Amazon Kendra

Managed Connection - Amazon Kendra

Amazon Kendra (https://aws.amazon.com/kendra/) is a highly accurate and easy to use enterprise search service that is powered by machine learning. Kendra delivers powerful natural language search capabilities. It is also a fully managed Amazon Service.

Please follow the link below to learn more and get started with Amazon Kendra https://www.youtube.com/watch?v=ow5DFGICHoI

Configuration on Amazon Kendra console

(1) Create Index

An index provides search results for documents and frequently asked questions (FAQ) that it has indexed. An index can contain documents that are indexed from a data source, documents that are added directly to the index, and FAQs.

(2) Create Data Source

A data source is a location, such as an Amazon Simple Storage Service (Amazon S3) bucket, where you store the documents for indexing. Data sources can be automatically synchronized with an Amazon Kendra index so that new, updated, or deleted documents in the source repositories are included in searches. Supported data sources are:

• Amazon S3 buckets

• Amazon RDS for MySQL and Amazon RDS for PostgreSQL databases

• Microsoft OneDrive for Business

• Microsoft SharePoint Online

• Salesforce sites

• ServiceNow instances

Supported document formats are plain text, Microsoft Word, Microsoft PowerPoint, HTML, and PDF

ixHello

ixHello platform allows for the rapid integration of Amazon Kendra to various voice channels such as, Alexa, Lex, Google Assistant and more.

To Configure Amazon Kendra, browse to: Integration > Connect System and press Connection Gallery

Scroll down to Amazon Kendra and press Connect.

The Amazon Kendra Instance Configuration Screen opens. Enter the Name for the service, Consumer Key (Secret Access Key), AWS Region, and Consumer Secret (Secret Access Key). You can get your required AWS Credentials from the AWS IAM console. Visit Video: How to get Amazon (AWS) Key and Secret Make sure the AWS account has the required permissions to access Amazon Kendra. When finished, press Validate and Save Settings.

Once you have saved settings you need to create a new Custom App. Browse to: Apps > Custom Apps and press New Custom App.

Add the details and press Save

The new App will appear under the Apps > Custom Apps page. Click on the App Name to open it.

Create a data source by navigating to the Data Sources tab and press Create New Data Source. Now you can create methods for the Kendra.

As of the publication date of this document, ixHello supports following Amazon Kendra methods,

1. ListIndices

2. Query

Method: ListIndices

Parameters: Not required

It returns a list of indexes that are already created in Amazon Kendra.

Below is a sample response format – You should get response like this.

[ { "CreatedAt": number, "Edition": "string", "Id": "string", "Name": "string", "Status": "string", "UpdatedAt":number } ]

Method: Query

Parameters:

Parameter	Sample Value	Info
IndexId	5D5C08F0-98B1-443F-8E9E-A1F67D551514	You can select from dropdown list of available indexes.
Query Text	Any search text	This is the query that you want to search.

Response: Below is a response syntax and you should get response like this. In sample shown below, “string”, number etc should be replaced by the actual value returned by Kendra.

{ "FacetResults": [ { "DocumentAttributeKey": "string", "DocumentAttributeValueCountPairs": [ { "Count": number, "DocumentAttributeValue": { "DateValue": number, "LongValue": number, "StringListValue": [ "string" ], "StringValue": "string" } } ] } ], "QueryId": "string", "ResultItems": [ { "AdditionalAttributes": [ { "Key": "string", "Value": { "TextWithHighlightsValue": { "Highlights": [ { "BeginOffset": number, "EndOffset": number, "TopAnswer": boolean } ], "Text": "string" } }, "ValueType": "string" } ], "DocumentAttributes": [ { "Key": "string", "Value": { "DateValue": number, "LongValue": number, "StringListValue": [ "string" ], "StringValue": "string" } } ], "DocumentExcerpt": { "Highlights": [ { "BeginOffset": number, "EndOffset": number, "TopAnswer": boolean } ], "Text": "string" }, "DocumentId": "string", "DocumentTitle": { "Highlights": [ { "BeginOffset": number, "EndOffset": number, "TopAnswer": boolean } ], "Text": "string" }, "DocumentURI": "string", "Id": "string", "Type": "string" } ], "TotalNumberOfResults": number }