Issue where NER evaluations passed incorrectly when expected results were empty, but actual results contained predictions. This should have failed. (Fixed)
Issue where NER predictions had differing lengths between expected and actual results. (Fixed)
[x] Training Dataset Limit Issue:
Exceeded the maximum limit set on the training dataset during test augmentation allocation. (Fixed)
[x] Augmentation Data Allocation:
Uneven allocation of augmentation data, resulting in some test cases not undergoing any transformations. (Fixed)
[x] DataAugmenter Class Issues:
Export types were not functioning as expected after data augmentation. (Fixed)
[x] Template Generation with OpenAI API:
Issues with OpenAI API while generating different templates from user-provided ones, leading to invalid outputs like paragraphs or incorrect JSON. Implemented structured outputs to resolve this. (Fixed)
[x] Pydantic Model Enhancements:
Added validation steps in the Pydantic model to ensure templates are generated as required.
[x] Azure OpenAI Service Integration:
implementated of template-based augmentation using Azure OpenAI service. (In progress)
[x] Text Classification Support:
Adding support for multi-label classification in text classification tasks.
Langtest 2.3.1 Dump Version