​
run_experiment

def run_experiment(experiment_name: str,
                   *,
                   prompt_template: Optional[PromptTemplate] = None,
                   prompt_settings: Optional[PromptRunSettings] = None,
                   project: Optional[str] = None,
                   project_id: Optional[str] = None,
                   dataset: Optional[Union[Dataset, list[dict[str, str]],
                                           str]] = None,
                   dataset_id: Optional[str] = None,
                   dataset_name: Optional[str] = None,
                   metrics: Optional[list[Union[GalileoScorers, Metric,
                                                LocalMetricConfig,
                                                str]]] = None,
                   function: Optional[Callable] = None) -> Any
Run an experiment with the specified parameters. There are two ways to run an experiment:
  1. Using a prompt template, prompt settings, and a dataset
  2. Using a runner function and a dataset
When using a runner function, you can also pass a list of dictionaries to the function to act as a dataset. The project can be specified by providing exactly one of the project name (via the ‘project’ parameter or the GALILEO_PROJECT environment variable) or the project ID (via the ‘project_id’ parameter or the GALILEO_PROJECT_ID environment variable). Arguments:
  • experiment_name: Name of the experiment
  • prompt_template: Template for prompts
  • prompt_settings: Settings for prompt runs
  • project: Optional project name. Takes preference over the GALILEO_PROJECT environment variable. Leave empty if using project_id
  • project_id: Optional project Id. Takes preference over the GALILEO_PROJECT_ID environment variable. Leave empty if using project
  • dataset: Dataset object, list of records, or dataset name
  • dataset_id: ID of the dataset
  • dataset_name: Name of the dataset
  • metrics: List of metrics to evaluate
  • function: Optional function to run with the experiment
Raises:
  • prompt_template0: If required parameters are missing or invalid
Returns: Experiment run results

​
get_experiment

def get_experiment(
    project_id: str, experiment_name: str
) -> Optional[Union[ExperimentResponse, HTTPValidationError]]
Get an experiment with the specified parameters. Arguments:
  • project_id: Galileo ID of the project associated with this experiment
  • experiment_name: Name of the experiment
Raises:
  • HTTPValidationError: If there’s a validation error in returning a ExperimentResponse
Returns: ExperimentResponse results

​
get_experiments

def get_experiments(
    project_id: str
) -> Optional[Union[HTTPValidationError, list[ExperimentResponse]]]
Get an experiments with the specified Project ID. Arguments:
  • project_id: Galileo ID of the project associated with this experiment
Raises:
  • HTTPValidationError: If there’s a validation error in returning a list of ExperimentResponse
Returns: List of ExperimentResponse results