v1.0.5

Initial Release

A Python SDK for creating custom evaluation metrics for LLM model evaluation on Sagemaker Training Job with built-in Pydantic validation.

Features

• Pydantic Validation: Automatic input/output validation using Pydantic models
• PreProcessor: For input data transformation with validation
• PostProcessor: For output data formatting with validation
• Lambda Handler Builder: Easy Lambda function creation
• Exception Handling: Custom error types with validation feedback

Documentation

README for detailed instructions on how to use the package
Sample example for a complete working sample to run locally.