Skip to content

Releases: aws-solutions/generative-ai-application-builder-on-aws

v1.3.1

27 Feb 21:35
a6b154f
Compare
Choose a tag to compare

Fixed

  • Add missing IAM action required to provision users for use cases when deploying through deployment dashboard

v1.3.0

22 Feb 22:17
8d86a2c
Compare
Choose a tag to compare

Added

  • Support for SageMaker as an LLM provider through SageMaker inference endpoints.
  • Ability to deploy both the deployment dashboard and use cases within a VPC, including bringing an existing VPC and allowing the solution to deploy one.
  • Option to return and display the source documents that were referenced when generating a response in RAG use cases.
  • New model-info API in the deployment dashboard stack which can retrieve available providers, models, and model info. Default parameters are now stored for each model and provider combination and are used to pre-populate values in the wizard.

Changed

  • Refactoring of UI components in the deployment dashboard.
  • Switch to poetry for Python package management, replacing requirements.txt files.
  • Updates to Node and Python package versions.

v1.2.3

06 Feb 18:34
4bb6276
Compare
Choose a tag to compare

Fixed

  • Fix AWS IAM policy that causes use case deployments to fail when creating, updating or deleting from the deployment dashboard.

v1.2.2

11 Jan 17:34
b2dac0f
Compare
Choose a tag to compare

Fixed

  • Pinned langchain-core and langchain-community versions, fixing a test failure caused by unpinned versions in the langchain packages dependencies
  • Removed a race condition causing intermittent failures to deploy the UI infrastructure

Security

  • Updated Node package versions to resolve security vulnerabilities

v1.2.1

21 Dec 19:32
74e46a1
Compare
Choose a tag to compare

Fixed

  • Unit tests failure due to a change in the underlying anthropic library.

v1.2.0

18 Dec 21:19
e350e95
Compare
Choose a tag to compare

Added

  • Support for Amazon Titan Text Lite, Anthropic Claude v2.1, Cohere Command models, and Meta Llama 2 Chat models

Changed

  • Increase the cap on the max number of docs retrieved in the Amazon Kendra retriever (for RAG use cases) from 5 to 100, to match the API limit

Fixed

  • Fix typo in UI deployment instructions (#26)
  • Fix bug causing failures with dictionary type advanced model parameters
  • Fixed bug causing erroneous error messages to appear to user in long running conversations

Security

  • Updated Python and Node package versions to resolve security vulnerabilities

v1.1.1

16 Nov 20:08
f1a24b9
Compare
Choose a tag to compare

Fixed

  • Remove NodeJS 16 from supported runtimes, which was not supported

Security

  • Updated Python and Node package versions to resolve security vulnerabilities

v1.1.0

02 Nov 17:03
930dca5
Compare
Choose a tag to compare

Added

  • Markdown rendering in Chat UI LLM responses

Updated

  • Increased prompt and chat input limits to 2000 and 2500 characters respectively
  • Updated package versions to resolve security vulnerabilities

v1.0.1

26 Oct 14:29
7573a29
Compare
Choose a tag to compare

Updated

  • Updated package versions to resolve security vulnerabilities.

v1.0.0

16 Oct 18:09
a32520d
Compare
Choose a tag to compare

Added

  • Initial Release