Releases: aws-samples/amazon-transcribe-post-call-analytics
Releases · aws-samples/amazon-transcribe-post-call-analytics
v0.7.17
v0.7.16
v0.7.15
[0.7.15] - 2025-07-03
Added
- Contributed feature for synthesizing test calls - PR #278
- Additional contributed solution documentation intended to facilitate developer onboarding #282
Fixed
- #300 - glue table definitions broken
- Update Lambda Runtime to NodeJS 22.x
- #299 - handle comprehend detect_sentiment api has limits of input size of 5kb
- #310 - Change Default Model from Nova-Lite to Nova-Pro for GenAI Queries and Summarization in PCA CFN Templates
- #305 - Extend query window to 5 years and modify sample file timestamps
- misc dependabot PRs
v0.7.13
[0.7.13] - 2025-02-21
Fixed
- Remove Boto3 layer from all Lambda functions as Bedrock features are available in the base Boto package deployed in Lambda
- Updated all Lambda functions to Python 3.13 runtime
[0.7.12] - 2025-02-21
Added
- Added support for Amazon Nova models (amazon.nova-micro-v1:0, amazon.nova-lite-v1:0, amazon.nova-pro-v1:0) - PR #295
- Updated Anthropic Claude models to the latest 3.5 versions (anthropic.claude-3-5-haiku-20241022-v1:0, anthropic.claude-3-5-sonnet-20241022-v2:0) - PR #295
- Removed older versions of Amazon Titan and Anthropic Claude models (amazon.titan-text-express-v1, anthropic.claude-v1, anthropic.claude-instant-v1, anthropic.claude-v2) - PR #295
- Refactored Bedrock calls to use the Converse API eliminating the need for custom model specific payloads - PR #295
- Refactored all model invocation to use Inference Profiles. This is required for Nova models. It is also applied to Anthropic models for consistency and improved scalability. - PR #295
- Added adaptive retry configuration to Bedrock api calls to add some tolerance for quota throttling exceptions (at the expense of latency) - PR #295
Fixed
v0.7.12
[0.7.12] - 2025-02-21
Added
- Added support for Amazon Nova models (amazon.nova-micro-v1:0, amazon.nova-lite-v1:0, amazon.nova-pro-v1:0) - PR #295
- Updated Anthropic Claude models to the latest 3.5 versions (anthropic.claude-3-5-haiku-20241022-v1:0, anthropic.claude-3-5-sonnet-20241022-v2:0) - PR #295
- Removed older versions of Amazon Titan and Anthropic Claude models (amazon.titan-text-express-v1, anthropic.claude-v1, anthropic.claude-instant-v1, anthropic.claude-v2) - PR #295
- Refactored Bedrock calls to use the Converse API eliminating the need for custom model specific payloads - PR #295
- Refactored all model invocation to use Inference Profiles. This is required for Nova models. It is also applied to Anthropic models for consistency and improved scalability. - PR #295
- Added adaptive retry configuration to Bedrock api calls to add some tolerance for quota throttling exceptions (at the expense of latency) - PR #295
Fixed
v0.7.11
[0.7.11] - 2024-10-09
Added
- Disable checking if Bedrock models are enabled (default is set to true i.e check it which is the right setting for most cases).
- Allow users to sign-up for access to Web UI when AllowedSignUpEmailDomain is populated (disable if left blank. enabled for all domains if * is entered).
V0.7.10
[0.7.10] - 2024-08-12
Added
- Allow Kendra Capacity to be specified (Enterprise Edition only) PR #250
- Make deployment of the PCA UI stack conditional (i.e. deploy server only) #264
Fixed
- Fix: When choosing Kendra option, PCA fails to deploy in new AWS accounts due to CodeCommit deprecation for new accounts. #265
- NOTE you will be asked to create a new password for the MediaSearch Finder app when you update an existing PCA stack with Kendra Transcript search enabled.
- Modified the LLM prompt for Titan Express - remove the Human and Assistant strings when Titan Express is selected. PR #244
- Dependabot PRs.