trulens.core.metric.selector¶

trulens.core.metric.selector ¶

Classes¶

Selector `dataclass` ¶

Attributes¶

is_dataset_selector `property` ¶

is_dataset_selector: bool

Whether this selector reads from a tabular dataset column.

Functions¶

from_column `staticmethod` ¶

from_column(
    column_name: str,
    *,
    collect_list: bool = True,
    ignore_none_values: bool = False
) -> Selector

Returns a Selector that reads its value from a dataset column.

This is used for batch/offline evaluation with BatchEvaluator, where metrics are run over a pre-collected dataset (a pandas DataFrame or a list of dicts) instead of over spans produced by a live app. Batch results are returned in-memory only and are not persisted to the dashboard; for dashboard-visible evaluation of pre-collected data, use Run with mode=Mode.LOG_INGESTION.

PARAMETER	DESCRIPTION
`column_name`	The name of the dataset column to read the value from. TYPE: `str`
`collect_list`	Only relevant when the column holds list values. If True (default), the whole list is passed to the metric in a single call. If False, the metric is called once per item in the list and the results are aggregated. TYPE: `bool` DEFAULT: `True`
`ignore_none_values`	If True, skip evaluation for rows where the selected value is None (or missing). TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`Selector`	A `Selector` that selects from the given tabular column.

select_conversation `staticmethod` ¶

select_conversation() -> Selector

Return a selector for ordered records in a conversation.

select_conversation_input `staticmethod` ¶

select_conversation_input() -> Selector

Return a selector for ordered inputs in a conversation.

select_conversation_output `staticmethod` ¶

select_conversation_output() -> Selector

Return a selector for ordered outputs in a conversation.

select_record_input `staticmethod` ¶

select_record_input(
    ignore_none_values: bool = True,
) -> Selector

Returns a Selector that gets the record input.

PARAMETER	DESCRIPTION
`ignore_none_values`	If True, skip evaluation when the input is None. Defaults to True to prevent errors on missing data. TYPE: `bool` DEFAULT: `True`

RETURNS	DESCRIPTION
`Selector`	`Selector` that gets the record input.

select_record_output `staticmethod` ¶

select_record_output(
    ignore_none_values: bool = True,
) -> Selector

Returns a Selector that gets the record output.

PARAMETER	DESCRIPTION
`ignore_none_values`	If True, skip evaluation when the output is None. Defaults to True to prevent errors on missing data. TYPE: `bool` DEFAULT: `True`

RETURNS	DESCRIPTION
`Selector`	`Selector` that gets the record output.

select_context `staticmethod` ¶

select_context(
    *, collect_list: bool, ignore_none_values: bool = True
) -> Selector

Returns a Selector that tries to retrieve contexts.

PARAMETER	DESCRIPTION
`collect_list`	Assuming the returned `Selector` describes a list of strings, whether to call the feedback function: 1. [if collect_list is True]: Once giving the entire list as input. 2. [if collect_list is False]: Separately for each entry in the list and aggregate the results. TYPE: `bool`
`ignore_none_values`	If True, skip evaluation when contexts are None. Defaults to True to prevent errors on missing data. TYPE: `bool` DEFAULT: `True`

RETURNS	DESCRIPTION
`Selector`	`Selector` that tries to retrieve contexts.

Trace `dataclass` ¶

Functions¶

to_compressed_json ¶

to_compressed_json(default_handler: Callable = str) -> str

Convert trace events to compressed JSON format. This reduces token usage while preserving essential information.

PARAMETER	DESCRIPTION
`default_handler`	Function to handle non-serializable objects TYPE: `Callable` DEFAULT: `str`

RETURNS	DESCRIPTION
`str`	Compressed JSON string representation of the trace

trulens.core.metric.selector¶