DeepchecksLLMClient.get_data

DeepchecksLLMClient.get_data(app_name: str, version_name: str, environment: EnvType | str, return_topics: bool = True, return_annotation_data: bool = True, return_input_props: bool = True, return_output_props: bool = True, return_custom_props: bool = True, return_llm_props: bool = True, start_time: datetime | int | None = None, end_time: datetime | int | None = None, return_similarities: bool = False, user_interaction_ids: List[str] | None = None) → DataFrame | None

Fetch all the interactions from the specified environment (PROD/EVAL) as a pandas DataFrame.

Parameters:

app_namestr

Application name

version_namestr

Name of application version

environmentEnvType | str

The environment type from which to fetch interactions. This can be either “PROD” or “EVAL”.

return_annotation_databool, optional

Whether to include annotation info in the data.

return_topicsbool, optional

Whether to include the topic in the data.

return_input_propsbool, optional

Whether to include input properties in the data.

return_output_propsbool, optional

Whether to include the output properties in the data.

return_custom_propsbool, optional

Whether to include custom properties in the data.

return_llm_propsbool, optional

Whether to include LLM properties in the data.

return_similaritiesbool, optional

Whether to include similarities in the data.

start_timedatetime | int | None, optional

The start time from which to fetch interactions. This can be a datetime object or an integer. If not provided, interactions will be fetched from the beginning.

end_timedatetime | int | None, optional

The end time until which to fetch interactions. This can be a datetime object or an integer. If not provided, interactions will be fetched up to the most recent.

user_interaction_ids: list | None, optional

user interactions ids to include in the data.

Returns:

pd.DataFrame | None

A pandas DataFrame containing the interactions, or None in case of a problem retrieving the data.