Feature/data augmentation for de biasing

[chakravarthik27]

This pull request introduces a new debiasing feature to the langtest package, including the addition of a new module for debiasing text, updates to the __init__.py file to include this new module, and updates to the pyproject.toml file to include a new dependency.

New debiasing feature:

• langtest/augmentation/debias.py: Added a new module for debiasing text, which includes multiple classes such as BiasDetectionRequest, BiasDetectionResponse, TextDebiasingRequest, DebiasedTextResponse, DebiasingRequest, DebiasingResult, and DebiasTextProcessing. These classes handle the detection and processing of bias in text data.

Updates to __init__.py:

• langtest/augmentation/__init__.py: Added DebiasTextProcessing to the list of imports and updated the __all__ list to include DebiasTextProcessing.

Dependency updates:

• pyproject.toml: Added the ollama dependency with version ^0.4.6 and included an ollama_sdk extra group for optional dependencies. [1] [2]

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

Comments suppressed due to low confidence (2)

langtest/augmentation/debias.py:8

• The word 'seperated' is misspelled. It should be 'separated'.

The following text contains biased information, such as discrimination and stereotyping, which fall into various categories. Each category includes specific subcategories with seperated by ',' , as listed below:

langtest/augmentation/debias.py:216

• The use of 'type[_Schema]' for type hinting might not be compatible with all versions of Python. Consider using 'Type[_Schema]' from the 'typing' module.

def interaction_llm(self, text: str, output_schema: type[_Schema], system_prompt: str) -> _Schema:

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.