You need to build a solution that will use optical character recognition (OCR) to scan sensitive documents by using the Computer Vision API. The solution must NOT be deployed to the public cloud. What should you do?
A.
Build an on-premises web app to query the Computer Vision endpoint.
B.
Host the Computer Vision endpoint in a container on an on-premises server.
C.
Host an exported Open Neural Network Exchange (ONNX) model on an on-premises server.
D.
Build an Azure web app to query the Computer Vision endpoint.
Host the Computer Vision endpoint in a container on an on-premises server is correct because this approach allows you to run the Computer Vision API locally without needing to deploy your solution to the public cloud. This setup ensures that sensitive documents are processed within your local environment, meeting the requirement to avoid the public cloud.
Answer is B
B is the answer.
https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/deploy-computer-vision-on-premises
One option to manage your Computer Vision containers on-premises is to use Kubernetes and Helm. Using Kubernetes and Helm to define a Computer Vision container image, we'll create a Kubernetes package. This package will be deployed to a Kubernetes cluster on-premises.
B. Host the Computer Vision endpoint in a container on an on-premises server.
Since the solution should not be deployed to the public cloud, option B is the correct answer. By hosting the Computer Vision endpoint in a container on an on-premises server, the solution can still leverage the capabilities of the Computer Vision API while keeping the processing and data within the on-premises environment. Option A and D both involve using a web app, which would likely require hosting in the public cloud. Option C involves hosting an exported ONNX model, which may not have the same capabilities as the Computer Vision API.
A voting comment increases the vote count for the chosen answer by one.
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one.
So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
syupwsh
3 weeks, 1 day agoHaraTadahisa
8 months, 2 weeks agotaiwan_is_not_china
9 months, 1 week agotakaimomoGcup
9 months, 2 weeks agoevangelist
1 year agordemontis
1 year, 4 months agozellck
1 year, 8 months agoRAN_L
1 year, 11 months agoHotDurian
2 years, 2 months ago