Package dev.dokimos.core
package dev.dokimos.core
-
ClassDescriptionAssertion utilities for evaluation-based testing.A non-blocking task that produces a
TaskResultasynchronously.Base class for implementing concrete evaluators.Optional metrics describing the LLM call that produced an item result.A collection of examples for evaluation.Builder for constructing datasets.Thrown when a dataset cannot be correctly resolved or loading fails.Resolves a dataset URI to aDataset.Singleton registry for dataset resolvers.The result of an evaluation.Builder for constructing evaluation results.A test case for evaluation.Builder for constructing test cases with multiple inputs and outputs.Evaluates test cases and produces scored results.A dataset example with inputs, expected outputs, and metadata.Builder for constructing examples with multiple inputs and outputs.An evaluation experiment that runs a task against a dataset and evaluates the results.Aggregated results from an experiment.Resolves datasets from the filesystem.The outcome of executing a single example: the example itself, the actual outputs the task produced, the evaluator results, and optional metrics describing the underlying LLM call.A language model used for evaluation.Utility methods for processing LLM responses.Strategy for determining if a retrieved item matches an expected item.A task that produces outputs together with optionalCallMetricsdescribing the underlying LLM call.A no-op implementation ofReporterthat does nothing.OutputType<T>A super-type token that captures a full generic typeT(including its type arguments) at compile time so it survives erasure at runtime.Turns a model id and token counts into a USD cost, returning null when the model is unknown or a count is missing (never throws, never fabricates a number).Interface for reporting experiment results to an external system.A handle representing an active experiment run.Results from a single run of an experiment.Status of an experiment run.The outcome of executing aMeasuredTask: the actual outputs and optional metrics describing the underlying LLM call.