Changelog
anonipy-0.5.0 (2025-05-08)
New Features:
- Replace
urchade/gliner_multi_pii-v1withE3-JSI/gliner-multi-pii-domains-v1as the main GLiNER extraction model inNERExtractor
Bug Fixes:
- Fix
LANGUAGE.SLOVENEtoLANGUAGE.SLOVENIAN - Fix
LanguageDetectorwhen handlingLANGUAGE.SLOVENIAN - Fix unit tests
anonipy-0.4.0 (2024-12-11)
New Features:
- Add
add_generation_prompttoapply_chat_templateinLLMLabelGenerator - Add function to detect repeated entities
- Add support for generator model quantization in
LLMLabelGenerator
anonipy-0.3.0 (2024-12-11)
New Features:
- Add
Pipelinemodule for streamlining text anonymization - Add better date handling and support in
DateGenerator
Bug Fixes:
- Fix unit tests
- Change unit test framework to
pytest
anonipy-0.2.0 (2024-11-09)
Breaking Changes:
- Change Python support between v3.9 and v3.12.
- Change default
model_nameforLLMLabelGeneratorto beHuggingFaceTB/SmolLM2-1.7B-Instruct(for ease of use)
New Features:
- Enable CPU utilization for
LLMLabelGenerator - Enable changing the input parameters for
LLMLabelGenerator(model_nameanduse_gpu) - Add additional unit tests for
NERExtractor
Bug Fixes:
- Fix package documentation
anonipy-0.1.2 (2024-07-23)
Bug Fixes:
- Fix entity creation in
PatternExtractor - Fix documentation duplication
anonipy-0.1.1 (2024-07-16)
New Features:
- Add
Entityregex group selection - Add option to ignore
Entityregex pattern inLLMLabelGenerator.generate
anonipy-0.1.0 (2024-07-16)
Breaking Changes:
- Rename the
EntityExtractortoNERExtractor - Rename the input variable
output_gentosub_variantinDateGenerator - Rename the input variable
entity_prefixtoadd_entity_attrsinLLMLabelGenerator.generate - Move the
regexsubmodule fromanonipy.anonymizetoanonipy.utils
New Features:
- Add a pattern extractor named
PatternExtractor, used to extract entities using spacy pattern matching and regex - Add a multi extractor named
MultiExtractor, used to extract entities using multiple extractors - Add the
DATE_TRANSFORM_VARIANTSconstant to help with date generator - Refine the
Entityimplementation - Improve package documentation
anonipy-0.0.8 (2024-06-17)
New Features:
- Add automatic date format detection support to
DateGenerator
anonipy-0.0.7 (2024-06-06)
New Features:
- Upgrade
gliner-spacyto have cleaner code - Add function to help manual post-anonymization replacement fixing
anonipy-0.0.6 (2024-05-31)
New Features:
- Add GPU support and entity scores to
EntityExtractor - Standardize the function naming in strategies
anonipy-0.0.5 (2024-05-29)
New Features:
- Re-implement file reading methods + add unit tests
- Expland the test environment on all OS
anonipy-0.0.4 (2024-05-27)
New Features:
- Add unit tests
- Refine the Entity implementation
- Update documentation
Bug Fixes:
- Fix the
LANGUAGESconstant
anonipy-0.0.3 (2024-05-22)
New features:
- Add
read_jsonfunction - Add
write_jsonfunction - Add blog post on anonymizing collections of documents
- Reduce the number of viable suggestions used to create a substitute in
MaskLabelGenerator - Add the entity label to the replacements in strategies
Bug Fixes:
- Fix the entity regex checking in
EntityExtractor
anonipy-0.0.2 (2024-05-22)
New Features:
- Add
write_filefunction - Add blog to the documentation
anonipy-0.0.1 (2024-05-21)
- Initial release