What's new and changed in Unstructured Data Integration

Unstructured Data Integration updates can include new features and fixes. Releases are listed in reverse chronological order so that the latest release is at the beginning of the topic.

You can see a list of the new features for the platform and all of the services at What's new in IBM Software Hub.

Installing or upgrading Unstructured Data Integration

Ready to install or upgrade Unstructured Data Integration?

  • To install Unstructured Data Integration along with the other IBM® Software Hub services, see Installing IBM Software Hub.
  • To upgrade Unstructured Data Integration along with the other IBM Software Hub services, see Upgrading IBM Software Hub.
  • To install or upgrade Unstructured Data Integration independently, see Unstructured Data Integration.
    Remember: All of the IBM Software Hub components associated with an instance of IBM Software Hub must be installed at the same version.

IBM Software Hub Version 5.2.2

A new version of Unstructured Data Integration was released in October 2025 with IBM Software Hub 5.2.2.

Operand version: 5.2.2

This release includes the following changes:

New features
This release of Unstructured Data Integration includes the following features:
New supported data sources
You can now ingest data from OneDrive and Cloud Object Storage connections.

IBM Software Hub Version 5.2.1

A new version of Unstructured Data Integration was released in August 2025 with IBM Software Hub 5.2.1.

Operand version: 5.2.1

This release includes the following changes:

Updates
The following updates were introduced in this release:
  • When viewing flow run history you can now download individual logs. You can also use the Copy button to copy the flow run log when you open it.
  • Document set storage details can be edited or removed.
  • The initial flow run status is now set to Queued.
Issues fixed in this release
The following issues were fixed in this release:
  • Fixed the document count in document set details.
  • Fixed the issue with inaccurate status of watsonx.data Milvus operator in the flow run details.
  • Fixed the issue with incremental ingestion setting being ignored for the S3 operator.
  • Fixed the issue with flow run showing Queued when it's actually running.
  • Fixed a number of security issues related to outdated base OS images.

IBM Software Hub Version 5.2.0

Unstructured Data Integration is a new service that is available on IBM Software Hub.

Unstructured Data Integration was released in June 2025 with IBM Software Hub 5.2.0.

Operand version: 5.2.0

Use Unstructured Data Integration to ingest, cleanse, transform, and enrich unstructured data. You can then use the transformed data for Retrieval-Augmented Generation (RAG) and agentic workflows.
  • Use the intuitive, drag-and-drop user interface with pre-built modules for tasks such as text data extraction, filtering, or PII and HAP redaction to process your data.
  • Ingest data from various sources: connected data from S3 or Box, local files, document sets.
  • Generate entities and embeddings for easier retrieval of data.
You can build repeatable visual data flows that help to continuously process new changes and updates in the source and ensure the latest available data is used in your projects.