Tonic Textual release information

Learn about what’s in the latest Tonic.ai product releases.
v190
v190
Removed
November 19, 2024

Added the Tonic NER model version to the model information. The API endpoint /api/environment/models reports version strings for NER models.

Entity manager for entity types - The new entity manager allows you to view all of the occurrences of each entity type in a dataset. it displays the original value, the context in the original file, and the context in the transformed file. To view the entities manager, from the entity value preview list, click Open Entities Manager. Note that by default, for the NUMERIC_VALUE entity type, Textual only provides context information for the first 20 occurrences. To change this, set the SOLAR_NER_OCCURRENCE_IGNORE_NUMERIC_VALUE environment variable to false.

v189
v189
Removed
November 14, 2024

Bug fixes and other internal updates.

v188
v188
Removed
November 14, 2024

Improved detection of names, particularly in ASR transcripts.

v187
v187
Removed
November 7, 2024

Added an optional jsonpath_allow_lists to redact_json. You use jsonpath_allow_lists to override NER results at specific JSON Path expressions.

v186
v186
Removed
November 6, 2024

Bug fixes and other internal updates.

v185
v185
Removed
November 5, 2024

Bug fixes and other internal updates.

v184
v184
Removed
November 4, 2024

Bug fixes and other internal updates.

v183
v183
Removed
November 2, 2024

Bug fixes and other internal updates.

v182
v182
Removed
November 1, 2024

Bug fixes and other internal updates.

v181
v181
Removed
November 1, 2024

Bug fixes and other internal updates.

v180
v180
Removed
October 31, 2024

Bug fixes and other internal updates.

v179
v179
Removed
October 31, 2024

Textual can now redact images in .docx files.

v178
v178
Removed
October 30, 2024

Fixed a rare issue where Azure OCR returned a400 response when the file upload stream contained corrupted data.

Improved synthesis on days of the week and ordinal numbers that are flagged as DATE_TIME.

Textual now only disables a numeric span when it overlaps one of the following disabled types: DATE_TIME, DOB, LOCATION, LOCATION_ADDRESS, LOCATION_ZIP, MONEY, CREDIT_CARD, PHONE_NUMBER.

v177
v177
Removed
October 28, 2024

Textual now allows you to parse EML and MSG files.

v176
v176
Removed
October 25, 2024

You can now use the Python SDK to configure Azure pipelines.

v175
v175
Removed
October 25, 2024

Bug fixes and other internal updates.

v174
v174
Removed
October 24, 2024

Bug fixes and other internal updates.

v173
v173
Removed
October 24, 2024

You can now use the Python SDK to configure Amazon S3 pipelines.

v172
v172
Removed
October 23, 2024

Amazon Textract can now be used to process dataset files.

v171
v171
Removed
October 23, 2024

On the Python SDK, added parameters for pipeline creation, including the file location, the connection credentials, and whether to also generate redacted files.

v170
v170
Removed
October 21, 2024

Improved the Textual NER model throughput on long strings that contain a large number of numeric characters.

Added the redact_html function to the SDK, which allows you redact sensitive values from HTML strings.

v169
v169
Removed
October 16, 2024

Improved detection of names and organizations.

Disabled auxiliary model detection of WORK_OF_ART.

v168
v168
Removed
October 16, 2024

Improved the Textual NER model throughput on long strings that contain a large number of detected entities.

Added support to store dataset files in a specified S3 bucket, instead of in the Textual application database.

When Textual replaces first name values, it now attempts to use a name with the same gender.

For the DOB (date of birth) entity type, you can now configure synthesis options. You can set how to shift the date.

v167
v167
Removed
October 14, 2024

Bug fixes and other internal updates.

v166
v166
Removed
October 11, 2024

Improved the synthesized values for the PERSON_AGE entity type.

v165
v165
Removed
October 11, 2024

You can now configure the entity type handling for a dataset before you upload the dataset files.

You can now provide added and excluded entity values when you use the SDK to redact individual strings and files.

Added a new method to the SDK. redact_xml works similarly to redact_json. To produce a redacted output, you pass in a redact_xml string.

v164
v164
Removed
October 9, 2024

Improve Pipeline UI to include better Python SDK code snippets

v163
v163
Removed
October 8, 2024

Improved the user experience when you load a large number of files to a dataset.

v162
v162
Removed
October 7, 2024

Updated the UI for adding and excluding values for entity types. Changed the tab labels to Add to detection and Exclude from detection, and removed the requirement to click the edit icon for the entries.

v161
v161
Removed
October 2, 2024

Added support in the SDK to create dataset include lists to define additional values for an entity type.

v160
v160
Removed
September 29, 2024

Removed support for en_core_web_trf and en_core_web_lg auxiliary models. Disabled model inference for ORGANIZATION, PERSON, LOCATION, and MONEY entity types. Updated the auxiliary model configuration environmental variables to have new default values:
TEXTUAL_AUX_MODEL_GPU: false
TEXTUAL_AUX_MODEL: en_core_web_sm

Fixed a redaction issue that was caused by a regression from v140.

Improved the Textual NER model, specifically for datetime values and and electronic health records.

Fix for correctly re-synthesizing files as part of pipelines

When you call the dataset.add_file method in the Textual SDK, you can now pass in IO bytes.

You can now specify a list of additional values to include for each entity in a datasets. This allows Textual to identify values that it might not identify because they are specific to your organization or industry. The list can contain both specific values and regular expressions.

Improved the file list display for datasets to better accommodate longer file names.

For an uploaded file pipeline, added a Back to Files breadcrumb to return the user to the main file list.

On the dataset details page, the bulk edit function for entity type handling is now a dropdown instead of separate buttons.

v159
v159
Removed
September 25, 2024

You can now use the Python SDK to delete files from a dataset.

To improve performance, enabled date synthesis inference on GPU. Added the environment variable TEXTUAL_DATE_ SYNTH_ GPU to manage whether to use it.

Renamed the following environment variables:

  • SOLAR_PREFER_GPU to TEXTUAL_AUX_MODEL_GPU
  • SOLAR_AUX_MODEL to TEXTUAL_AUX_MODEL
v158
v158
Removed
September 24, 2024

Bug fixes and other internal updates.

v157
v157
Removed
September 23, 2024

Bug fixes and other internal updates.

v156
v156
Removed
September 23, 2024

Bug fixes and other internal updates.

v155
v155
Removed
September 20, 2024

Bug fixes and other internal updates.

v154
v154
Removed
September 19, 2024

You can now create pipelines that use files from Azure Blob Storage.

v153
v153
Removed
September 18, 2024

Bug fixes and other internal updates.

v152
v152
Removed
September 18, 2024

Bug fixes and other internal updates.

v151
v151
Removed
September 18, 2024

Bug fixes and other internal updates.

v150
v150
Removed
September 17, 2024

Bug fixes and other internal updates.

v149
v149
Removed
September 16, 2024

Improved performance for previewing PDF files.

v148
v148
Removed
September 10, 2024

Bug fixes and other internal updates.

v147
v147
Removed
September 9, 2024

Bug fixes and other internal updates.

v146
v146
Removed
September 8, 2024

The responses for textual.redact and textual.llm_synthesis now include:
br<

  • The language for each entity value.
  • The start location (new_start) of each entity value in the redacted content.
  • The end location (new_end) of each entity value in the redacted string.

For uploaded file pipelines that also generate redacted files, you can now configure the handling option for each entity type.

v145
v145
Removed
August 30, 2024

Bug fixes and other internal updates.

v144
v144
Removed
August 29, 2024

Added a HEALTHCARE_ID entity type for identifiers associated with health care.

Removed the right-hand panels from the Home page. Added the API Keys panel to the dataset details page to accompany the code snippets.

v143
v143
Removed
August 28, 2024

Bug fixes and other internal updates.

v142
v142
Removed
August 26, 2024

On the Playground, LLM Synthesis is now turned off by default.

v141
v141
Removed
August 22, 2024

Improved synthesis for DATE_TIME entities by recognizing non-standard date formats.

v140
v140
Removed
August 21, 2024

Added a forgot password option to allow Textual Cloud users to reset their password.

Improved our detection of date values.

Removed the US_DRIVER_LICENSE entity type.

v139
v139
Removed
August 19, 2024

Introduced a new model that improves performance for non-English languages.

The responses for textual.redact and textual.llm_synthesis now include the redacted or synthesized value.

v138
v138
Removed
August 15, 2024

Bug fixes and other internal updates.

v137
v137
Removed
August 12, 2024

When Textual synthesizes values, it now matches the capitalization of the original value.

v135
v135
Removed
August 8, 2024

For PDF and image files, the pipeline file details now include any tables and key-value pairs that are in the file.

The Pipelines and Datasets pages now display lists instead of cards.

v134
v134
Removed
August 8, 2024

You can now set up a pipeline to connect to a Databricks workspace. You can also configure a Databricks pipeline to generate redacted files in addition to the JSON output.

Textual can now detect values in multiple languages. Textual Cloud supports a set of non-English languages. For a self-hosted instance, you must enable multi-language support and provide the language models for Textual to use.

v132
v132
Removed
August 1, 2024

Textual no longer includes the option to create custom models to use for datasets.

v131
v131
Removed
August 1, 2024

Textual now supports a pay-as-you-go option for Textual Cloud. When you set up a pay-as-you-go subscription, you provide a credit card that is automatically billed each month for your Textual usage.

v133
v133
Removed
August 1, 2024

Bug fixes and other internal updates.

v130
v130
Removed
July 31, 2024

Redesigned the structure of the JSON output.

v129
v129
Removed
July 26, 2024

Bug fixes and other internal updates.

v127
v127
Removed
July 25, 2024

NOTE: This version was removed because of a regression.

Fixed an issue where pipelines failed to run.

Updated the Python SDK to add options to create pipelines, delete pipelines, upload pipeline files, and download pipeline results.

Disabled the Run Pipeline option when a pipeline does not have a configured output path.

v128
v128
Removed
July 25, 2024

Bug fixes and other internal updates.

v126
v126
Removed
July 22, 2024

Bug fixes and other internal updates.

v125
v125
Removed
July 20, 2024

The user menu now displays the current Textual version.

Fixed an issue where you could not upload a file that had the same name as a file that was deleted.

v124
v124
Removed
July 18, 2024

Added entity types, for money, a person's age, data of birth, organizations, and countries. Improved the detection of occupation.

Updated the display of JSON output to add collapse/expand functionality.

The Snowflake Native App now supports JSON files.

v123
v123
Removed
July 17, 2024

Added a new Next Steps panel for pipelines. Includes copyable code snippets

v122
v122
Removed
July 11, 2024

Bug fixes and other internal updates.

v121
v121
Removed
July 5, 2024

Updated the getting started flow to focus on pipelines.

v120
v120
Removed
July 3, 2024

Bug fixes and other internal updates.

v119
v119
Removed
July 3, 2024

You can now configure an Amazon S3 pipeline to also generate redacted versions of the original files.

v118
v118
Removed
July 2, 2024

For self-hosted instances, Textual no longer requires you to input AWS credentials if they are available from the environment.

v117
v117
Removed
June 28, 2024

The Snowflake Native App now supports parsing files to produce JSON output.

v116
v116
Removed
June 26, 2024

Bug fixes and other internal updates.

v115
v115
Removed
June 26, 2024

Bug fixes and other internal updates.

v112
v112
Removed
June 25, 2024

Added support to provide AWS session tokens for pipelines.

v114
v114
Removed
June 25, 2024

Bug fixes and other internal updates.

v113
v113
Removed
June 25, 2024

Bug fixes and other internal updates.

v111
v111
Removed
June 24, 2024

The Entities tab of the pipeline file details no longer displays the tabular list of entities. It only displays the detected entities in context.

v110
v110
Removed
June 14, 2024

For uploaded file pipelines, removed the run option and list of runs. Uploaded file pipelines now run automatically to process each new file as it is added.

v109
v109
Removed
June 11, 2024

Bug fixes and other internal updates.

v108
v108
Removed
June 7, 2024

For Amazon S3 pipelines, in the file selection, highlight buckets that contain selected files or folders.

On the file details page for a pipeline file, changed the Redactions tab to Entities.

v106
v106
Removed
June 5, 2024

Added an option to copy the identifier of a pipeline run.

Updated the onboarding flow and redesigned the Home page.

Added a confirmation modal for canceling a pipeline run.

v107
v107
Removed
June 5, 2024

Fixed a display issue with pipeline titles.

v104
v104
Removed
May 31, 2024

You can now delete a newly uploaded file without having to refresh the page.

Fixed an issue with the status information for pipeline files.

For plain text pipeline files, removed the option to toggle between Markdown and the original content.

Fixed an issue with previewing PDF files.

The file list for a pipeline run no longer displays while the run is queued.

v105
v105
Removed
May 31, 2024

Bug fixes and other internal updates.

v103
v103
Removed
May 24, 2024

Added support for Amazon S3 files in pipelines.

Added support for image files.

v102
v102
Removed
May 22, 2024

Bug fixes and other internal updates.

v101
v101
Removed
May 20, 2024

Bug fixes and other internal updates.

v100
v100
Removed
May 14, 2024

Bug fixes and other internal updates.

v099
v099
Removed
May 13, 2024

Added support for .xlsx files.Added support for headers, footers, footnotes, and endnotes in .docx files.

v098
v098
Removed
May 9, 2024

Textual can now detect gender labels and occupations.

Fixed an issue with .docx files that started with an empty paragraph.

v097
v097
Removed
May 3, 2024

Bug fixes and other internal updates.

v096
v096
Removed
May 1, 2024

Bug fixes and other internal updates.

v095
v095
Removed
April 30, 2024

Bug fixes and other internal updates.

v094
v094
Removed
April 29, 2024

Improved handling of emojis.

v093
v093
Removed
April 26, 2024

Bug fixes and other internal updates.

v092
v092
Removed
April 25, 2024

Bug fixes and other internal updates.

v091
v091
Removed
April 24, 2024

Fixed an issue with the preview of .docx files.

Added support for image files.

Added an LLM synthesis option to the Playground.

v090
v090
Removed
April 16, 2024

Updated the SDK to support redacting individual text and .csv files.