In v40, models for flows created in v38 and above are forward compatible, meaning that you can use them in v40 without having to retrain them during the upgrade process. As a result, forward-compatible models allow you to:
upgrade v38 or v39 models after upgrading the application to v40,
maintain the automation levels achieved in v38 or v39, and
continue existing training efforts for any use cases that may be in implementation when upgrading to v40.
Which models are forward-compatible
In v40, the following types of models are forward-compatible:
Identification models
Classification models
The following types of models are not forward compatible, so you need to train v40 versions of these models in order to use them in v40:
Transcription models (i.e., sets of finetuning models)
Text Classification models
To learn more about Text Classification, see Text Classification.
Using v38 and v39 models and flows in v40
As mentioned earlier, you can continue using v38 and v39 flows in v40 without interruption or loss of automation, provided that their models were last trained on v38 or later. For more information on what combinations of flow and model versions you can use in v40, see Compatibility Across Application, Flow, and Model Versions.
When using v38 or v39 flows, you can use cloned versions of the releases you used in v38 or v39. However, if you add Semi-structured layouts to those releases, there is no automation for the submissions matched to these layouts. That is, the system generates Supervision tasks for these submissions.
Memory Management
If you are using flows from multiple versions of the application and out-of-memory errors occur, you should enable the Memory Management feature. This feature assigns flows that were created in specific application versions to specific application machines in your instance.
To learn more about Memory Management, see Memory Management.
How to know when to train forward-compatible models
When you open a flow created in v38 or later in Flow Studio, the system lets you know which models for the flow need to be trained.
From there, you can click on an issue's Go to Model Management button.
If the affected model is an Identification model, you are redirected to the Model Library. There, you can find the model mentioned in the issue's description and click on its name. On the model’s details page, you can take action to correct the issue.
If the model mentioned in the issue is a Classification or Transcription model, clicking Go to Model Management takes you directly to the model’s details page, where you can take corrective action.
Models from unsupported versions do not appear in the Model Library.