AWS-Kendra

• Kendra is a highly accurate & easy to use enterprise search service that’s powered by machine learning.

• It provides ML-powered search capabilities for all unstructured data customers store in AWS.

• It does not yet support questions for which the answers require cross-document passage aggregation or calculations.

• It supports unstructured & semi-structured data in .html, MS Office (.doc & .ppt), PDF & text formats.

• It supports US English.

• It's machine learning models are regularly retrained & tuned for each customer by analyzing and incorporating end-user search patterns and feedback.

• It is currently available in the following AWS regions: Northern Virginia, Oregon & Ireland.

• It API allows users to build their own connector to send data directly to Kendra from their data source via existing ETL jobs or applications.

• Users just upload a file with their specific terminology & Kendra will use these synonyms to enrich user searches.

• When Users data does not contain a precise answer to a question, Kendra returns a list of the most relevant documents ranked by its deep learning models.