Skip to content

Releases: aws-samples/amazon-transcribe-post-call-analytics

v0.7.3

11 Oct 23:23
Compare
Choose a tag to compare

[0.7.3] - 2023-10-11

Fixed

  • #187 - Got error message in PostCallAnalyticsWorkflow step function
  • #189 - Uploading some MP3 files fails to trigger workflow - files remain unprocessed
  • #190 - Transcription search web UI opens with an error page after deployment
  • #199 - BedrockBoto3 stack update failure when lambda function is replaced during update

v0.7.2

03 Oct 16:10
Compare
Choose a tag to compare

[0.7.2] - 2023-10-03

Fixed

  • Enable Bedrock GA by default for call summarization and chat/generative query
  • Prompt updates for Bedrock GA release (formatting, multiple prompts per call)
  • Updated GenerativeAI README and main README with model access details
  • Links to the LLM Parameter Store Prompts from the CloudFormation Output
  • Adaptive retries for SSM GetParameter and InvokeModel to prevent throttling errors

v0.7.1

05 Sep 15:55
Compare
Choose a tag to compare

[0.7.1] - 2023-09-05

Fixed

  • Stack deploy failure (unable to create secret in SecretsManager) when SummarizationLLMThirdPartyApiKey is left empty. Changed default value to 'undefined'.

[0.7.0] - 2023-09-01

Added

  • Bedrock summarization support
  • Support for multiple summarization prompts
  • Bedrock and Anthropic chat/generative query support
  • Additional configurable columns in call list
  • Migrate 3P LLM API Key to Secrets Manager

v0.7.0

01 Sep 22:25
Compare
Choose a tag to compare

[0.7.0] - 2023-09-01

Added

  • Bedrock summarization support
  • Support for multiple summarization prompts
  • Bedrock and Anthropic chat/generative query support
  • Additional configurable columns in call list
  • Migrate 3P LLM API Key to Secrets Manager

v0.6.0

12 Jun 20:36
Compare
Choose a tag to compare

[0.6.0] - 2023-06-12

Added

  • Experimental generative transcript summarization provides a short paragraph with a synopsis of each completed call; use the built-in summarization model with runs on Amazon Sagemaker, or use Anthropic's Claude API with 100K token limit (eliminating transcript length limitations), or experiment with custom language models or APIs of your choice. See Transcript Summarization
  • User Interface updated to use the Cloudscape framework with improved functionality and appearance.

What's Changed

  • Cloudscape UI + Generative AI call summarization by @chrislott in #169
  • fix NRE & bug with splitting agent/ivr segments by @chrislott in #156

Full Changelog: v0.5.2...v0.6.0

v0.5.2

25 May 13:22
Compare
Choose a tag to compare

[0.5.2] - 2023-05-25

Fixed

  • Update Lambda runtime from node.js 12.x to 14.x (12.x is deprecated)

v0.5.1

15 May 17:32
Compare
Choose a tag to compare

[0.5.1] - 2023-05-15

Fixed

  • Cloudformation stack failing due to recent S3 bucket changes on ACLs #163 #165

v0.5.0

23 Mar 19:09
Compare
Choose a tag to compare

[0.5.0] - 2023-03-23

Added

  • Option to deploy Advanced reporting and analytics with Amazon QuickSight
  • Supports Transcribe Custom Language Models (CLM)

v0.4.0

28 Nov 03:44
Compare
Choose a tag to compare

[0.4.0] - 2022-11-27

Added

v0.3.4

09 Nov 23:47
Compare
Choose a tag to compare

[0.3.4] - 2022-11-9

Added

  • Additional processing for Genesys CTR telephony files. See Integration with Telephony CTR Files
    • Handling the same agent being on the call multiple times
    • Removing entities from lines tagged as being from the IVR
    • Extraction of header-level metadata from Genesys in a new Telephony results header block

Fixed

  • lag on Call Detail UI page reload for long calls
  • refactored code to incorporate witch lambda layer source in the repo instead of downloading prebuild zip file