Llm evaluation

[Mazenh2003]

Senselab project integrates deepeval for evaluating conversations,
using an api.py script to interface with deep_eval.py,
which includes a custom ROUGE metric for comprehensive evaluation.
The ScriptLine class standardizes input data, and unit tests ensure accurate functionality,
making Senselab a robust wrapper for deepeval and other tools.

[batwood-1]

Nice use of style and cleanliness, some quick points -

-Still failing checks
-We have a script_line data structure available already in utils/datastructures, is there a reason you are rewriting rather than importing this?
-write a file called metrics.py, with an abstract base class called Metric, define the abstractmethods you want to be inherited by the different implementations of Metric (see https://docs.python.org/3/library/abc.html), then define various implementations (rouge, etc)
-give some various options for calculating overall_score in evaluate_conversation, perhaps harmonic mean, etc

by the time of the review, all tests failed.