FeedbackCreate#
- class langsmith.schemas.FeedbackCreate[source]#
Bases:
FeedbackBase
Schema used for creating feedback.
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- param comment: str | None = None#
Comment or explanation for the feedback.
- param comparative_experiment_id: UUID | None = None#
If logged within a ‘comparative experiment’, this is the ID of the experiment.
- param correction: str | dict | None = None#
Correction for the run.
- param created_at: datetime | None = None#
The time the feedback was created.
- param extra: Dict | None = None#
The metadata of the feedback.
- param feedback_config: FeedbackConfig | None = None#
- param feedback_group_id: UUID | None = None#
For preference scoring, this group ID is shared across feedbacks for each
run in the group that was being compared.
- param feedback_source: FeedbackSourceBase [Required]#
The source of the feedback.
- param id: UUID [Required]#
The unique ID of the feedback.
- param key: str [Required]#
The metric name, tag, or aspect to provide feedback on.
- param modified_at: datetime | None = None#
The time the feedback was last modified.
- param run_id: UUID | None = None#
The associated run ID this feedback is logged for.
- param score: StrictBool | StrictInt | StrictFloat | None = None#
Value or score to assign the run.
- param session_id: UUID | None = None#
The associated project ID (Session = Project) this feedback is logged for.
- param trace_id: UUID | None = None#
The associated trace ID this feedback is logged for.
- param value: Dict | str | None = None#
The display value, tag or other value for the feedback if not a metric.