Releases: awslabs/LISA
Releases · awslabs/LISA
v3.3.2
Bug Fixes
- Resolved issue where invalid schema import was causing create model api calls to fail
- Resolved issue where RAG citations weren't being populated in metadata for non-streaming requests
- Resolved issue where managing in-memory file context wouldn't display success notification and close the modal
Acknowledgements
Full Changelog: v3.3.1...v3.3.2
Contributors
dustins, estohlmann, and bedanley
Assets 2
v3.3.1
Bug Fixes
- Resolved issue where AWS partition was hardcoded in RAG Pipeline
- Added back in LiteLLM environment override support
- Updated Makefile Model and ECR Account Number parsing
Acknowledgements
Full Changelog: v3.3.0...v3.3.1
Contributors
dustins, estohlmann, and bedanley
Assets 2
v3.3.0
2f205bf
This commit was signed with the committer’s verified signature.
estohlmann
Evan Stohlmann
Key Features
RAG ETL Pipeline
- This feature introduces a second RAG ingestion capability for LISA customers. Today, customers can manually upload documents via the chatbot user interface directly into a vector store. With this new ingestion pipeline, customers have a flexible, scalable solution for automating the loading of documents into configured vector stores.
Enhancements
- Implemented a confirmation modal prior to closing the create model wizard, enhancing user control and preventing accidental data loss
- Added functionality allowing users to optionally override auto-generated security groups with custom security groups at deployment time
Acknowledgements
Full Changelog: v3.2.1...v3.3.0
Contributors
dustins, estohlmann, and 2 other contributors
Assets 2
v3.2.1
Bug Fixes
- Resolved issue where subnet wasn't being passed into ec2 instance creation
- Resolved role creation issue when deploying with custom subnets
- Updated docker image to grant permissions on copied in files
Coming Soon
- Version 3.3.0 will include a new RAG ingestion pipeline. This will allow users to configure an S3 bucket and an ingestion trigger. When triggered, these documents will be pre-processed and loaded into the selected vector store.
Acknowledgements
Full Changelog: v3.2.0...v3.2.1
Contributors
estohlmann and bedanley
Assets 2
v3.2.0
Key Features
Enhanced Deployment Configuration
- LISA v3.2.0 introduces a significant update to the configuration file schema, optimizing the deployment process
- The previous single config.yaml file has been replaced with a more flexible two-file system: config-base.yaml and config-custom.yaml
- config-base.yaml now contains default properties, which can be selectively overridden using config-custom.yaml, allowing for greater customization while maintaining a standardized base configuration
- The number of required properties in the config-custom.yaml file has been reduced to 8 items, simplifying the configuration process
- This update enhances the overall flexibility and maintainability of LISA configurations, providing a more robust foundation for future developments and easier customization for end-users
Important Note
- The previous config.yaml file format is no longer compatible with this update
- To facilitate migration, we have developed a utility. Users can execute
npm run migrate-propertiesto automatically convert their existing config.yaml file to the new config-custom.yaml format
Admin UI Configuration Page
- Administrative Control of Chat Components:
- Administrators now have granular control over the activation and deactivation of chat components for all users through the Configuration Page
- This feature allows for dynamic management of user interface elements, enhancing system flexibility and user experience customization
- Items that can be configured include:
- The option to delete session history
- Visibility of message metadata
- Configuration of chat Kwargs
- Customization of prompt templates
- Adjust chat history buffer settings
- Modify the number of RAG documents to be included in the retrieval process (TopK)
- Ability to upload RAG documents
- Ability to upload in-context documents
- System Banner Management:
- The Configuration Page now includes functionality for administrators to manage the system banner
- Administrators can activate, deactivate, and update the content of the system banner
LISA Documentation Site
- We are pleased to announce the launch of the official LISA Documentation site
- This comprehensive resource provides customers with additional guides and extensive information on LISA
- The documentation is also optionally deployable within your environment during LISA deployment
- The team is continuously working to add and expand content available on this site
Enhancements
- Implemented a selection-based interface for instance input, replacing free text entry
- Improved CDK Nag integration across stacks
- Added functionality for administrators to specify block volume size for models, enabling successful deployment of larger models
- Introduced options for administrators to choose between Private or Regional API Gateway endpoints
- Enabled subnet specification within the designated VPC for deployed resources
- Implemented support for headless deployment execution
Bug Fixes
- Resolved issues with Create and Update model alerts to ensure proper display in the modal
- Enhanced error handling for model creation/update processes to cover all potential scenarios
Coming Soon
- Version 3.3.0 will include a new RAG ingestion pipeline. This will allow users to configure an S3 bucket and an ingestion trigger. When triggered, these documents will be pre-processed and loaded into the selected vector store.
Acknowledgements
Full Changelog: v3.1.0...v3.2.0
Contributors
dustins, estohlmann, and bedanley
Assets 2
v3.1.0
Enhancements
Model Management Administration
- Supports customers updating a subset of model properties through the model management user interface (UI) or APIs
- These new model management features are also limited to users in the configured IDP LISA administration group
- This feature prevents customers from having to delete and re-create models every time they want to make changes to available models already deployed in the infrastructure
Other Enhancements
- Updated the chat UI to pull available models from the model management APIs instead of LiteLLM. This will allow the UI to pull all metadata that is stored about a model to properly enable/disable features, current model status is used to ensure users can only interact with
InServicemodels when chatting - Updated default Model Creation values, so that there are fewer fields that should need updating when creating a model through the UI
- Removed the unnecessary fields for ECS config in the properties file. LISA will be able to go and pull the weights with these optional values and if an internet connection is available
- Added the deployed LISA version in the UI profile dropdown so users understand what version of the software they are using
Bug fixes
- Updated naming prefixes if they are populated to prevent potential name clashes, customers can now more easily use prefix resource names with LISA
- Fixed an issue where a hard reload was not pulling in the latest models
- Resolved a deployment issue where the SSM deployment parameter was being retained
- Addressed an issue where users could interact with the chat API if a request was being processed by hitting the
Enterkey
Coming Soon
- Version 3.2.0 will simplify the deployment process by removing all but the key properties required for the deployment, and extracting constants into a separate file as optional items to override. This will make LISA's deployment process a lot easier to understand and manage.
Acknowledgements
Full Changelog: v3.0.1...v3.1.0
Contributors
dustins, petermuller, and estohlmann
Assets 2
v3.0.1
Bug fixes
- Updated our Lambda admin validation to work for no-auth if user has the admin secret token. This applies to model management APIs.
- State machine for create model was not reporting failed status
- Delete state machine could not delete models that weren't stored in LiteLLM DB
Enhancements
- Added units to the create model wizard to help with clarity
- Increased default timeouts to 10 minutes to enable large documentation processing without errors
- Updated ALB and Target group names to be lower cased by default to prevent networking issues
Coming Soon
- 3.1.0 will expand support for model management. Administrators will be able to modify, activate, and deactivate models through the UI or APIs. The following release we will continue to ease deployment steps for customers through a new deployment wizard and updated documentation.
Acknowledgements
Full Changelog: v3.0.0...v3.0.1
Contributors
dustins, petermuller, and estohlmann
Assets 2
v3.0.0
Key Features
Model Management Administration
- Supports customers creating and deleting models through a new model management user interface (UI), or APIs
- Our new Model Management access limits these privileges to users in the configured IDP LISA administration group
- This feature prevents customers from having to re-deploy every time they want to add or remove available models
Note
- These changes will require a redeployment of LISA
- Take note of your configuration file and the models you have previously configured. Upon deployment of LISA 3.0 these models will be deleted and will need to be added back via the new model management APIs or UI
- You can see breaking changes with migrating from 2.0 -> 3.0 in the README
Enhancements
- Updated our documentation to include more details and to account for model management
Coming Soon
- 3.0.1 will expand support for model management. Administrators will be able to modify, activate, and deactivate models through the UI or APIs. The following release we will continue to ease deployment steps for customers through a new deployment wizard and updated documentation.
Acknowledgements
Full Changelog: v2.0.1...v3.0.0
Contributors
dustins, petermuller, and 4 other contributors
Assets 2
v2.0.1
What's Changed
Since the release of v2.0.0 we have made a few bugfixes, added greater model support, and added user experience changes to help reduce the friction in sending chat prompts to a model in the Chat UI. The following are the highlights of changes since v2.0.0.
- Fixed support for self-signed certs across RAG and LISA Serve features
- Added support for vLLM embedding models
- Simplified API Token usage for those users who already use OpenAI clients. README and example notebook have been updated to reflect this change
- Fixed default values in the Chat UI so that TGI models are less likely to throw errors if the model kwargs are not modified before the first prompt
- Various dependency version bumps for security fixes
- Formally deprecated v1 routes. See the README for migrating to the v2 routes
v2.0.0
What's Changed
The LISA v2.0.0 release boasts wider support for the OpenAI spec for users making queries directly against the LISA Serve endpoint. The following is a list of changes that we have introduced since v1.2.0
- LiteLLM added as a model proxy in the REST API container. LiteLLM provides LISA's OpenAI API spec support
- SageMaker Endpoint and Bedrock Foundation Model support added via LiteLLM configuration
- Added support for vLLM containers in addition to the existing support for TGI and TEI containers
- Chat UI updates to support LISA's OpenAI API support
- Documentation updates
- Added example Jupyter notebook showing the OpenAI compatibility with the LISA Serve endpoint
- Deprecated v1 endpoints as they will be removed in a future release