Amazon Kendra has a deep learning model that searches specifically for frequently asked questions (FAQ) that have been ingested as independent question-answer pairs. You can add questions and answers (FAQs) directly to your index using the console or the CreateFaq operation.
The data for the FAQ is contained in a file that you store in an Amazon Simple Storage Service (Amazon S3) bucket. You can use comma-separated values (.csv) files (either Basic without attributes or Custom with attributes) or, JSON files. You can find more details and a programmatic example on how to create FAQs in the documentation site.
FAQs do not have the same update scanning capability provided in the built-in connectors. As such, if you change a FAQ file you will need to delete that file from the index and then re-ingest
For this example we will create a custom CSV file that will allow us to add the attribute _source_uri to the results.
We will create a CSV file with the following content:
_question,_answer,_source_uri Which AWS service has 11 nines of durability?,Amazon S3,https://aws.amazon.com/s3/ What is the AWS Well-Architected Framework?,The AWS Well-Architected Framework enables customers and partners to review their architectures using a consistent approach and provides guidance to improve designs over time.,https://aws.amazon.com/architecture/well-architected/ In what regions is Amazon Kendra available?,"Amazon Kendra is currently available in the following AWS regions: Northern Virginia, Oregon, and Ireland",https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/
You can also download this file here.
After the FAQ is created you will see a message like this: