Repo for BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology https://arxiv.org/abs/2310.10632
conda env create -f environment.yml
conda activate bioplanner
poetry install
To run an Evaluation, add a correctly filled out json file to the to_evaluate folder then run python src/run_evaluate.py. The results of the evaluation will be in a json file results.json