Exam AI-102 All Questions

View all questions & answers for the AI-102 exam

Exam AI-102 topic 6 question 1 discussion

Actual exam question from Microsoft's AI-102

Question #: 1
Topic #: 9

DRAG DROP -
You are developing the smart e-commerce project.
You need to design the skillset to include the contents of PDFs in searches.
How should you complete the skillset design diagram? To answer, drag the appropriate services to the correct stages. Each service 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:

Show Suggested Answer

Suggested Answer:

Box 1: Azure Blob storage -
At the start of the pipeline, you have unstructured text or non-text content (such as images, scanned documents, or JPEG files). Data must exist in an Azure data storage service that can be accessed by an indexer.

Box 2: Computer Vision API -
Scenario: Provide users with the ability to search insight gained from the images, manuals, and videos associated with the products.
The Computer Vision Read API is Azure's latest OCR technology (learn what's new) that extracts printed text (in several languages), handwritten text (English only), digits, and currency symbols from images and multi-page PDF documents.

Box 3: Translator API -
Scenario: Product descriptions, transcripts, and alt text must be available in English, Spanish, and Portuguese.

Box 4: Azure Files -
Scenario: Store all raw insight data that was generated, so the data can be processed later.
Incorrect Answers:
The custom vision API from Microsoft Azure learns to recognize specific content in imagery and becomes smarter with training and time.
Reference:
https://docs.microsoft.com/en-us/azure/search/cognitive-search-concept-intro https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocr

by Sharks82 at Sept. 10, 2022, 12:37 a.m.

Comments

Submit Cancel

M25

Highly Voted 1 year, 9 months ago

Source [Azure Blob Storage] https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-intro Import is the first step. Here, the indexer connects to a data source and pulls content (documents) into the search service. Azure Blob Storage is the most common resource used in AI enrichment scenarios, but any supported data source can provide content. https://learn.microsoft.com/en-us/azure/search/search-indexer-overview#document-cracking • When the document is a file with embedded images, such as a PDF, the indexer extracts text, images, and metadata. Indexers can open files from Azure Blob Storage, Azure Data Lake Storage Gen2, and SharePoint.

upvoted 12 times

M25

1 year, 9 months ago

--> Cracking [Computer Vision API] --> Preparation [Translator API] https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-intro Built-in skills are based on the Azure AI services APIs: Azure AIComputer Vision and Language Service. • Image processing skills include Optical Character Recognition (OCR) and identification of visual features, such as facial detection, image interpretation, image recognition (famous people and landmarks), or attributes like image orientation. These skills create text representations of image content for full text search in Azure Cognitive Search. • Machine translation is provided by the Text Translation skill, often paired with language detection for multi-language solutions.

upvoted 11 times

M25

1 year, 9 months ago

--> Destination [Azure Blob Storage] https://learn.microsoft.com/en-us/azure/search/cognitive-search-concept-intro • Enriched content is generated during skillset execution, and is temporary unless you save it. You can enable an enrichment cache [Physically, the cache is stored in a blob container in your Azure Storage account, one per indexer.] to persist cracked documents and skill outputs for subsequent reuse during future skillset executions. Exploration is the last step. Output is always a search index that you can query from a client app. Output can optionally be a knowledge store consisting of blobs and tables in Azure Storage that are accessed through data exploration tools or downstream processes. If you're creating a knowledge store, projections determine the data path for enriched content. The same enriched content can appear in both indexes and knowledge stores.

upvoted 18 times

rdemontis

1 year, 7 months ago

thanks for explanation

upvoted 3 times

...

Sharks82

Highly Voted 2 years, 9 months ago

Given answer is correct

upvoted 7 times

...

tech_rum

Most Recent 1 month, 2 weeks ago

In this case study You are not just storing documents. You have requirements like: - Real-time stock updates into the search index. - Multilingual structured data (English, Spanish, Portuguese). - Enriched search over product descriptions, images, videos, etc. ➡ Because of the "smart e-commerce" project's structured metadata and real-time stock update needs, Cosmos DB is the better choice as the destination.

upvoted 1 times

...

syupwsh

3 months, 2 weeks ago

Azure Blob Storage is CORRECT because it is a scalable object storage solution for unstructured data, including documents like PDFs. It integrates seamlessly with Azure Cognitive Search, allowing you to store and manage the documents that need to be processed and indexed for search capabilities. This enables the contents of the PDFs to be included in search results. Computer Vision API is CORRECT because it can be used to extract text and other information from images, including PDFs. The "Cracking" step typically involves extracting readable text from documents, and the Computer Vision API's OCR (Optical Character Recognition) capabilities are specifically designed for this purpose.

upvoted 2 times

syupwsh

3 months, 2 weeks ago

Translator API is CORRECT because it is designed to translate text between different languages. In this case, after extracting and preparing the text, you need to ensure that product descriptions, transcripts, and alt text are available different languages. The Translator API can handle the translation of text into different languages, ensuring multilingual support. Azure Files is CORRECT because, in the context of a knowledge store, the final step involves storing the output data. Azure Files provides managed file shares that can be used to store the processed and enriched data, making it accessible for data exploration tools or downstream processes. This ensures that the enriched content is available in a structured format for further analysis or querying

upvoted 1 times

...

GoldBear

11 months, 3 weeks ago

This link has a diagram with the flow chart. https://learn.microsoft.com/en-us/azure/architecture/solution-ideas/articles/cognitive-search-with-skillsets

upvoted 3 times

...

rookiee1111

11 months, 3 weeks ago

Given the fact that the enriched data needs to be used for further processing, Azure blob storage make sense, as it will support any file format, and is scalable and will able to support multiple processing services.

upvoted 1 times

rookiee1111

11 months, 3 weeks ago

as destination

upvoted 1 times

...