Class GoldenExpectation (0.7.1) 

GoldenExpectation(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Represents a single, checkable requirement.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

Attributes
Name Description
tool_call google.cloud.ces_v1beta.types.ToolCall
Optional. Check that a specific tool was called with the parameters. This field is a member of oneof_ condition.
tool_response google.cloud.ces_v1beta.types.ToolResponse
Optional. Check that a specific tool had the expected response. This field is a member of oneof_ condition.
agent_response google.cloud.ces_v1beta.types.Message
Optional. Check that the agent responded with the correct response. The role "agent" is implied. This field is a member of oneof_ condition.
agent_transfer google.cloud.ces_v1beta.types.AgentTransfer
Optional. Check that the agent transferred the conversation to a different agent. This field is a member of oneof_ condition.
updated_variables google.protobuf.struct_pb2.Struct
Optional. Check that the agent updated the session variables to the expected values. Used to also capture agent variable updates for golden evals. This field is a member of oneof_ condition.
mock_tool_response google.cloud.ces_v1beta.types.ToolResponse
Optional. The tool response to mock, with the parameters of interest specified. Any parameters not specified will be hallucinated by the LLM. This field is a member of oneof_ condition.
no_tool_calls bool
Optional. Check that no tools were called during this turn. This field is a member of oneof_ condition.
note str
Optional. A note for this requirement, useful in reporting when specific checks fail. E.g., "Check_Payment_Tool_Called".
skip_evaluation bool
Optional. If set to true, this specific expectation will not be evaluated.
expectation_level_metrics_thresholds_override google.cloud.ces_v1beta.types.EvaluationMetricsThresholds.GoldenEvaluationMetricsThresholds.ExpectationLevelMetricsThresholds
Optional. Overrides metrics at the step level.
agent_response_semantic_similarity_metrics_config_override google.cloud.ces_v1beta.types.EvaluationMetricsConfig.SemanticSimilarityMetricsConfig
Optional. Overrides for agent_response semantic similarity metrics.
agent_response_hallucination_metrics_config_override google.cloud.ces_v1beta.types.EvaluationMetricsConfig.HallucinationMetricsConfig
Optional. Overrides for agent_response hallucination metrics.
comparison_type google.cloud.ces_v1beta.types.EvaluationMetricsConfig.ComparisonType
Optional. The comparison type to use for the expectation check.