v0.2.0

Dependency updates and allow for csv inputs and outputs

v0.1.3

• Added functionality to automatically apply scorer function to obtained responses
• Allows for multiple prompt templates for LLM-as-judge evaluation

v0.1.2

• Functionality for automatic evaluation via LLM-as-judge or applying a scoring function
• Further tests implemented

v0.1.1

bump 0.1.1

v0.1.0

add pypi on publish workflow