Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
create_metric_configs

def create_metric_configs(project_id: str,
                          run_id: str | None,
                          metrics: builtins.list[GalileoMetrics | Metric | LocalMetricConfig | str]) -> tuple[builtins.list[ScorerConfig], builtins.list[LocalMetricConfig]]
Process metrics and create scorer configurations for experiments or log streams. This unified function categorizes metrics into server-side and client-side types, validates they exist, and registers server-side metrics with Galileo. Metrics can be specified as:
  • GalileoMetrics enum values (human-readable labels like “Correctness”)
  • Metric objects with name and optional version
  • UUID strings (scorer IDs for direct lookup)
  • Plain strings (searched by label with name fallback)
  • LocalMetricConfig objects (processed client-side)
Arguments
  • project_id (str): The ID of the project
  • run_id (Optional[str]): The ID of the run (can be experiment ID or log stream ID). When None, scorer registration is skipped (trigger=True flow).
  • metrics (list): List of metrics to configure
Raises
  • ValueError: If any specified metrics are unknown or don’t exist in Galileo
Returns
  • tuple[list[ScorerConfig], list[LocalMetricConfig]]: A tuple containing:
  • List of ScorerConfig objects for server-side metrics configured in Galileo
  • List of LocalMetricConfig objects for client-side metrics to process locally