (F0) or standard (S) pricing tier. 1) Provision the language service resource in Azure

1) Provision the language service in Azure 2) Deploy a docker container to container instance - this is because you can inject a container instance into a VNET (remember there is no requirement for anything to be on-prem, it just says internal which could be a internal VNET) 3) Run the container and query the prediction endpoint

This was in the exam on 15/08/2024

Provision the Language service resource in Azure Deploy a Docker container to an on-premises server Run the container and query the prediction endpoint

Deploy on-premises Provision Run

Provision the Language service resource in Azure: This is the first step where you set up the Language service resource in Azure. This service will provide you with the Sentiment Analysis API. Deploy a Docker container to an on-premises server: After provisioning the Language service, you should deploy a Docker container on an on-premises server. This container will host the Azure AI Language service and ensure that the managed feedback remains on your company’s internal network. Identify the Language service endpoint URL and query the prediction endpoint: Once the Docker container is running on your on-premises server, you can identify the Language service endpoint URL. You can then query the prediction endpoint to analyze the sentiment of the comments.

Remember that the order matters: provision the language service first, then Identify the Language Service Endpoint URL and Query the Prediction Endpoint and finally deploy the container based on your chosen deployment target which is on-premises 🚀

That is correct, see prerequisites where you need to have 1) Docker installed and 2) provisioned a Language resource: https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/use-containers