Fusion AI Release NotesSubscribe

Latest Release: 5.1.2 (14 May 2020)

Component Versions

Fusion comes bundled with everything you need to get started.

Solr 8.4.1

ZooKeeper 3.5.6

Spark 2.4.3

New features

No new features or improvements are introduced in Fusion AI 5.1.2. See the Fusion 5.1.2 Release Notes for full details.

Improvements

  • The Synonym Rules UI previously showed synonym pairs by default. The job now creates new grouped rules based on whether the job determines pair or context. If the job predicts context, then synonym pairs will display as context pairs.

  • Synonym context will be shown as default if the job predicts context. UI will allow users to switch between suggestions per synonym.

Previous releases

5.1.1 (8 April 2020)

Component Versions

Solr 8.4.1

ZooKeeper 3.5.6

Spark 2.4.3

No new features or improvements are introduced in Fusion AI 5.1.1. See the Fusion 5.1.1 Release Notes for full details.

4.2.6 (31 March 2020)

Component Versions

Solr 7.7.2

ZooKeeper 3.4.13

Spark 2.3.2

Jetty 9.4.19.v20190610

Ignite 2.6.0

  • Support is added for individually selecting multiple rules to publish in the Fusion UI:

    Individually publish rules in the Fusion UI

  • Fields in the Business Rules edit modal now flex to show more information when the panel is expanded.

5.1.0 (12 March 2020)

Component Versions

Solr 8.3.1

ZooKeeper 3.5.6

Spark 2.4.2

Sentiment analysis

One major part of understanding intent is understanding sentiment. When you assign sentiment values to incoming queries, or to documents during indexing, you can leverage that data to deliver more insight to your business applications.

This release includes two state-of-the-art, pre-trained sentiment analysis models that you can use to embed sentiment scoring into your query and indexing pipelines:

sentiment-general sentiment-reviews

A general-purpose model, trained on short sentences.

Suitable for short texts and for intent prediction.

See Deploy The sentiment-general Model for instructions.

A model trained on a variety of customer reviews.

Optimized for longer texts. It also supports highlighting the tokens that provide stronger sentiment.

See Deploy The sentiment-reviews Model for instructions.

See Sentiment Analysis and Prediction for more details and instructions.