-
Install dependencies by running:
pip install -r requirements.txt
-
Configure your OpenAI API key by copying
apis_example.envtoapis.envand setting your API key:cp apis_example.env apis.env
Then edit
apis.envand replace"your-api-key"with your actual OpenAI API key.
Each experiment folder should contain:
config.yaml: Configuration file with experiment definitionsdata/: Dataset files (CSV or Excel)prompts/: Text files containing prompts for each experimentbatches/: Generated batch files (created by prepare_experiment.py)results/: Results from OpenAI API (downloaded by execute_experiment.py)outputs/: Final processed results (created by generateResults.py)
-
Prepare the experiment by running:
python prepare_experiment.py <EXPERIMENT_NAME> <EXPERIMENT_PATH>
This generates the batch files from your configuration.
Available EXPERIMENT_NAME options:
Option Description <experiment_name>Process specific experiment allProcess all existing experiments in config.yaml failedRetry failed experiments statusShow failed experiments -
Run the experiment by executing:
python execute_experiment.py <EXPERIMENT_NAME> <EXPERIMENT_PATH>
This executes the batches and automatically downloads results when completed.
Available EXPERIMENT_NAME options:
Option Description <experiment_name>Process specific experiment allProcess all existing experiments in the batches folder failedRetry failed experiments remainCheck and download batches still in tracking statusShow batches still in tracking
-
Execute:
python generateResults.py <EXPERIMENT_NAME> <EXPERIMENT_PATH>
This processes the downloaded results and generates a .xlsx file in the folder
outputs/<EXPERIMENT NAME>Available EXPERIMENT_NAME options:
Option Description <experiment_name>Process specific experiment allProcess all existing experiments that have batches and results (in the bathces and results folders respectively) failedRetry failed experiments statusShow failed experiments