Creates a new tracker for a fresh AI run. Each call mints a new runId (a UUIDv4) that LaunchDarkly uses to correlate the run's events in metrics views. Call this once per AI run; metrics from different runIds cannot be combined.
Whether the configuration is enabled.
Optional evaluationEvaluation metric key for judge configurations. The key of the metric that this judge can evaluate.
The key of the AI Config.
Optional messagesOptional prompt data for judge configurations.
Optional modelOptional model configuration.
Optional providerOptional configuration for the provider.
Generated using TypeDoc
Judge-specific AI Config with required evaluation metric key.