Experimental
Optional
concurrency?: numberThe number of dataset examples to run in parallel
The dataset to run the experiment on
Optional
dryRun?: number | booleanWhether or not to run the experiment as a dry run. If a number is privided, n examples will be run.
Optional
evaluators?: Evaluator[]The evaluators to use
Optional
experimentDescription?: stringThe description of the experiment
Optional
experimentMetadata?: Record<string, unknown>Experiment metadata E.x. modelName
Optional
experimentName?: stringAn optional name for the experiment. Defaults to the dataset name + a timestamp
Optional
logger?: LoggerThe logger to use
Optional
record?: booleanWhether to record the experiment results
Optional
setGlobalTracerProvider?: booleanWhether to set the global tracer provider when running the task. If set to false, a locally scoped tracer will be created but will not get registered. This may cause certain spans to not be picked up by Phoenix. Notably libraries like the AI SDK that leverage the global tracer.
The task to run
Parameters for running an experiment.
This feature is not complete, and will change in the future.