In InterSystems IRIS 2024.3 and subsequent IRIS versions, the AutoML component is now delivered as a separate Python package that is installed after installation. Unfortunately, some recent versions of Python packages that AutoML relies on have introduced incompatibilities, and can cause failures when training models (TRAIN MODEL statement). If you see an error mentioning "TypeError" and the keyword argument "fit_params" or "sklearn_tags", read on for a quick fix.
We've recently made available a new version of InterSystems IRIS in the Vector Search Early Access Program, featuring a new Approximate Nearest Neighbor index based upon the Hierarchical Navigable Small World (HNSW) indexing algorithm. This addition allows for highly efficient, approximate nearest-neighbor searches over large vector datasets, dramatically improving query performance and scalability.
The Data Platforms team is very pleased to announce the 2021.2 release of InterSystems IRIS Data Platform, InterSystems IRIS for Health and HealthShare Health Connect, which are now Generally Available (GA) to our customers and partners.
InterSystems IRIS Data Platform 2021.2 makes it even easier to develop, deploy and manage augmented applications and business processes that bridge data and application silos. It has many new capabilities including:
Enhancements for application and interface developers, including:
Preview releases are now available for the 2021.2 version of InterSystems IRIS, IRIS for Health, and HealthShare Health Connect.
As this is a preview release, we are eager to learn from your experiences with this new release ahead of its General Availability release next month. Please share your feedback through the Developer Community so we can build a better product together.
InterSystems IRIS Data Platform 2021.2 makes it even easier to develop, deploy and manage augmented applications and business processes that bridge data and application silos. It has many new capabilities including:
GA releases are now published for the 2020.3 version of InterSystems IRIS, IRIS for Health, with IntegratedML!
Preview releases are now available for InterSystems IRIS Advanced Analytics, and InterSystems IRIS for Health Advanced Analytics! The Advanced Analytics add-on for InterSystems IRIS introduces IntegratedML as a key new feature.
The build number for these releases is: 2020.3.0AA.331.0
Full product installation kits, container images, and evaluation license keys are available via the WRC's preview download site.
Community Edition containers can also be pulled from the Docker store using the following commands:
Greetings Developer Community!
InterSystems IntegratedML (formerly known as QuickML) is ready for external beta, and is looking for some users to kick the tires!
IntegratedML is an all-SQL machine learning (ML) feature in IRIS that:
• Gives users the ability to create, train and deploy powerful models from simple SQL syntax
• Wraps "best of breed" open source and proprietary ML and "automl" frameworks such as TensorFlow, XGBoost, H2O-3, and DataRobot
• Focuses on ease of deployment, so you can add predictions to your application with a single SQL function call