[WIP] [#262] Add med rule extraction tests and model evaluations#290

Draft

sahilds1 wants to merge 22 commits intoCodeForPhilly:listOfMedfrom

sahilds1:262-extract-meds-rules

Commits on May 23, 2025

Add med rule extraction tests and model evaluations
sahilds1
committed

Commits on May 27, 2025

Add CLI support for eval script with input and output file arguments
sahilds1
committed
Include token usage and cost estimation in Claude Haiku evals
sahilds1
committed

Commits on May 28, 2025

Commits on Jun 2, 2025

Refactor model invocation logic with ModelFactory and handler classes
sahilds1
committed

Commits on Jun 3, 2025

Replace ROUGE and BERTScore with Extractiveness metric for response evaluation
sahilds1
committed

Commits on Jun 5, 2025