Cassandra 3.11.3 support for Pega Platform
Valid from Pega Version 8.3
Increase your system's reliability and reduce its memory footprint by upgrading the internal Cassandra database to version 3.11.3.
For on-premises Pega Platform™ users, after you upgrade to Pega 8.3, it is recommended that you manually upgrade to Cassandra 3.11.3. You can upgrade to Cassandra 3.11.3 on all operating systems except IBM AIX. If you do not want to upgrade to Cassandra 3.11.3, you can continue to use Cassandra 2.1.20, which is still supported.
For Pega Cloud Services 2.13 and later versions, Cassandra automatically upgrades to version 3.11.3 after your environment is upgraded to Pega Platform 8.3.
For information on how to manually upgrade to Cassandra 3.11.3, see the Pega Platform 8.3 Upgrade Guide for your server and database at Deploy Pega Platform.
Upgrade impact
After an on-premises Pega Platform upgrade, you still have the older version of Cassandra and must manually upgrade.
What steps are required to update the application to be compatible with this change?
To upgrade Cassandra, you must create a prconfig setting or a dynamic system setting with the new Cassandra version and then do a rolling restart of all the Decision Data Store nodes to upgrade them to the latest version of Cassandra.
Support for the decisioning-enabled NLP text analyzer in IVAs and Email Bots
Valid from Pega Version 8.3
You can now use the new intelligent natural language processing (iNLP) text analyzer in Pega Intelligent Virtual Assistants™ (IVAs) and Pega Email Bots™. This advanced text analyzer is decisioning-enabled and empowers IVA or Email Bot for all conversational channels to provide smarter responses. The decisioning capability in the system integrates text analytics with strategies, prepositions, and interaction history, to provide the context for making better next-best-action decisions.
For more information, see Use the decisioning-enabled NLP text analyzer in IVAs and Email Bots, Defining advanced Facebook text analyzer configuration and Facebook channel behavior.
Upgrade impact
Existing channels remain with the current configuration, and their current functionality does not change. Channels created after the upgrade automatically use the new text analyzer.
What steps are required to update the application to be compatible with this change?
The new text analyzer is enabled or disabled using a new interactive API (iAPI) selection, which is selected by default for new channels. You can disable the iAPI for new channels if you want to maintain current functionality. You can also enable it for existing channels if you want to move existing channels to the new functionality.
Text analytics models editing and versioning
Valid from Pega Version 8.3
Pega Platform™ now supports editing and updating training data for text analytics models.
Pega Platform also supports the versioning of text analytics models. When you update the model, Prediction Studio creates an updated model version. You can then switch between the model versions.
Upgrade impact
In versions of Pega Platform earlier than 8.3, the training data for text models was stored in the database. In Pega Platform version 8.3 and later, the training data for text models is stored in Pega Repository. You cannot build new models without setting the repository. After the repository is set, all text models are automatically upgraded and will work normally.
What steps are required to update the application to be compatible with this change?
After a successful upgrade, set the repository in Prediction Studio before building or updating any Natural Language Processing (NLP) models. In Prediction Studio, click Settings > Text Model Data Repository.
For more information, see:
- Increase the accuracy of text analytics models by adding feedback data (8.3)
- Updating training data for text analytics models
Text analytics models migration
Valid from Pega Version 8.3
Pega Platform™ now supports the exporting and importing of text analytics models. For example, you can export a model to a production system so that it can gather feedback data. You can then update the model with the collected feedback data to increase the model's accuracy.
Upgrade impact
In versions of Pega Platform earlier than 8.3, the training data for text models was stored in the database. In Pega Platform version 8.3 and later, the training data for text models is stored in Pega Repository. You cannot build new models without setting the repository. After the repository is set, all text models are automatically upgraded and will work normally.
What steps are required to update the application to be compatible with this change?
After a successful upgrade, set the repository in Prediction Studio before building or updating any Natural Language Processing (NLP) models. In Prediction Studio, click Settings > Text Model Data Repository.
For more information, see:
- Increase the accuracy of text analytics models by adding feedback data (8.3)
- Exporting text analytics models
- Importing text analytics models
Improved rich user interface controls in IVA for Web Chatbot
Valid from Pega Version 8.3
In Pega Intelligent Virtual Assistant™ (IVA) for Web Chatbot, you can use additional rich user interface controls, such as the time and date picker or a simple form, to help users accomplish tasks more quickly and to limit errors. IVA for Web Chat can now also display a welcome message in the chat window, for example, to inform the user about the person with whom they are chatting.
For more information, see Streamline conversations in IVA for Web Chatbot with rich user interface controls.
Upgrade impact
The new Ul controls for Web Chatbot are enabled by default upon upgrade. If you do not want the controls enabled, you must disable them.
Also, if you have changed the styles for the welcome message, you may need to make changes to the welcome message to incorporate the new areas in the bot conversation area (such as quick replies).
What steps are required to update the application to be compatible with this change?
Existing channels will behave as they did previously, so you should determine whether you want to use the new UI controls. If you want to use the new Ul controls, configure the new design-time options.
If you have changed the default styles for the welcome message, review the new settings to ensure that the welcome message is configured properly.