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

• Fixed: Only one PCA stack may be sucessfully deployed in a given account/region due to fixed SSM parameter names - PR #291, #293
• Fixed: Current publish.sh does not work with ARM chipsets such as the Apple M series. Set x86_64 arch for local build - PR #288

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

• Fixed: Only one PCA stack may be sucessfully deployed in a given account/region due to fixed SSM parameter names - PR #291, #293
• Fixed: Current publish.sh does not work with ARM chipsets such as the Apple M series. Set x86_64 arch for local build - PR #288

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.

v0.7.9

[0.7.9] - 2024-05-24

Added

• Support for Anthropic Claude Haiku and Sonnet models to perform call summarization and queries.
• Upgraded Python runtime to 3.11 and NodeJS to version 18.x

v0.7.8

[0.7.8] - 2024-03-29

• Fix an issue with job status indicator (step function workflow) inserting duplicate entries into DynamoDB.
• Fix regression in the mediasearch finder to re-enable hyperlink to PCA call detail page

v0.7.7

[0.7.7] - 2024-03-06

Added

• Fix #245 TranscriptKendraSearch page fails to build / load after deployment

v0.7.6

[0.7.6] - 2024-02-16

Added

• PCA UI now shows the status of the step function workflow for each call.
• Added support for the new Transcribe Call Analytics generative call summarization option.

Fixed

• Dependabot updates for PCA
• #234 Fix exception for files that contain no speech segments.
• Fix input bucket trigger to not create a DynamoDB record for metadata files.
• Updated NodeJS to v16.
• Fix bug when deploying with Amazon Titan Text Express.

v0.7.5

[0.7.5] - 2024-01-17

Added

• Support for larger prompts by storing LLMPromptSummaryTemplate in S3 rather than SSM. By default, the CF template will migrate existing SSM prompts to DynamoDB.

Fixed

• #125 Updated the pca-aws-sf-bulk-queue-space.py function to correctly count jobs based on IN_PROGRESS as well as QUEUED
• #224 Updated the pca-aws-sf-bulk-queue-space.py function to correctly count both Transcribe and Transcribe Call Analytics (vs just Transcribe).

v0.7.4

[0.7.4] - 2023-12-15

Added

• Drag/drop upload from call list page
• Refresh call summary from call details page

Fixed

• Accessibility improvements