Designing and Implementing a Microsoft Azure AI Solution practice questions

1. Question 1 of 25

   You successfully run the following HTTP request. POST https://management.azure.com/subscriptions/18c51a87-3a69-47a8-aedc-a54745f708a1/resourceGroups/RG1/providers/ Microsoft.CognitiveServices/accounts/contoso1/regenerateKey?api-version=2017-04-18 Body{"keyName": "Key2"} What is the result of the request?

   • AA key for Azure Cognitive Services was generated in Azure Key Vault.
   • BA new query key was generated.
   • CThe primary subscription key and the secondary subscription key were rotated.
   • DThe secondary subscription key was reset.

   Show answer

   Correct answer: D

   How others answered

   • D92%

   Explanation

   Answer is correct - Sample response will be, { "key1": "KEY1", "key2": "KEY2" } This shows, Key1 is already there and this JSON request will generate Key2.

   Adapted from community discussion by LPreethi · 2021-07-20 · 15 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 1 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. L

      LPreethi

      2021-07-20

      15 upvotes

      Answer is correct - Sample response will be, { "key1": "KEY1", "key2": "KEY2" } This shows, Key1 is already there and this JSON request will generate Key2.

   2. Z

      ziizai

      2021-09-03

      10 upvotes

      B is wrong. Query key is for search service. The Rest request of create query key is like POST https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.Search/searchServices/{searchServiceName}/createQueryKey/{name}?api-version=2021-04-01-preview See in https://docs.microsoft.com/en-us/rest/api/searchmanagement/2021-04-01-preview/query-keys/create

   3. A

      azurelearner666

      2021-06-28

      5 upvotes

      What a crap question! it's confusing account keys which they are regenerating with the Subscription keys... those are aCcount keys not "query keys" The only matching option is "A. a key for cognitive services was generated" But... ... it was RE-generated the other options are even worse, "a query key was generated" (what this call does is regenerate an account key) or c or d, they talk about "subscription keys", which there is nothing by that name. Clearly the goal is to confuse, this question is as bad as it can be.

   4. G

      ghoppa

      2022-03-25

      5 upvotes

      Key2 has always been there. They are automatically created by default when you create a resource. You cannot delete them or add new ones, you can only regenerate/refresh them (poorly worded here as RESET). Still, correct answer is D in my opinion.

2. Question 2 of 25

   Select 3

   You build a custom Form Recognizer model. You receive sample files to use for training the model as shown in the following table.

   

   Which three files can you use to train the model? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

   • AFile1
   • BFile2
   • CFile3
   • DFile4
   • EFile5
   • FFile6

   Show answer

   Correct answer: A, C, F

   How others answered

   • ACF88%

   Explanation

   File 2 and 5 are excluded. New service limits now goes up to 500MB so... File 1, 3, and 6 are correct for "training the model", however if MSFT remove the word "training" from the question - be careful. https://docs.microsoft.com/en-gb/learn/modules/work-form-recognizer/3-get-started https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/service-limits?tabs=v21

   Adapted from community discussion by Eltooth · 2022-07-14 · 19 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 2 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. E

      Eltooth

      2022-07-14

      Selected A, C, F19 upvotes

      File 2 and 5 are excluded. New service limits now goes up to 500MB so... File 1, 3, and 6 are correct for "training the model", however if MSFT remove the word "training" from the question - be careful. https://docs.microsoft.com/en-gb/learn/modules/work-form-recognizer/3-get-started https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/service-limits?tabs=v21

   2. R

      RupRizal

      2023-11-22

      6 upvotes

      For custom model training the total size is still 50MB. Answer is correct https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-custom-classifier?view=doc-intel-4.0.0

   3. R

      rdemontis

      2023-11-11

      Selected A, C, F4 upvotes

      Correct but probably outdated answer. Because considering current limit of 500 MD we con consider correct the D answer too. https://docs.microsoft.com/en-gb/learn/modules/work-form-recognizer/3-get-started

   4. F

      fux

      2022-07-08

      5 upvotes

      The PDF must be capped at 50mb, so in reality, there are only 3 answers

3. Question 3 of 25

   Select 3

   A customer uses Azure Cognitive Search. The customer plans to enable a server-side encryption and use customer-managed keys (CMK) stored in Azure. What are three implications of the planned change? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

   • AThe index size will increase.
   • BQuery times will increase.
   • CA self-signed X.509 certificate is required.
   • DThe index size will decrease.
   • EQuery times will decrease.
   • FAzure Key Vault is required.

   Show answer

   Correct answer: A, B, F

   How others answered

   • ABF95%

   Explanation

   correct : "Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance." same document also lists Azure Key Vault as a requirement: https://docs.microsoft.com/en-us/azure/search/search-security-overview#data-protection

   Adapted from community discussion by SuperPetey · 2021-08-21 · 17 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 3 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. S

      SuperPetey

      2021-08-21

      17 upvotes

      correct : "Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance." same document also lists Azure Key Vault as a requirement: https://docs.microsoft.com/en-us/azure/search/search-security-overview#data-protection

   2. C

      CDL_Learner

      2024-04-10

      4 upvotes

      Based on the information from Microsoft’s documentation12, the implications of enabling server-side encryption and using customer-managed keys (CMK) stored in Azure for Azure Cognitive Search are: A. The index size will increase. Enabling CMK encryption increases the index size1. B. Query times will increase. Enabling CMK encryption degrades query performance. You can expect to see an increase of 30-60 percent in query times1. F. Azure Key Vault is required. CMK encryption depends on Azure Key Vault. You can create your own encryption keys and store them in a key vault, or you can use Azure Key Vault APIs to generate encryption keys1. So, the correct answers are A, B, and F. Please note that these changes might also lead to additional costs2. It’s always a good idea to review the Azure pricing details before making such changes.

   3. R

      reachmymind

      2022-03-05

      3 upvotes

      A. The index size will increase. B. Query times will increase. F. Azure Key Vault is required https://docs.microsoft.com/en-us/azure/search/search-security-overview#customer-managed-keys-cmk Customer-managed keys (CMK) Customer-managed keys require an additional billable service, Azure Key Vault, which can be in a different region, but under the same subscription, as Azure Cognitive Search. Enabling CMK encryption will increase index size and degrade query performance. Based on observations to date, you can expect to see an increase of 30%-60% in query times, although actual performance will vary depending on the index definition and types of queries. Because of this performance impact, we recommend that you only enable this feature on indexes that really require it.

   4. Z

      zellck

      2023-06-27

      Selected A, B, F2 upvotes

      ABF is the answer. https://learn.microsoft.com/en-us/azure/search/search-security-manage-encryption-keys Azure Cognitive Search automatically encrypts data at rest with service-managed keys. If more protection is needed, you can supplement default encryption with another encryption layer using keys that you create and manage in Azure Key Vault. https://learn.microsoft.com/en-us/azure/search/search-security-manage-encryption-keys?tabs=portal-pp%2Cmanaged-id-sys#work-with-encrypted-content With customer-managed key encryption, you'll notice latency for both indexing and queries due to the extra encrypt/decrypt work. Azure Cognitive Search doesn't log encryption activity, but you can monitor key access through key vault logging. We recommend that you enable logging as part of key vault configuration.

4. Question 4 of 25

   You are developing a new sales system that will process the video and text from a public-facing website. You plan to notify users that their data has been processed by the sales system. Which responsible AI principle does this help meet?

   • Atransparency
   • Bfairness
   • Cinclusiveness
   • Dreliability and safety

   Show answer

   Correct answer: A

   How others answered

   • A93%

   Explanation

   The correct answer is A, transparency: "When an AI application relies on personal data, such as a facial recognition system that takes images of people to recognize them; you should make it clear to the user how their data is used and retained, and who has access to it." from: https://docs.microsoft.com/en-us/learn/paths/prepare-for-ai-engineering/

   Adapted from community discussion by SuperPetey · 2021-08-21 · 78 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 4 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. S

      SuperPetey

      2021-08-21

      78 upvotes

      The correct answer is A, transparency: "When an AI application relies on personal data, such as a facial recognition system that takes images of people to recognize them; you should make it clear to the user how their data is used and retained, and who has access to it." from: https://docs.microsoft.com/en-us/learn/paths/prepare-for-ai-engineering/

   2. A

      ayoitu

      2021-08-27

      16 upvotes

      "Transparency: AI systems should be understandable." "Reliability and safety: AI systems should perform reliably and safely." so the answer is correct, reliability and safety https://docs.microsoft.com/en-us/azure/cloud-adoption-framework/strategy/responsible-ai

   3. E

      evangelist

      2024-02-11

      Selected A3 upvotes

      Notifying users that their data has been processed by the sales system helps meet the A. transparency principle. Transparency involves informing users about how their data is used, processed, and the purpose behind it, thereby fostering trust and understanding between the technology providers and the users.

   4. T

      torugao

      2022-07-01

      3 upvotes

      I also believe in A transparency. Because : "When an AI application relies on personal data, such as a facial recognition system that takes images of people to recognize them; you should make it clear to the user how their data is used and retained, and who has access to it." https://docs.microsoft.com/EN-US/learn/modules/prepare-to-develop-ai-solutions-azure/5-understand-considerations-for-responsible-ai

5. Question 5 of 25

   DRAG DROP - You need to develop an automated call handling system that can respond to callers in their own language. The system will support only French and English. Which Azure Cognitive Services service should you use to meet each requirement? To answer, drag the appropriate services to the correct requirements. Each service may be used once, more than once, or not at all. You may need to drag the split bat between panes or scroll to view content. NOTE: Each correct selection is worth one point. Select and Place:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer

   Explanation

   It should be: - Speech to Text with AutoDetectSourceLanguageConfig. It can't be Text Analytics because the input is callers' voice. - Text to Speech: the output is voice.

   Adapted from community discussion by Khiem · 2022-05-23 · 92 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Answer figure

   

   View community discussion4

   Candidate context

   Question 5 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. K

      Khiem

      2022-05-23

      92 upvotes

      It should be: - Speech to Text with AutoDetectSourceLanguageConfig. It can't be Text Analytics because the input is callers' voice. - Text to Speech: the output is voice.

   2. E

      Eltooth

      2022-07-14

      13 upvotes

      Speech-to-Text : https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-to-text Text-to-Speech : https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/text-to-speech Both support common languages, including French. https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support?tabs=speechtotext

   3. Z

      zellck

      2023-06-30

      7 upvotes

      1. Speech to Text 2. Test to Speech https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/language-identification?tabs=once&pivots=programming-language-csharp#speech-to-text You use Speech to text recognition when you need to identify the language in an audio source and then transcribe it to text. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/text-to-speech Text to speech enables your applications, tools, or devices to convert text into humanlike synthesized speech. The text to speech capability is also known as speech synthesis. Use humanlike prebuilt neural voices out of the box, or create a custom neural voice that's unique to your product or brand.

   4. B

      booofin

      2022-06-20

      5 upvotes

      I believe it should be: Text Analyzer Text to Speech The process being: 1) convert speech to text 2) recognize the language (Text Analyzer) 3) translate text with language from step 2 4) speak translated text (text to speech)

6. Question 6 of 25

   HOTSPOT - You are building an app that will process incoming email and direct messages to either French or English language support teams. Which Azure Cognitive Services API should you use? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Hot Area:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer

   Explanation

   The answer is wrong. Correct answer should be: Box1: https://eastus.api.cognitive.microsoft.com Box2: /text/analytics/v3.1/languages REF: https://learn.microsoft.com/en-us/rest/api/cognitiveservices-textanalytics/3.0/languages/languages?tabs=HTTP. NOTE: Pay special attention to the Sample Request provided. Request to the API should be of the form: POST {Endpoint}/text/analytics/v3.0/languages Where the {Endpoint} as stated under the sub-heading "URI Parameters" was described as quoted here (see "Description" column of the table): "Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com)." So the sample given shows the correct format of the *endpoint* as https://{location}.api.cognitive.microsoft.com

   Adapted from community discussion by Adedoyin_Simeon · 2022-12-27 · 58 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Answer figure

   

   View community discussion4

   Candidate context

   Question 6 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. A

      Adedoyin_Simeon

      2022-12-27

      58 upvotes

      The answer is wrong. Correct answer should be: Box1: https://eastus.api.cognitive.microsoft.com Box2: /text/analytics/v3.1/languages REF: https://learn.microsoft.com/en-us/rest/api/cognitiveservices-textanalytics/3.0/languages/languages?tabs=HTTP. NOTE: Pay special attention to the Sample Request provided. Request to the API should be of the form: POST {Endpoint}/text/analytics/v3.0/languages Where the {Endpoint} as stated under the sub-heading "URI Parameters" was described as quoted here (see "Description" column of the table): "Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com)." So the sample given shows the correct format of the *endpoint* as https://{location}.api.cognitive.microsoft.com

   2. M

      mk1967

      2022-09-07

      11 upvotes

      We only need to detect the language, so the Language Cognitive Service could be used, i.e.: POST {Endpoint}/text/analytics/v3.0/languages where Endpoint could be for example "westus" https://docs.microsoft.com/en-us/rest/api/cognitiveservices-textanalytics/3.0/languages/languages?tabs=HTTP

   3. Z

      zellck

      2023-06-30

      8 upvotes

      1. eastus.api.cognitive.microsoft.com 2. /text/analytics/v3.1/languages https://learn.microsoft.com/en-us/rest/api/cognitiveservices-textanalytics/3.0/languages/languages Detect Language The API returns the detected language and a numeric score between 0 and 1. Scores close to 1 indicate 100% certainty that the identified language is true. POST {Endpoint}/text/analytics/v3.0/languages - Endpoint Supported Cognitive Services endpoints (protocol and hostname, for example: https://westus.api.cognitive.microsoft.com).

   4. R

      RAN_L

      2023-03-15

      3 upvotes

      api.cogitive.microsofttranslator.com eastus.api.cognitive.microsoft.com portal.azure.com Out of these three options, only option 2 is a valid Azure Cognitive Services endpoint. The eastus.api.cognitive.microsoft.com endpoint is used for various Azure Cognitive Services, including the Text Analytics and Translator services. Option 1, api.cogitive.microsofttranslator.com, is not a valid endpoint for Azure Cognitive Services. It appears to be a typo, as "cogitive" is misspelled. Option 3, portal.azure.com, is the URL for the Azure portal, which is a web-based management interface for Azure services. It is not an endpoint for Azure Cognitive Services APIs. -./text/analytics/v3.1/languages One of the APIs that you can use to process incoming email and direct messages to either French or English language support teams is the Text Analytics API. The specific API endpoint you can use is /text/analytics/v3.1/languages. This API can detect the language of a given text and return the ISO 639-1 language code. You can then use this information to route the message to the appropriate language support team.

7. Question 7 of 25

   You have an Azure Cognitive Search instance that indexes purchase orders by using Form Recognizer. You need to analyze the extracted information by using Microsoft Power BI. The solution must minimize development effort. What should you add to the indexer?

   • Aa projection group
   • Ba table projection
   • Ca file projection
   • Dan object projection

   Show answer

   Correct answer: B

   How others answered

   • B88%

   Explanation

   Should be B . Its for Tables the Power BI " Use Power BI for data exploration. This tool works best when the data is in Azure Table Storage. Within Power BI, you can manipulate data into new tables that are easier to query and analyze"

   Adapted from community discussion by momentumhd · 2022-09-14 · 22 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 7 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. M

      momentumhd

      2022-09-14

      Selected B22 upvotes

      Should be B . Its for Tables the Power BI " Use Power BI for data exploration. This tool works best when the data is in Azure Table Storage. Within Power BI, you can manipulate data into new tables that are easier to query and analyze"

   2. L

      Lion007

      2023-10-29

      Selected B9 upvotes

      B is the correct answer. See below to understand the workflow: Purchase Orders (POs) -> Form Recognizer -> OCR -> JSON (extracted info from POs) -> Shaper skill -> JSON -> Table Projection -> JSON -> Power BI Ref: Define a table projection https://learn.microsoft.com/en-us/azure/search/knowledge-store-projections-examples#define-a-table-projection

   3. U

      uira

      2023-04-07

      7 upvotes

      You receive a JSON object, so ObjectProjection is the most appropriate way to explore: Objects: "Used when you need the full JSON representation of your data and enrichments in one JSON document. As with table projections, only valid JSON objects can be projected as objects, and shaping can help you do that." As per https://learn.microsoft.com/en-us/azure/search/knowledge-store-projection-overview

   4. R

      RAN_L

      2023-03-15

      Selected B3 upvotes

      To enable integration with Power BI, you should add a table projection to the indexer. This allows the data to be easily queried and visualized in Power BI. A projection in Azure Cognitive Search is a way to specify the fields that should be included in the search index. A table projection specifies the columns of a table to be projected as fields in the search index. By including a table projection in the indexer, you can extract the relevant data from the purchase orders and make it available for analysis in Power BI. This would minimize development effort, as Power BI has built-in integration with Azure Cognitive Search and can easily consume data from the search index. Therefore, the correct answer is B. a table projection.

8. Question 8 of 25

   You have a factory that produces food products. You need to build a monitoring solution for staff compliance with personal protective equipment (PPE) requirements. The solution must meet the following requirements: * Identify staff who have removed masks or safety glasses. * Perform a compliance check every 15 minutes. * Minimize development effort. * Minimize costs. Which service should you use?

   • AFace
   • BComputer Vision
   • CAzure Video Analyzer for Media (formerly Video Indexer)

   Show answer

   Correct answer: A

   How others answered

   • A39%
   • B30%
   • C30%

   Only 39% agreed on this answer — treat it as contested rather than settled.

   Explanation

   A. Face. The solution link explains: Embed facial recognition into your apps for a seamless and highly secured user experience. No machine-learning expertise is required. Features include face detection that perceives facial features and attributes—such as a face mask, glasses, or face location—in an image, and identification of a person by a match to your private repository or via photo ID.

   Adapted from community discussion by Davard · 2022-09-20 · 16 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 8 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. D

      Davard

      2022-09-20

      16 upvotes

      A. Face. The solution link explains: Embed facial recognition into your apps for a seamless and highly secured user experience. No machine-learning expertise is required. Features include face detection that perceives facial features and attributes—such as a face mask, glasses, or face location—in an image, and identification of a person by a match to your private repository or via photo ID.

   2. Z

      zellck

      2023-06-27

      Selected A8 upvotes

      A is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-identity#face-detection-and-analysis Face detection is required as a first step in all the other scenarios. The Detect API detects human faces in an image and returns the rectangle coordinates of their locations. It also returns a unique ID that represents the stored face data. This is used in later operations to identify or verify faces. Optionally, face detection can extract a set of face-related attributes, such as head pose, age, emotion, facial hair, and glasses. These attributes are general predictions, not actual classifications. Some attributes are useful to ensure that your application is getting high-quality face data when users add themselves to a Face service. For example, your application could advise users to take off their sunglasses if they're wearing sunglasses.

   3. T

      Toby86

      2024-07-11

      2 upvotes

      It's C. From: https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-overview People's detected clothing (preview): Detects the clothing types of people appearing in the video and provides information such as long or short sleeves, long or short pants and skirt or dress. The detected clothing is associated with the people wearing it and the exact timestamp (start, end) along with a confidence level for the detection are provided. For more information, see detected clothing. Featured clothing (preview): Captures featured clothing images appearing in a video. You can improve your targeted ads by using the featured clothing insight. For information on how the featured clothing images are ranked and how to get the insights, see featured clothing.

   4. S

      syupwsh

      2025-02-14

      Selected A1 upvote

      "identify" and "check every 15 minutes" https://learn.microsoft.com/en-gb/azure/ai-services/computer-vision/overview-identity Verify user identity: Verify a person against a trusted face image. This verification could be used to grant access to digital or physical properties such as a bank account, access to a building, and so on. In most cases, the trusted face image could come from a government-issued ID such as a passport or driver’s license, or it could come from an enrollment photo taken in person. During verification, liveness detection can play a critical role in verifying that the image comes from a real person, not a printed photo or mask The goal of liveness detection is to ensure that the system is interacting with a physically present live person at the time of authentication I would say A

9. Question 9 of 25

   You have an Azure Cognitive Search solution and a collection of blog posts that include a category field. You need to index the posts. The solution must meet the following requirements: * Include the category field in the search results. * Ensure that users can search for words in the category field. * Ensure that users can perform drill down filtering based on category. Which index attributes should you configure for the category field?

   • Asearchable, sortable, and retrievable
   • Bsearchable, facetable, and retrievable
   • Cretrievable, filterable, and sortable
   • Dretrievable, facetable, and key

   Show answer

   Correct answer: B

   How others answered

   • B96%

   Explanation

   Vote for B Retrievable: Include the category field in the search results. Searchable: Ensure that users can search for words in the category field. Facetable: Ensure that users can perform drill down filtering based on category.

   Adapted from community discussion by Internal_Koala · 2022-09-05 · 48 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

   Supporting references

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   View community discussion4

   Candidate context

   Question 9 discussion

   These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

   1. I

      Internal_Koala

      2022-09-05

      Selected B48 upvotes

      Vote for B Retrievable: Include the category field in the search results. Searchable: Ensure that users can search for words in the category field. Facetable: Ensure that users can perform drill down filtering based on category.

   2. Z

      zellck

      2023-06-27

      Selected B5 upvotes

      B is the answer. https://learn.microsoft.com/en-us/rest/api/searchservice/create-index#-field-definitions- - retrievable Indicates whether the field can be returned in a search result. - searchable Indicates whether the field is full-text searchable and can be referenced in search queries. - facetable Indicates whether to enable the field to be referenced in facet queries.

   3. P

      PeteColag

      2024-05-26

      4 upvotes

      B. searchable, facetable, and retrievable Here's why: Searchable: This allows the category field to be included in full-text searches, meaning users can search for words within the category field. Facetable: This allows the category field to be used in drill-down filtering, enabling users to filter search results based on the categories. Retrievable: This ensures that the category field is included in the search results that are returned to the user. These attributes together satisfy all the given requirements.

   4. E

      evangelist

      2024-02-12

      Selected B2 upvotes

      For indexing blog posts in Azure Cognitive Search with the requirements specified, the correct attributes for the category field would be: B. searchable, facetable, and retrievable searchable: Allows users to search for words within the category field. facetable: Enables drill down filtering based on category, which is essential for users to narrow down search results. retrievable: Ensures that the category field is included in the search results, allowing users to see which category each blog post belongs to.

10. Question 10 of 25

    HOTSPOT - You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must meet the following requirements: ✑ Use a single key and endpoint to access multiple services. ✑ Consolidate billing for future services that you might use. ✑ Support the use of Computer Vision in the future. How should you complete the HTTP request to create the new resource? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Hot Area:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    Box 1: PUT - Sample Request: PUT https://management.azure.com/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/test-rg/providers/ Microsoft.DeviceUpdate/accounts/contoso?api-version=2020-03-01-preview Incorrect Answers: PATCH is for updates. Box 2: CognitiveServices - Microsoft Azure Cognitive Services provide us to use its pre-trained models for various Business Problems related to Machine Learning. List of Different Services are: ✑ Decision ✑ Language (includes sentiment analysis) ✑ Speech ✑ Vision (includes OCR) ✑ Web Search Reference: https://docs.microsoft.com/en-us/rest/api/deviceupdate/resourcemanager/accounts/create https://www.analyticsvidhya.com/blog/2020/12/microsoft-azure-cognitive-services-api-for-ai-development/

    Adapted from community discussion by WillyMac · 2021-06-12 · 26 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 10 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. W

       WillyMac

       2021-06-12

       26 upvotes

       I think answer is correct. PUT: puts a file or resource at a specific URI, and exactly at that URI. If there's already a file or resource at that URI, PUT replaces that file or resource. If there is no file or resource there, PUT creates one. POST: POST sends data to a specific URI and expects the resource at that URI to handle the request.

    2. A

       Adedoyin_Simeon

       2021-07-01

       14 upvotes

       Although in Web Programming, and API dev, PUT is an http(s) request method for an update operation. I can however create a resource when there is no resource to update. I don't know why precisely but the method used by Azure to actually make a REST API request to create a resource is actually "PUT". So, the answers are correct. See Ref: https://docs.microsoft.com/en-us/rest/api/resources/resources/create-or-update

    3. Z

       zellck

       2023-06-30

       8 upvotes

       1. PUT 2. CognitiveServices https://learn.microsoft.com/en-us/rest/api/resources/resources/create-or-update https://learn.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account?tabs=multiservice%2Canomaly-detector%2Clanguage-service%2Ccomputer-vision%2Cwindows#types-of-cognitive-services-resources You can access Azure Cognitive Services through two different resources: A multi-service resource, or a single-service one. - Multi-service resource: Access multiple Azure Cognitive Services with a single key and endpoint. Consolidates billing from the services you use.

    4. L

       LPreethi

       2021-07-20

       4 upvotes

       May be the reason to use PUT is because , PUT requests must be idempotent. If a client submits the same PUT request multiple times, the results should always be the same (the same resource will be modified with the same values). POST and PATCH requests are not guaranteed to be idempotent.

11. Question 11 of 25

    HOTSPOT - You have an Azure Cognitive Search resource named Search1 that is used by multiple apps. You need to secure Search1. The solution must meet the following requirements: • Prevent access to Search1 from the internet. • Limit the access of each app to specific queries. What should you do? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    1. Create a private endpoint 2. Use Azure roles https://learn.microsoft.com/en-us/azure/search/service-create-private-endpoint#why-use-a-private-endpoint-for-secure-access Private Endpoints for Azure Cognitive Search allow a client on a virtual network to securely access data in a search index over a Private Link. The private endpoint uses an IP address from the virtual network address space for your search service. Network traffic between the client and the search service traverses over the virtual network and a private link on the Microsoft backbone network, eliminating exposure from the public internet. https://learn.microsoft.com/en-us/azure/search/search-security-rbac?tabs=config-svc-portal%2Croles-portal%2Ctest-portal%2Ccustom-role-portal%2Cdisable-keys-portal#grant-access-to-a-single-index In some scenarios, you may want to limit application's access to a single resource, such as an index. The portal doesn't currently support role assignments at this level of granularity, but it can be done with PowerShell or the Azure CLI.

    Adapted from community discussion by zellck · 2023-06-30 · 29 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 11 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. Z

       zellck

       2023-06-30

       29 upvotes

       1. Create a private endpoint 2. Use Azure roles https://learn.microsoft.com/en-us/azure/search/service-create-private-endpoint#why-use-a-private-endpoint-for-secure-access Private Endpoints for Azure Cognitive Search allow a client on a virtual network to securely access data in a search index over a Private Link. The private endpoint uses an IP address from the virtual network address space for your search service. Network traffic between the client and the search service traverses over the virtual network and a private link on the Microsoft backbone network, eliminating exposure from the public internet. https://learn.microsoft.com/en-us/azure/search/search-security-rbac?tabs=config-svc-portal%2Croles-portal%2Ctest-portal%2Ccustom-role-portal%2Cdisable-keys-portal#grant-access-to-a-single-index In some scenarios, you may want to limit application's access to a single resource, such as an index. The portal doesn't currently support role assignments at this level of granularity, but it can be done with PowerShell or the Azure CLI.

    2. E

       examworld

       2023-05-29

       5 upvotes

       1. Private Endpoint https://learn.microsoft.com/en-us/azure/search/service-create-private-endpoint 2. Key authentication https://learn.microsoft.com/en-us/azure/search/search-security-api-keys?tabs=portal-use%2Cportal-find%2Cportal-query

    3. U

       Ultron00

       2024-07-08

       2 upvotes

       Azure Cognitive Search primarily relies on API keys for authentication and authorization. By generating different API keys, you can control and restrict the access each app has to specific queries. Azure Roles are not used directly for query-level permissions in Azure Cognitive Search. So, the complete solution would be: Prevent access to Search1 from the internet: Configure a Private Endpoint for Search1 Limit the access of each app to specific queries: Use key authentication

    4. N

       NullVoider_0

       2024-04-02

       2 upvotes

       Create Private Endpoint Use Key authentication. Azure roles, specifically Azure Role-Based Access Control (RBAC), are designed to manage who has access to Azure resources and what they can do with those resources. While RBAC is effective for controlling access at the resource level (e.g., who can manage the search service, indexes, or data sources), it does not provide the granularity needed to limit access to specific queries within Azure Cognitive Search.

12. Question 12 of 25

    You have the following C# method for creating Azure Cognitive Services resources programmatically.

    

    You need to call the method to create a free Azure resource in the West US Azure region. The resource will be used to generate captions of images automatically. Which code should you use?

    • Acreate_resource(client, "res1", "ComputerVision", "F0", "westus")
    • Bcreate_resource(client, "res1", "CustomVision.Prediction", "F0", "westus")
    • Ccreate_resource(client, "res1", "ComputerVision", "S0", "westus")
    • Dcreate_resource(client, "res1", "CustomVision.Prediction", "S0", "westus")

    Show answer

    Correct answer: A

    How others answered

    • A85%
    • B15%

    Explanation

    Answer shall be A, as there is free tier available for Computer Vision service. - Free - Web/Container - 20 per minute - 5,000 free transactions per month

    Adapted from community discussion by dinesh_tng · 2021-08-13 · 68 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • azure.microsoft.com documentation
    • azure.microsoft.com documentation
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 12 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. D

       dinesh_tng

       2021-08-13

       68 upvotes

       Answer shall be A, as there is free tier available for Computer Vision service. - Free - Web/Container - 20 per minute - 5,000 free transactions per month

    2. Z

       zellck

       2023-06-28

       Selected A6 upvotes

       A is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account-client-library?pivots=programming-language-csharp#create-a-cognitive-services-resource-c To create and subscribe to a new Cognitive Services resource, use the Create method. This method adds a new billable resource to the resource group you pass in. When creating your new resource, you'll need to know the "kind" of service you want to use, along with its pricing tier (or SKU) and an Azure location. The following method takes all of these as arguments and creates a resource.

    3. Y

       Yazn

       2022-07-19

       4 upvotes

       I'm 100% sure the answer is A. Computer vision has free tier offering generating image captions (I have tried it), and the customer vision doesn't directly support generate captions on the image but returns some info about the given image specifically in the object detection part, under a very specific condition that you have pretrained the model on your own images which is not stated in the question.

    4. S

       sumanshu

       2022-01-03

       4 upvotes

       C & D - Looks Wrong (Because both are not FREE TIER) and in question is explicitly mention, we have to use FREE TIER. So, remaining options are A & B. There is a FREE TIER for computer vision - but that FREE TIER will not perform caption image part. So, Customer Vision prediction will predict / guess / generate the caption of the image. Vote for B

13. Question 13 of 25

    You are developing the knowledgebase by using Azure Cognitive Search. You need to process wiki content to meet the technical requirements. What should you include in the solution?

    • Aan indexer for Azure Blob storage attached to a skillset that contains the language detection skill and the text translation skill
    • Ban indexer for Azure Blob storage attached to a skillset that contains the language detection skill
    • Can indexer for Azure Cosmos DB attached to a skillset that contains the document extraction skill and the text translation skill
    • Dan indexer for Azure Cosmos DB attached to a skillset that contains the language detection skill and the text translation skill

    Show answer

    Correct answer: D

    How others answered

    • D81%
    • C19%

    Explanation

    The correct answer is D. Use an indexer connected to Azure Cosmos DB that includes language detection and text translation skills. This solution meets the requirement for handling multiple languages and supports content transformation for English, French, and Portuguese by using the text translation skill, which aligns with the technical requirement for multilingual support. Additionally, using Azure Cosmos DB and associated skill sets ensures content security and role-based access control (RBAC), meeting the requirements for content approval and security.

    Adapted from community discussion by evangelist · 2024-02-16 · 15 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 13 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. E

       evangelist

       2024-02-16

       Selected D15 upvotes

       The correct answer is D. Use an indexer connected to Azure Cosmos DB that includes language detection and text translation skills. This solution meets the requirement for handling multiple languages and supports content transformation for English, French, and Portuguese by using the text translation skill, which aligns with the technical requirement for multilingual support. Additionally, using Azure Cosmos DB and associated skill sets ensures content security and role-based access control (RBAC), meeting the requirements for content approval and security.

    2. G

       g2000

       2022-05-20

       Selected D11 upvotes

       Document extraction skill only works for files. It's less likely to work with CosmoDB.

    3. R

       rdemontis

       2023-11-11

       Selected D3 upvotes

       IMHO the correct answer should be D. You don't need Document Extraction to extract text from files. You have already the text in wikis. https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-document-extraction It's true that Text Translation could also detect the source language but reading the documentation seems it could be not so accurate. https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-text-translation For sure you need two operations here: detect and translate.

    4. M

       Murtuza

       2024-03-24

       Selected D4 upvotes

       Therefore, A. an indexer for Cosmos DB attached to a skillset that contains the language detection skill and the text translation skill aligns with the technical requirements for content approval, multilingual support, and RBAC1

14. Question 14 of 25

    HOTSPOT - You are developing an application that will use the Computer Vision client library. The application has the following code.

    

    For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Hot Area:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    Box 3 should be Yes, a stream is only a pathway for data. and in this case the data actually comes from a local file. The correct answer would be No, Yes, Yes.

    Adapted from community discussion by Adedoyin_Simeon · 2021-07-04 · 38 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 14 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. M

       motu

       2021-06-07

       101 upvotes

       Box 3 is Yes, the stream will be generated from a local image!

    2. A

       Adedoyin_Simeon

       2021-07-04

       38 upvotes

       Box 3 should be Yes, a stream is only a pathway for data. and in this case the data actually comes from a local file. The correct answer would be No, Yes, Yes.

    3. Z

       zellck

       2023-07-01

       11 upvotes

       NYY is the answer. https://learn.microsoft.com/en-us/java/api/com.microsoft.azure.cognitiveservices.vision.computervision.computervision?view=azure-java-legacy#com-microsoft-azure-cognitiveservices-vision-computervision-computervision-analyzeimageinstreamasync(byte-()-analyzeimageinstreamoptionalparameter) his operation extracts a rich set of visual features based on the image content. Two input methods are supported (1) Uploading an image or (2) specifying an image URL.

    4. D

       Duch003

       2021-06-30

       7 upvotes

       I agree that C is technically correct, but they are still expecting us to answer No for that one, because, if we stick that much to the details, it will be read from stream, not as a picture directly. Tricky one, I do not like it as well.

15. Question 15 of 25

    DRAG DROP - You are developing a call to the Face API. The call must find similar faces from an existing list named employeefaces. The employeefaces list contains 60,000 images. How should you complete the body of the HTTP request? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point. Select and Place:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    Box 1: LargeFaceListID - LargeFaceList: Add a face to a specified large face list, up to 1,000,000 faces. Note: Given query face's faceId, to search the similar-looking faces from a faceId array, a face list or a large face list. A "faceListId" is created by FaceList - Create containing persistedFaceIds that will not expire. And a "largeFaceListId" is created by LargeFaceList - Create containing persistedFaceIds that will also not expire. Incorrect Answers: Not "faceListId": Add a face to a specified face list, up to 1,000 faces. Box 2: matchFace - Find similar has two working modes, "matchPerson" and "matchFace". "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces. Reference: https://docs.microsoft.com/en-us/rest/api/faceapi/face/findsimilar

    Adapted from community discussion by Eltooth · 2022-07-18 · 7 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 15 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. P

       PHD_CHENG

       2022-05-06

       12 upvotes

       Facelist ID up to 1,000 faces; LargeFaceListId up to 1,000,000 faces https://docs.microsoft.com/en-us/rest/api/faceapi/large-face-list

    2. E

       Eltooth

       2022-07-18

       7 upvotes

       I'm leaning towards: largeFaceListId and matchedPerson https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar?tabs=HTTP#find-similar-results-example "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces.

    3. S

       sumanshu

       2022-01-04

       5 upvotes

       In Question it's given we have to find similar faces - So we have to use "matchFace" and because there are large list , so we have to use LargeFaceListID

    4. L

       luishenriquesb

       2022-05-29

       5 upvotes

       it's should be largeFaceListId not LargeFaceListId (Capitalized). It's wouldn't work in a http request...

16. Question 16 of 25

    DRAG DROP - You are developing a photo application that will find photos of a person based on a sample image by using the Face API. You need to create a POST request to find the photos. How should you complete the request? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point. Select and Place:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    findsimilars and matchPerson https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar?tabs=HTTP#find-similar-results-example "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces.

    Adapted from community discussion by Eltooth · 2022-07-18 · 15 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 16 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. M

       motu

       2021-06-07

       79 upvotes

       Box 1 is "findsimilars", others do not match the given request body and make no sense anyway. https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar

    2. E

       Eltooth

       2022-07-18

       15 upvotes

       findsimilars and matchPerson https://docs.microsoft.com/en-us/rest/api/faceapi/face/find-similar?tabs=HTTP#find-similar-results-example "matchPerson" is the default mode that it tries to find faces of the same person as possible by using internal same-person thresholds. It is useful to find a known person's other photos. Note that an empty list will be returned if no faces pass the internal thresholds. "matchFace" mode ignores same-person thresholds and returns ranked similar faces anyway, even the similarity is low. It can be used in the cases like searching celebrity-looking faces.

    3. Z

       zellck

       2023-07-01

       11 upvotes

       1. findsimilars 2. matchPerson https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/find-similar-faces?tabs=rest#find-and-print-matches The Find Similar operation does face matching between a target face and a set of candidate faces, finding a smaller set of faces that look similar to the target face. This is useful for doing a face search by image.

    4. R

       reachmymind

       2022-03-04

       5 upvotes

       Box 1: findsimilars Box 2: matchPerson https://dev.cognitive.azure.cn/docs/services/563879b61984550e40cbbe8d/operations/563879b61984550f30395237

17. Question 17 of 25

    HOTSPOT - You develop an application that uses the Face API. You need to add multiple images to a person group. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Hot Area:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    Parallel.For(0, PersonCount, async i => { Guid personId = persons[i].PersonId; string personImageDir = @"/path/to/person/i/images"; foreach (string imagePath in Directory.GetFiles(personImageDir, "*.jpg")) { await WaitCallLimitPerSecondAsync(); using (Stream stream = File.OpenRead(imagePath)) { await faceClient.PersonGroupPerson.AddFaceFromStreamAsync(personGroupId, personId, stream); } } }); https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces

    Adapted from community discussion by Happiness20 · 2022-03-20 · 3 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 17 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. L

       leo822

       2021-12-14

       70 upvotes

       AddFaceFromStreamAsync. Step 5 on https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces

    2. A

       azurelearner666

       2021-12-30

       53 upvotes

       Wrong! A - Stream (this is correct) B - AddFaceFromStreamAsync (literally the same code from Step 5 at https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces)

    3. M

       motu

       2021-12-07

       5 upvotes

       AddFileFromStreamAsync is right: https://docs.microsoft.com/en-us/dotnet/api/microsoft.azure.cognitiveservices.vision.face.persongrouppersonextensions.addfacefromstreamasync?view=azure-dotnet

    4. Z

       zellck

       2024-01-01

       5 upvotes

       1. Stream 2. AddFaceFromStreamAsync https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/add-faces#step-5-add-faces-to-the-persons

18. Question 18 of 25

    You plan to build an app that will generate a list of tags for uploaded images. The app must meet the following requirements: • Generate tags in a user's preferred language. • Support English, French, and Spanish. • Minimize development effort. You need to build a function that will generate the tags for the app. Which Azure service endpoint should you use?

    • AContent Moderator Image Moderation
    • BCustom Vision image classification
    • CComputer Vision Image Analysis
    • DCustom Translator

    Show answer

    Correct answer: C

    How others answered

    • C100%

    Explanation

    I think the answer should be C, because of the minimized developement effort. Since the prebuilt model of C also fits the other two requirements, so there is no need to train a custom model. source: https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/call-analyze-image?tabs=rest

    Adapted from community discussion by MaliSanFuu · 2023-04-24 · 19 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 18 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. M

       MaliSanFuu

       2023-04-24

       Selected C19 upvotes

       I think the answer should be C, because of the minimized developement effort. Since the prebuilt model of C also fits the other two requirements, so there is no need to train a custom model. source: https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/call-analyze-image?tabs=rest

    2. E

       evangelist

       2024-01-27

       Selected C8 upvotes

       Here's why: Multilingual Tag Generation: Azure's Computer Vision Image Analysis service can analyze images and provide a list of tags describing the content of the images. It also has the capability to return these tags in various languages, including English, French, and Spanish, which aligns with your requirement. Minimizing Development Effort: This service offers a pre-built model, which means there is no need for you to collect data and train your own model. This significantly reduces the development effort and time. You simply need to call the API with your images, and it will return the tags.

    3. Z

       zellck

       2023-06-28

       4 upvotes

       https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/language-support#image-analysis Some features of the Analyze - Image API can return results in other languages, specified with the language query parameter. Other actions return results in English regardless of what language is specified, and others throw an exception for unsupported languages. Actions are specified with the visualFeatures and details query parameters; see the Overview for a list of all the actions you can do with image analysis. Languages for tagging are only available in API version 3.2 or later.

    4. Z

       zellck

       2023-06-28

       Selected C3 upvotes

       C is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-tagging-images Image Analysis can return content tags for thousands of recognizable objects, living beings, scenery, and actions that appear in images. Tags are not organized as a taxonomy and do not have inheritance hierarchies. A collection of content tags forms the foundation for an image description displayed as human readable language formatted in complete sentences. When tags are ambiguous or not common knowledge, the API response provides hints to clarify the meaning of the tag in context of a known setting.

19. Question 19 of 25

    HOTSPOT - You have a Computer Vision resource named contoso1 that is hosted in the West US Azure region. You need to use contoso1 to make a different size of a product photo by using the smart cropping feature. How should you complete the API URL? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point. Hot Area:

    

    This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

    Show the answer figure

    Answer

    Explanation

    Both answers are incorrect. The correct answers are: https://contoso1.cognitiveservices.azure.com/ AND generateThumbnail westus.dev.cognitive.microsoft.com wouldn't be a correct Computer Vision endpoint if the resource name is contoso1. Also, per the documentation, areaOfInterest "returns a bounding box around the most important area of the image", it doesn't return a different size photo (https://docs.microsoft.com/en-us/rest/api/computervision/3.1/get-area-of-interest).

    Adapted from community discussion by VulcanMXNY · 2021-10-26 · 48 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    Answer figure

    

    View community discussion4

    Candidate context

    Question 19 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. V

       VulcanMXNY

       2021-10-26

       48 upvotes

       Both answers are incorrect. The correct answers are: https://contoso1.cognitiveservices.azure.com/ AND generateThumbnail westus.dev.cognitive.microsoft.com wouldn't be a correct Computer Vision endpoint if the resource name is contoso1. Also, per the documentation, areaOfInterest "returns a bounding box around the most important area of the image", it doesn't return a different size photo (https://docs.microsoft.com/en-us/rest/api/computervision/3.1/get-area-of-interest).

    2. Z

       zellck

       2023-07-01

       13 upvotes

       1. https://contoso1.cognitiveservices.azure.com 2. generateThumbnail https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-generating-thumbnails A thumbnail is a reduced-size representation of an image. Thumbnails are used to represent images and other data in a more economical, layout-friendly way. The Computer Vision API uses smart cropping to create intuitive image thumbnails that include the most important regions of an image with priority given to any detected faces. The Computer Vision thumbnail generation algorithm works as follows: - Remove distracting elements from the image and identify the area of interest—the area of the image in which the main object(s) appears. - Crop the image based on the identified area of interest. - Change the aspect ratio to fit the target thumbnail dimensions.

    3. Z

       ziizai

       2021-09-03

       15 upvotes

       yes, the question is exactly the sample here https://docs.microsoft.com/en-us/rest/api/computervision/3.1/generate-thumbnail/generate-thumbnail#examples

    4. D

       dazdzadzadzaazd

       2023-07-22

       11 upvotes

       Today (july 2023), both regional and resource endpoints are supported. So both are correct : https://contoso1.cognitiveservices.azure.com/ AND https://westus.api.cognitive.microsoft.com Doc : https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-custom-subdomains#what-if-an-sdk-asks-me-for-the-region-for-a-resource "Regional endpoints and custom subdomain names are both supported and can be used interchangeably." I tested it by creating a custom vision resource and used it with both endpoints.

20. Question 20 of 25

    You are building an app that will include one million scanned magazine articles. Each article will be stored as an image file. You need to configure the app to extract text from the images. The solution must minimize development effort. What should you include in the solution?

    • AComputer Vision Image Analysis
    • Bthe Read API in Computer Vision
    • CForm Recognizer
    • DAzure Cognitive Service for Language

    Show answer

    Correct answer: B

    How others answered

    • B89%

    Explanation

    To me the correct answer is B. With the new Image Analysis API 4.0 (in preview) you could use OCR feature too, but as i said, it is in preview. And i don't think it is considered in the exam. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0 Instead the Read API is particularly adapted for text-heavy documents and it seems this is the case https://learn.microsoft.com/en-us/rest/api/computervision/read/read?view=rest-computervision-v3.1&tabs=HTTP

    Adapted from community discussion by rdemontis · 2023-11-04 · 11 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 20 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. R

       rdemontis

       2023-11-04

       Selected B11 upvotes

       To me the correct answer is B. With the new Image Analysis API 4.0 (in preview) you could use OCR feature too, but as i said, it is in preview. And i don't think it is considered in the exam. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-image-analysis?tabs=4-0 Instead the Read API is particularly adapted for text-heavy documents and it seems this is the case https://learn.microsoft.com/en-us/rest/api/computervision/read/read?view=rest-computervision-v3.1&tabs=HTTP

    2. J

       jangotango

       2023-10-05

       9 upvotes

       All answers should have a reference to prove the answer is true

    3. J

       JDKJDKJDK

       2023-10-06

       Selected B5 upvotes

       i also think its B Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents. https://learn.microsoft.com/en-us/rest/api/computervision/3.2preview2/read/read?tabs=HTTP

    4. M

       MarceloManhaes

       2024-06-16

       2 upvotes

       This is a good explanation from chat GPT why B is the correct fit and A is not: A - Computer Vision Image Analysis: This is a service provided by Azure that can extract a wide variety of visual features from your images. It can determine whether an image contains adult content, find specific brands or objects, or find human faces. However, while it does have OCR capabilities, it is not specifically designed for large-scale text extraction from images. B - Read API in Computer Vision: This is a part of the Azure Computer Vision service that is designed to extract printed and handwritten text from images. It uses state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents2. This could be a good fit for your needs as it is designed to handle large amounts of text in images. the key here is option A it is not specifically designed for large-scale text extraction from images.

21. Question 21 of 25

    You have a 20-GB video file named File1.avi that is stored on a local drive. You need to index File1.avi by using the Azure Video Indexer website. What should you do first?

    • AUpload File1.avi to an Azure Storage queue.
    • BUpload File1.avi to the Azure Video Indexer website.
    • CUpload File1.avi to Microsoft OneDrive.
    • DUpload File1.avi to the www.youtube.com webpage.

    Show answer

    Correct answer: C

    How others answered

    • C78%
    • B22%

    Explanation

    Upload file size and video duration If uploading a file from your device, the file size limit is 2 GB. If the video is uploaded from a URL, the file size limit is 30 GB. The URL must lead to an online media file with a media file extension (for example myvideo.MP4) and not a webpage such as https://www.youtube.com. The file duration limit is 4 hours. https://learn.microsoft.com/en-us/azure/azure-video-indexer/avi-support-matrix

    Adapted from community discussion by Mehe323 · 2024-03-27 · 5 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 21 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. S

       suryakalla

       2023-10-06

       20 upvotes

       This question is part of free assessment given by Microsoft and the answer in that was C.

    2. M

       Mehe323

       2024-03-27

       Selected C5 upvotes

       Upload file size and video duration If uploading a file from your device, the file size limit is 2 GB. If the video is uploaded from a URL, the file size limit is 30 GB. The URL must lead to an online media file with a media file extension (for example myvideo.MP4) and not a webpage such as https://www.youtube.com. The file duration limit is 4 hours. https://learn.microsoft.com/en-us/azure/azure-video-indexer/avi-support-matrix

    3. S

       Student2023

       2023-10-06

       Selected C4 upvotes

       Uploading Guidelines: Uploading files to Video Indexer Uploading a local file from your device Supported file formats include: .wmv, .avi, .mov. The file should be up to 2GB and up to 4 hours. You can upload up to 10 files at a time. Uploading an online file The URL should lead to an online media file (for example a OneDrive file), not a webpage (like www.youtube.com). The file should be up to 30GB and up to 4 hours. You can upload up to 10 files at a time.

    4. J

       Jimmy1017

       2024-04-26

       1 upvote

       B. Upload File1.avi to the Azure Video Indexer website. Explanation: The Azure Video Indexer website is specifically designed to analyze and index video files, extracting insights such as keywords, faces, sentiments, and more. Uploading File1.avi directly to the Azure Video Indexer website allows the platform to process the video file and generate the necessary metadata and insights. Options A, C, and D are not relevant for indexing File1.avi using the Azure Video Indexer website. Uploading to Azure Storage queue (option A) is not appropriate for indexing videos. Microsoft OneDrive (option C) is a cloud storage service and doesn't provide video indexing capabilities like the Azure Video Indexer. Uploading to YouTube (option D) is also not relevant as the task is to index the video using the Azure Video Indexer website. Therefore, option B is the correct choice.

22. Question 22 of 25

    Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen. You build a language model by using a Language Understanding service. The language model is used to search for information on a contact list by using an intent named FindContact. A conversational expert provides you with the following list of phrases to use for training. ✑ Find contacts in London. ✑ Who do I know in Seattle? ✑ Search for contacts in Ukraine. You need to implement the phrase list in Language Understanding. Solution: You create a new pattern in the FindContact intent. Does this meet the goal?

    • AYes
    • BNo

    Show answer

    Correct answer: A

    How others answered

    • A51%
    • B49%

    Only 51% agreed on this answer — treat it as contested rather than settled.

    Explanation

    Using a pattern could be a good solution IMHO... ✑ Find contacts in London. ✑ Who do I know in Seattle? ✑ Search for contacts in Ukraine. Like Where is {FormName}[?] Who authored {FormName}[?] {FormName} is published in French[?] (taken from https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-patterns) we could do: ✑ Find contacts in {CityOrCountry}. ✑ Who do I know in {CityOrCountry}[?] ✑ Search for contacts in {CityOrCountry}[?]. So, to me a pattern is a Solution (A)

    Adapted from community discussion by azurelearner666 · 2021-06-30 · 35 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 22 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. A

       azurelearner666

       2021-06-30

       35 upvotes

       Using a pattern could be a good solution IMHO... ✑ Find contacts in London. ✑ Who do I know in Seattle? ✑ Search for contacts in Ukraine. Like Where is {FormName}[?] Who authored {FormName}[?] {FormName} is published in French[?] (taken from https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-patterns) we could do: ✑ Find contacts in {CityOrCountry}. ✑ Who do I know in {CityOrCountry}[?] ✑ Search for contacts in {CityOrCountry}[?]. So, to me a pattern is a Solution (A)

    2. S

       STH

       2022-09-20

       Selected A12 upvotes

       According to MS learn, answer should be yes (A) https://learn.microsoft.com/en-us/training/modules/create-language-understanding-app/5-use-patterns-to-differentiate-similar-utterances This is a FindContact intent with a location entity pattern

    3. A

       ap1234pa

       2023-01-18

       Selected A3 upvotes

       Adding a new pattern to existing findContact() intent will help

    4. A

       anto69

       2024-06-08

       Selected A3 upvotes

       ChatGPT says not enough, Copilot says yes. I stay with Copilot

23. Question 23 of 25

    You are building a Language Understanding model for an e-commerce platform. You need to construct an entity to capture billing addresses. Which entity type should you use for the billing address?

    • Amachine learned
    • BRegex
    • CgeographyV2
    • DPattern.any
    • Elist

    Show answer

    Correct answer: A

    How others answered

    • A82%

    Explanation

    My guess is A. An ML entity can be composed of smaller sub-entities, each of which can have its own properties. For example, Address could have the following structure: Address: 4567 Main Street, NY, 98052, USA Building Number: 4567 Street Name: Main Street State: NY Zip Code: 98052 Country: USA

    Adapted from community discussion by ExamPrep2021 · 2021-06-08 · 39 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 23 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. E

       ExamPrep2021

       2021-06-08

       39 upvotes

       My guess is A. An ML entity can be composed of smaller sub-entities, each of which can have its own properties. For example, Address could have the following structure: Address: 4567 Main Street, NY, 98052, USA Building Number: 4567 Street Name: Main Street State: NY Zip Code: 98052 Country: USA

    2. A

       azurelearner666

       2021-06-30

       10 upvotes

       Right! (the correct response is A, Machine Learned) See https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-entity-types It is a Machine Learned Entity (check ML Entity with Structure in the link, as it is an Address example… )

    3. O

       Omobonike

       2021-06-03

       7 upvotes

       I think the answer is geographyv2 because it searches specifically for places.

    4. D

       Deepusuraj

       2022-02-12

       Selected A4 upvotes

       ML Entity with Structure An ML entity can be composed of smaller sub-entities, each of which can have its own properties. For example, an Address entity could have the following structure: Address: 4567 Main Street, NY, 98052, USA Building Number: 4567 Street Name: Main Street State: NY Zip Code: 98052 Country: USA

24. Question 24 of 25

    You are building a retail kiosk system that will use a custom neural voice. You acquire audio samples and consent from the voice talent. You need to create a voice talent profile. What should you upload to the profile?

    • Aa .zip file that contains 10-second .wav files and the associated transcripts as .txt files
    • Ba five-minute .flac audio file and the associated transcript as a .txt file
    • Ca .wav or .mp3 file of the voice talent consenting to the creation of a synthetic version of their voice
    • Da five-minute .wav or .mp3 file of the voice talent describing the kiosk system

    Show answer

    Correct answer: C

    How others answered

    • C76%
    • A24%

    Explanation

    C should be the correct answer instead. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice-talent#add-voice-talent - On the Upload voice talent statement page, follow the instructions to upload the voice talent statement you've recorded beforehand. Make sure the verbal statement was recorded with the same settings, environment, and speaking style as your training data. - Enter the voice talent name and company name. The voice talent name must be the name of the person who recorded the consent statement. The company name must match the company name that was spoken in the recorded statement.

    Adapted from community discussion by zellck · 2023-06-29 · 4 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 24 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. Z

       zellck

       2023-06-29

       Selected C4 upvotes

       C should be the correct answer instead. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice-talent#add-voice-talent - On the Upload voice talent statement page, follow the instructions to upload the voice talent statement you've recorded beforehand. Make sure the verbal statement was recorded with the same settings, environment, and speaking style as your training data. - Enter the voice talent name and company name. The voice talent name must be the name of the person who recorded the consent statement. The company name must match the company name that was spoken in the recorded statement.

    2. [

       [Removed]

       2023-08-13

       Selected C3 upvotes

       I would have choosen A but it's actually C because of https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-custom-voice-talent "A voice talent is an individual or target speaker whose voices are recorded and used to create neural voice models. Before you can train a neural voice, you must submit a recording of the voice talent's consent statement. The voice talent statement is a recording of the voice talent reading a statement that they consent to the usage of their speech data to train a custom voice model. The consent statement is also used to verify that the voice talent is the same person as the speaker in the training data."

    3. E

       evangelist

       2024-02-03

       Selected C3 upvotes

       Based on the Azure AI documentation, the correct option for creating a voice talent profile for a custom neural voice is: C. a .wav or .mp3 file of the voice talent consenting to the creation of a synthetic version of their voice. This is because the documentation specifies the need for a recording of the voice talent's consent statement, acknowledging the use of their voice recordings by a specified company to create and use a synthetic version of their voice

    4. M

       mVic

       2023-05-23

       Selected C4 upvotes

       C is correct, as per below documentation. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-voice-talent

25. Question 25 of 25

    Select 2

    You have an Azure Cognitive Search solution and an enrichment pipeline that performs Sentiment Analysis on social media posts. You need to define a knowledge store that will include the social media posts and the Sentiment Analysis results. Which two fields should you include in the definition? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

    • AstorageContainer
    • BstorageConnectionString
    • Cfiles
    • Dtables
    • Eobjects

    Show answer

    Correct answer: B, E

    How others answered

    • BE64%
    • BD15%

    Only 64% agreed on this answer — treat it as contested rather than settled.

    Explanation

    Typo, BE is the answer. https://learn.microsoft.com/en-us/azure/search/knowledge-store-concept-intro?tabs=portal#knowledge-store-definition A knowledge store is defined inside a skillset definition and it has two components: - A connection string to Azure Storage - Projections that determine whether the knowledge store consists of tables, objects or files. The projections element is an array. You can create multiple sets of table-object-file combinations within one knowledge store.

    Adapted from community discussion by zellck · 2023-06-29 · 19 community upvotes. Third-party contribution; reviewed by our quality filter, not independently verified.

    Supporting references

    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn
    • Microsoft Learn

    View community discussion4

    Candidate context

    Question 25 discussion

    These are quality-filtered excerpts from third-party community discussion. They can be useful reasoning signals, but they are not official answers and have not been independently verified by AI-102 or CertExamHQ.

    1. Z

       zellck

       2023-06-29

       Selected B, E19 upvotes

       Typo, BE is the answer. https://learn.microsoft.com/en-us/azure/search/knowledge-store-concept-intro?tabs=portal#knowledge-store-definition A knowledge store is defined inside a skillset definition and it has two components: - A connection string to Azure Storage - Projections that determine whether the knowledge store consists of tables, objects or files. The projections element is an array. You can create multiple sets of table-object-file combinations within one knowledge store.

    2. Z

       zellck

       2023-06-29

       5 upvotes

       The type of projection you specify in this structure determines the type of storage used by knowledge store, but not its structure. Fields in tables, objects, and files are determined by Shaper skill output if you're creating the knowledge store programmatically, or by the Import data wizard if you're using the portal. - objects project JSON document into Blob storage. The physical representation of an object is a hierarchical JSON structure that represents an enriched document.

    3. H

       halfway

       2022-11-27

       Selected B, E3 upvotes

       storageConnectionString and Tables. The projection types are mutually exclusive. There is no need to have 2 projections in this scenario.

    4. P

       propanther

       2023-10-28

       1 upvote

       Behind the scenes, table projection stored data in Azure Table Storage, where scalability and performance of the storage becomes vital to deal with when unstructured data like social media post is stored. By design, table storages should not be used to store objects which can be of very big in size and can be extremely difficult to apply search pattern on. Check this out: The scalability and performance targets listed here are high-end targets, but are achievable. In all cases, the request rate and bandwidth achieved by your storage account depends upon the size of objects stored, the access patterns utilized, and the type of workload your application performs. ref: https://learn.microsoft.com/en-us/azure/storage/tables/scalability-targets

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AI-102 practice, question 1 of 25