Create a custom question and answer chatbot

Publication date: September 2021 (last update: November 2024)

The QnABot on AWS solution is a generative AI-enabled multi-channel, multi-language conversational chatbot that responds to your customer’s questions, answers, and feedback. It is built on Amazon Lex, Amazon Polly, Amazon OpenSearch Service, Amazon Translate, Amazon Comprehend, Amazon Kendra, and Amazon Bedrock. This solution helps you to quickly deploy self-service conversational artificial intelligence (AI) on multiple channels, including your contact centers, websites, social media channels, SMS text messaging, or Amazon Alexa without programming.

This implementation guide provides an overview of the QnABot on AWS solution, its reference architecture and components, considerations for planning the deployment, configuration steps for deploying the solution to the Amazon Web Services (AWS) Cloud. It also includes a user’s guide with prescriptive guidance for using QnABot on AWS.

Use this navigation table to quickly find answers to these questions:

If you want to . . .	Read . . .
Know the cost for running this solution	Cost
Understand the security considerations for this solution	Security
Know how to plan for quotas for this solution	Quotas
Know which AWS Regions are supported for this solution	Supported AWS Regions
View or download the AWS CloudFormation template included in this solution to automatically deploy the infrastructure resources (the “stack”) for this solution	AWS CloudFormation template
Access the source code and optionally use the AWS Cloud Development Kit (AWS CDK) (AWS CDK) to deploy the solution	GitHub repository