Explanation:

Step 1: For the knowledge base, select Show active learning suggestions.
In order to see the suggested questions, on the Edit knowledge base page, select View Options, then select Show active learning suggestions.
Step 2: Approve and reject suggestions.
Each QnA pair suggests the new question alternatives with a check mark, #, to accept the question or an x to reject the suggestions. Select the check mark to add the question.
Step 3: Save and train the knowledge base.
Select Save and Train to save the changes to the knowledge base.
Step 4: Publish the knowledge base.
Select Publish to allow the changes to be available from the GenerateAnswer API.
When 5 or more similar queries are clustered, every 30 minutes, QnA Maker suggests the alternate questions for you to accept or reject.
Reference:
https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/how-to/improve-knowledge-base

Explanation:
Comprehensive Detailed ExplanationYou have 1,000 untagged images and want to retrain the Custom Vision model as quickly as possible. The key is to avoid manually tagging every image, since that is time-consuming.
Step 1: Upload all the images
* First, bulk upload all the untagged images into the Custom Vision project.
* At this stage, they will have no labels.
Step 2: Get suggested tags
* The Custom Vision portal offers an auto-suggest feature that uses the current trained model to predict tags for new, untagged images.
* This dramatically reduces manual tagging effort.
Step 3: Review the suggestions and confirm the tags
* Auto-suggestions are not always 100% accurate, so you must confirm or correct them.
* Once confirmed, the dataset is labeled properly and ready for retraining.
Why not the other options?
* Upload the images by category / group into category folders: This is only helpful if the images already have known categories, but here they arrive untagged.
* Tag the images manually: This would take much longer and contradicts the requirement to minimize time.
* Upload all the images.
* Get suggested tags.
* Review the suggestions and confirm the tags.
Correct Sequence
* Custom Vision - Tag images
* Custom Vision - Suggested tags with predictions
Microsoft References

The Computer Vision API uses text recognition APIs to extract and recognize text information from images.
Read uses the latest recognition models, and is optimized for large, text-heavy documents and noisy images.
Reference:
https://docs.microsoft.com/en-us/azure/architecture/solution-ideas/articles/cognitive-search-with-skillsets

Explanation:

To create a resource that can generate fictional stories from prompts, you need an Azure OpenAI account (-- kind OpenAI).
To protect data with a customer-managed key (CMK), you must pass the key information (Key Vault URI, key name, key version) via the --encryption parameter when creating the Cognitive Services account. The JSON shown (with keyName, keyVersion, and keyVaultUri) is exactly the payload expected by --encryption.
A complete example pattern:
az cognitiveservices account create \
-n myresource -g myResourceGroup -l westeurope \
--kind OpenAI --sku S \
--assign-identity \
--encryption '{
"keyName":"keyname",
"keyVersion":"secretVersion",
"keyVaultUri":"https://<your-kv>.vault.azure.net/"
}'
(Adding --assign-identity allows the service to access the Key Vault key; the hotspot specifically asks for the parameter that takes the JSON block and the resource kind, which are --encryption and OpenAI.) Microsoft References
* Azure CLI: Create Cognitive Services account with customer-managed keys using --encryption.
https://learn.microsoft.com/azure/ai-services/cognitive-services-encryption-keys#configure-customer- managed-keys
* Azure Cognitive Services (Azure AI services) CLI parameters including --kind OpenAI.https://learn.
microsoft.com/azure/ai-services/cognitive-services-management-api-cli#create-a-cognitive-services- account