AI-102 Question 420
Select 4You are tasked with implementing a custom Azure AI Search skill to extract structured data from scanned invoices and store it in an Azure Cognitive Search index. You decide to use a prebuilt document intelligence model from Azure Form Recognizer. Which of the following steps are required to successfully integrate the solution?
- A
Create a Form Recognizer resource and configure it with the necessary endpoint and API key.
- B
Write a custom skill that sends the invoice data to the Form Recognizer API and processes the response.
- C
Configure a skillset in Azure Cognitive Search and include the custom skill to call Form Recognizer.
- D
Deploy the Form Recognizer model as a containerized solution for offline skill execution.
- E
Ensure the data extraction output from the custom skill is mapped to the search index schema.
Show answer and explanation
Correct answers: A, B, C, E
Explanation
To implement a document intelligence model as a custom Azure AI Search skill, you need to set up a Form Recognizer resource, create a custom skill to interact with its API, and configure a skillset in Azure Cognitive Search to include this custom skill. Additionally, the extracted data must be mapped appropriately to the search index schema for effective storage and querying. Deploying Form Recognizer as a container is not required for this use case since the managed cloud service provides the necessary functionality.
- A. Correct.
Correct. A Form Recognizer resource is required to access the API and utilize the document intelligence model.
- B. Correct.
Correct. A custom skill is needed to interact with the Form Recognizer API to process the invoices.
- C. Correct.
Correct. A skillset in Azure Cognitive Search organizes how skills (such as the custom Form Recognizer skill) are executed.
- D. Incorrect.
Incorrect. Deploying Form Recognizer as a containerized solution is unnecessary unless you have specific offline requirements. For this scenario, the managed cloud version is sufficient.
- E. Correct.
Correct. Mapping the extracted data to the search index schema ensures it is properly stored and searchable in the Azure Cognitive Search index.