Scenario(mapping=None, *, ignore_unknown_fields=False, **kwargs)The config for a scenario
Attributes |
|
|---|---|
| Name | Description |
task |
str
Required. The task to be targeted by the scenario. |
user_facts |
MutableSequence[google.cloud.ces_v1beta.types.Evaluation.Scenario.UserFact]
Optional. The user facts to be used by the scenario. |
max_turns |
int
Optional. The maximum number of turns to simulate. If not specified, the simulation will continue until the task is complete. |
rubrics |
MutableSequence[str]
Required. The rubrics to score the scenario against. |
scenario_expectations |
MutableSequence[google.cloud.ces_v1beta.types.Evaluation.ScenarioExpectation]
Required. The ScenarioExpectations to evaluate the conversation produced by the user simulation. |
variable_overrides |
google.protobuf.struct_pb2.Struct
Optional. Variables / Session Parameters as context for the session, keyed by variable names. Members of this struct will override any default values set by the system. Note, these are different from user facts, which are facts known to the user. Variables are parameters known to the agent: i.e. MDN (phone number) passed by the telephony system. |
task_completion_behavior |
google.cloud.ces_v1beta.types.Evaluation.Scenario.TaskCompletionBehavior
Optional. Deprecated. Use user_goal_behavior instead. |
user_goal_behavior |
google.cloud.ces_v1beta.types.Evaluation.Scenario.UserGoalBehavior
Optional. The expected behavior of the user goal. |
evaluation_expectations |
MutableSequence[str]
Optional. The evaluation expectations to evaluate the conversation produced by the simulation against. Format: projects/{project}/locations/{location}/apps/{app}/evaluationExpectations/{evaluationExpectation}
|
Classes
TaskCompletionBehavior
TaskCompletionBehavior(value)The expected behavior of the user task. This is used to determine whether the scenario is successful.
UserFact
UserFact(mapping=None, *, ignore_unknown_fields=False, **kwargs)Facts about the user as a key value pair.
UserGoalBehavior
UserGoalBehavior(value)The expected behavior of the user goal. This is used to determine whether the scenario is successful.