ExperimentItemModel¶

class opik.message_processing.emulation.models.ExperimentItemModel(id: str, experiment_id: str, trace_id: str, dataset_item_id: str)¶

Bases: object

Represents an experiment item model that links a trace to a dataset item in an experiment.

id¶

Unique identifier for the experiment item.

Type:: str

experiment_id¶

The ID of the experiment this item belongs to.

Type:: str

trace_id¶

The ID of the trace associated with this experiment item.

Type:: str

dataset_item_id¶

The ID of the dataset item associated with this experiment item.

Type:: str

__init__(id: str, experiment_id: str, trace_id: str, dataset_item_id: str) → None¶

Description¶

ExperimentItemModel links a trace produced during evaluation to the dataset item and experiment run that generated it. The SDK instantiates these records for you while opik.evaluate() or experiment reruns execute; most users interact with them through ScoreResult.metadata rather than constructing instances manually. Metrics that analyse evaluation outputs can rely on this structure to connect results back to source data.

Attributes¶

opik.message_processing.emulation.models.id: str: Unique identifier for the experiment item record.

opik.message_processing.emulation.models.experiment_id: str: Identifier of the experiment that produced this item.

opik.message_processing.emulation.models.trace_id: str: Identifier of the trace logged during the evaluation run.

opik.message_processing.emulation.models.dataset_item_id: str: Identifier of the dataset item evaluated in this experiment result.

Usage Example¶

The SDK populates ExperimentItemModel instances automatically while running evaluations:

from opik.message_processing.emulation.models import ExperimentItemModel

experiment_item = ExperimentItemModel(
    id="exp_item_001",
    experiment_id="exp_123",
    trace_id="trace_abc",
    dataset_item_id="dataset_item_xyz",
)

ExperimentItemModel¶

Description¶

Attributes¶

Usage Example¶

See Also¶