Release Highlights

General

• Added badges to the README for improved visibility and quick access to key resources.
• Restructured folders for better organization of samples and source code.

Data Discovery

• Added support for structured text classification.
• Introduced categorized “harmonized” classifications; may affect expected results.
• General performance and accuracy improvements.

Semantic Guardrails

• Included richer examples in the sample files for easier understanding.
• Added pre-trained support for additional verticals, Finance and Healthcare.
• Added a Jupyter notebook sample for seamless evaluation and execution.

API Wrappers

• Online notebook to quickly test tokenization.
• Provided support and sample implementations for both Python and Java.
• Ensured Java samples are fully compatible across Linux, macOS, and Windows.
• Delivered Java source code for customization and compilation flexibility.

Synthetic Data

• Introduced a new feature for synthetic data generation to support testing and experimentation.
• Added Jupyter notebook samples for quick evaluation and execution.