DeepchecksLLMClient.update_interaction

DeepchecksLLMClient.update_interaction(app_name: str, version_name: str, user_interaction_id: str, annotation: AnnotationType | str | None = None, annotation_reason: str | None = None, custom_props: Dict[str, Any] | None = None, steps: List[Step] = None, information_retrieval: List[str] | str = None, input: str | None = None, output: str | None = None, is_completed: bool | None = None, finished_at: datetime | float = None)

Update a specific interaction by its user_interaction_id.

Parameters:

app_namestr

Application name

version_name

Name of the version to which this interaction belongs

user_interaction_id

Unique id of the interaction to update

annotationAnnotationType or str

Could be one of AnnotationType or ‘good’, ‘bad’, ‘unknown’

annotation_reason: str

String that explains the reason for the annotation

custom_props: dict

Dictionary of custom properties for interaction

steps: list of Step

List of steps taken during the interaction. New steps will be added to existing ones for previously incomplete interactions. Cannot be changed for completed interactions

information_retrievalstr or list of str

Information retrieval. New data will be added to existing ones for previously incomplete interactions. Cannot be changed for completed interactions

input: str or None

Input data. Old value will be overridden by the new value. Note that once interactions are marked as completed, this value cannot be changed.

output: str or None

Output data. Old value will be overridden by the new value. It cannot be modified for completed interactions.

is_completed: bool or None.

Completed interactions will be shown in the system, and cannot be further modified except for annotations, topics and custom properties. Interaction completeness status will be not changed if None is sent

finished_atdatetime or float

Timestamp the interaction finished at. Datetime format is deprecated, use timestamp instead

Returns

——-

None