v5.1.1

Added

• Expanded language support for voice and text interactions. Also included support for Neural voices for Lex language locales. See supported languages.
• Expanded config.json to support LexV2BotLocaleIds parameter.
• Updated LexV2BotLocaleIds parameter in CloudFormation template to include link to supported languages.
• Updated Multi Language Support readme and added supported languages section.
• Updated ENABLE_MULTI_LANGUAGE_SUPPORT setting in Settings readme with link to supported languages.

Fixed

• Fixed Kendra Webcrawler data source sync issue by adding support to check for Kendra webcrawler data source {status} before initiating sync
• Fixed issue where the Kendra Webcrawler data source {settings} page in Kendra console was resulting in a blank page - by updating configuraton parameters for data source create and update steps

v5.1.0

Added

• Tags to questions in Content Designer and ability to create reports in Kibana.
• Integration with Genesys call center platform.
• Client Filtering with Session Attributes (i.e., Support to allow the same set of questions to be answered differently based on a session attribute).
• Intelligent redaction of Personally Identifiable Information in logs with Amazon Comprehend.
• A QnABot client (e.g. a Connect contact flow) can now optionally provide a value for session attribute, qnabotUserId. When this session attribute is set, QnABot tracks user activity based on the provided value. If not set, QnABot continues to track user activity based on the request userId (LexV1) or sessionId (LexV2). NOTE: qnabotUserId value is not used when user authentication using JWTs is enabled - in this case users are securely identified and verified from the JWT.
• Support for pre and post processing AWS Lambda Hooks.
• Setting that determines whether Amazon Kendra responses are abbreviated when sent via SSML (ALT_SEARCH_KENDRA_ABBREVIATE_MESSAGE_FOR_SSML)
• Setting that determines the types of responses that Amazon Kendra returns (ALT_SEARCH_KENDRA_RESPONSE_TYPES: ANSWER, DOCUMENT, QUESTION_ANSWER)

Fixed

• Test tab in Content Designer to show same results as the web client when using Kendra FAQ.
• Broken link in documentation for downloading CloudFormation template.
• Integration with Slack on Amazon LexV2 bots.
• QnABot will set the sessionAttribute from CONNECT_NEXT_PROMPT_VARNAME to an empty string if QnABot is in a response bot in a voice channel. This will prevent QnABot from saying the next prompt in the middle of a response bot flow.
• Kendra FAQ sync where export Lambda was missing the Layer containing qnabot log.
• Bug with response bots with Alexa where QnABot was filling in a malformed reprompt.text in the response.
• Excel import improvements and bug fixes.

Changed

• Bot routing capability to have multiple-bot architecture (e.g., General bot routing questions to specialty bots).
• The built-in Amazon Kendra “web page indexer” with the new Kendra Web Crawler Datasource.

v5.0.1

Added

• Architecture diagram and more details on README.md

Fixed

• Regex Redaction in CloudWatch and Amazon OpenSearch Service.
• Outdated NPM dependencies via Dependabot alerts and npm audit tool.

Changed

• License from Amazon Software License to Apache License 2

Refer to changelog for more information.

v5.0.0

Added

• AWS QnABot release as an AWS Solution Implementation
  • AWS QnABot now has a landing page and Implementation Guide
• Minor changes in IAM scopes to enhance security posture.
• Bug fixes related to multiple language support
• Amazon Connect integration wizard now uses Amazon LexV2 bots in all Regions (no longer requires the 'LexV2 Only' setting to be true.)

Refer to changelog for more information.

4.7.3

• The QnABot fulfillment Lambda function can now be configured for provisioned concurrency to further improve query response times after periods of inactivity
• Bug fix for proper invocation of ESWarmer lambda
• Bug fix to resolve sporadic API Compression CloudFormation exception

4.7.2

• Bug fix "TypeError: AWS.LexRuntimeV2 is not a constructor" when using Lex V2 based Elicit Response Bots.
• Bug fix "Cannot read property 'buttons' of undefined" when no buttons specified in response card.
• Bug fix Protect against TypeError exception while processing fallback intent case for an invalid response provided to a LexV2 Response Bot.

4.7.1

4.7.1 provides performance improvements and component upgrades

• Amazon Elasticsearch version 7.10 is now utilized.
• Encrypted Elasticsearch (production) instance types now use m6g.large.elasticsearch for improved price/performance/memory.
• The QnABot fulfillment Lambda function has been optimized to reduce query response times and variability,
  especially after periods of inactivity.
• LexV2 built-in Elicit Response bots have been added.
• Custom settings can now be exported and imported from the Content Designer Settings page.
• Bug fix when ES_SCORE_ANSWER_FIELD is set to true. Prior to this fix, answer fields were not
  utilized fully in Elasticsearch queries.

4.7.0

• QnABot now supports LexV2 with voice interaction in multiple languages.
  • Two installation/update modes are now available:
    • (i) LexV1 + LexV2 (default, recommended for most AWS regions.
    • (ii) LexV2-only (currently recommended for AWS regions where LexV1 is not available).
  • LexV2 locales are specified via a new CloudFormation parameter
    • The default locales are US English, US Spanish and Canadian French.
• The QnABot web client now uses LexV2 and supports dynamic bot locale selection from a new title bar menu.
• Custom LexV2 Elicit Response bots are now supported. The built-in response bots still use LexV1 and are
  available only when QnABot is installed in LexV1+LexV2 mode.
• CloudFormation deployment is now available for Canada/Montreal region (LexV2-only mode).
• Amazon Connect integration in the Canada/Montreal region supports multiple voice languages using LexV2.
• The Content Designer 'Test All' feature now uses LexV2.
• Content Designer's "Rebuild Lex Bot" feature now rebuilds both LexV2 and LexV1 bots
• Non-English LexV2 bot locales are automatically generated with sample utterances translated from English questions using Amazon Translate.
• Content Designer's Import feature now supports Excel spreadsheets as well as the existing JSON format.
• QnABot's Elasticsearch cache is now automatically kept warm to improve query time consistency.
• Negative feedback (thumbs down) messages can now generate notifications (text, email, etc.) using Amazon SNS.

4.6.0

• Kendra integration is now fully automated during install or update when the new default Kendra Index Id parameter is provided.
• Kendra custom no_hits item required in earlier releases is no longer required to enable Kendra Fallback and should be removed, configurable confidence thresholds now available for filtering Kendra results.
• Kibana dashboard now shows additional detail on questions answered via Kendra FAQ and Kendra Fallback.
• Standard markdown is now automatically converted to Slack markdown when using Slack, Kibana dashboard logs and metrics retention period is now configurable during install or update, Lambda runtime upgraded to Node.js 12.x.
• Two new settings have been added
  ALT_SEARCH_KENDRA_FALLBACK_CONFIDENCE_SCORE - Answers will only be returned that or at or above the specified confidence level when using Kendra Fallback
  ALT_SEARCH_KENDRA_FAQ_CONFIDENCE_SCORE - Synchronized FAQ questions will only be matched to an ElasticSearch question if the Kendra FAQ confidence level is at or above the specified confidence level.

4.5.1

4.5.1

Defect fixes:

• Fix for incorrect Thumbs Up / Thumbs Down processing in 4.5.0.
• Fix for multi-language support when manually switching languages in 4.5.0.
• Improve formatting of markdown responses from Kendra ANSWER responses.