Tonic Textual release information

Learn about what’s in the latest Tonic.ai product releases.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
v273
April 30, 2025

As an administrator, you can now use a dedicated API endpoint to view audit logs of user actions.

v272
April 29, 2025

Self-hosted customers can now download a usage report that lists their users' actions across the product.

v271
April 25, 2025

Bug fixes and other internal updates.

v270
April 25, 2025

Bug fixes and other internal updates.

v269
April 24, 2025

Enabled support for the LOCATION_COMPLETE_ADDRESS in PDFs and images.

For connections to Amazon S3, you can now choose whether to use Amazon S3 encryption (the default) or use KMS encryption.

You can now assign tags to datasets and pipelines.

Self-hosted instances can now configure custom endpoints for connections to AWS.

v268
April 17, 2025

Add support for a LOCATION_COMPLETE_ADDRESS entity type. By default, the handling type for this entity type is Off, meaning that detected values are ignored. It is not currently supported for PDFs and images.

v267
April 17, 2025

Improved the predications for the named-entity recognition entity type ORGANIZATION.

v266
April 16, 2025

The new environment variable SOLAR_MAX_CONCURRENT_WORKER_JOBS allows you to configure the number of jobs that each worker can process at the same time. By default, each worker can process 8 jobs simultaneously.

v265
April 15, 2025

You can now use the Tonic Textual SDK to redact audio files. When you send a request to redact an audio file, Textual first transcribes the audio into text, and then redacts the transcription. The request includes the entity type handling.

v264
April 14, 2025

Bug fixes and other internal updates.

v263
April 14, 2025

Bug fixes and other internal updates.

v262
April 11, 2025

Added the Password entity type to the named-entity recognition (NER) model.

v261
April 9, 2025

Bug fixes and other internal updates.

v260
April 8, 2025

Added the Password entity type to the named-entity recognition (NER) model.

When you select an AWS Region, the dropdown list now includes the ISO Regions.

Additional consistency between Textual and Structural - A new environment variable allows you to configure a statistics seed to enable you to ensure that synthesized values in Textual match corresponding generated values in Structural. The statistics seed is also displayed in the Textual application. To ensure consistency between the application, provide the same statistics seed value in both.

The consistency applies to non-HIPAA addresses, to match the Address generator in Structural, and US telephone numbers, to match the US Phone Number generator. For these types of values, when the statistics seeds match, the same input value produces the same output value in both Textual and Structural.

v259
April 2, 2025

Fixed an issue where quotes and whitespaces broke the LLM_MODEL setting for LLM synthesis.

Added a new entity type, NUMERIC_PII, for numeric values that act as identifiers.

v258
March 31, 2025

Bug fixes and other internal updates.

v257
March 28, 2025

Bug fixes and other internal updates.

v256
March 25, 2025

Bug fixes and other internal updates.

v255
March 25, 2025

Bug fixes and other internal updates.

v254
March 24, 2025

Dataset settings are moved from a popup modal to a separate page.

v253
March 19, 2025

Bug fixes and other internal updates.

v252
March 18, 2025

Bug fixes and other internal updates.

v251
March 17, 2025

Bug fixes and other internal updates.

v250
March 17, 2025

Bug fixes and other internal updates.

v249
March 15, 2025

Bug fixes and other internal updates.