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…

The correct answer is B. Host the Computer Vision endpoint in a container on an on-premises server. One option to manage your Computer Vision containers on-premises is to use Kubernetes and Three primary parameters for all Cognitive Services containers are required. The Microsoft Software License Terms must be present with a value of accept. An Endpoint URI and API key are…

Submitted by yousef_jo· Mar 30, 2026

Question

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?

Options

ABuild an on-premises web app to query the Computer Vision endpoint.
BHost the Computer Vision endpoint in a container on an on-premises server.
CHost an exported Open Neural Network Exchange (ONNX) model on an on-premises server.
DBuild an Azure web app to query the Computer Vision endpoint.

How the community answered

(50 responses)

A
4% (2)
B
68% (34)
C
10% (5)
D
18% (9)

Explanation

One option to manage your Computer Vision containers on-premises is to use Kubernetes and Three primary parameters for all Cognitive Services containers are required. The Microsoft Software License Terms must be present with a value of accept. An Endpoint URI and API key are also needed. Not D: This Computer Vision endpoint would be available for the public, unless it is secured. https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/deploy-computer-visio

Topics

#Computer Vision API#OCR#Cognitive Services containers#On-premises AI deployment

Community Discussion

No community discussion yet for this question.

Full AI-102 Practice