ContentModerationGuardrailConfig¶
- class oci.generative_ai_agent.models.ContentModerationGuardrailConfig(**kwargs)¶
Bases:
objectThe configuration details about whether to apply the content moderation feature to input and output. Content moderation removes toxic and biased content from responses. It is recommended to use content moderation.
Attributes:
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig.
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig.
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig.
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig.
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig.
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig.
Gets the input_guardrail_mode of this ContentModerationGuardrailConfig.
Gets the output_guardrail_mode of this ContentModerationGuardrailConfig.
Methods:
__init__(**kwargs)Initializes a new ContentModerationGuardrailConfig object with values from keyword arguments.
- INPUT_GUARDRAIL_MODE_BLOCK = 'BLOCK'¶
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “BLOCK”
- INPUT_GUARDRAIL_MODE_DISABLE = 'DISABLE'¶
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “DISABLE”
- INPUT_GUARDRAIL_MODE_INFORM = 'INFORM'¶
A constant which can be used with the input_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “INFORM”
- OUTPUT_GUARDRAIL_MODE_BLOCK = 'BLOCK'¶
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “BLOCK”
- OUTPUT_GUARDRAIL_MODE_DISABLE = 'DISABLE'¶
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “DISABLE”
- OUTPUT_GUARDRAIL_MODE_INFORM = 'INFORM'¶
A constant which can be used with the output_guardrail_mode property of a ContentModerationGuardrailConfig. This constant has a value of “INFORM”
- __init__(**kwargs)¶
Initializes a new ContentModerationGuardrailConfig object with values from keyword arguments. The following keyword arguments are supported (corresponding to the getters/setters of this class):
- Parameters
input_guardrail_mode (str) – The value to assign to the input_guardrail_mode property of this ContentModerationGuardrailConfig. Allowed values for this property are: “DISABLE”, “BLOCK”, “INFORM”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.
output_guardrail_mode (str) – The value to assign to the output_guardrail_mode property of this ContentModerationGuardrailConfig. Allowed values for this property are: “DISABLE”, “BLOCK”, “INFORM”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.
- property input_guardrail_mode¶
Gets the input_guardrail_mode of this ContentModerationGuardrailConfig. An input guardrail mode for content moderation.
Allowed values for this property are: “DISABLE”, “BLOCK”, “INFORM”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.
- Returns
The input_guardrail_mode of this ContentModerationGuardrailConfig.
- Return type
str
- property output_guardrail_mode¶
Gets the output_guardrail_mode of this ContentModerationGuardrailConfig. An output guardrail mode for content moderation.
Allowed values for this property are: “DISABLE”, “BLOCK”, “INFORM”, ‘UNKNOWN_ENUM_VALUE’. Any unrecognized values returned by a service will be mapped to ‘UNKNOWN_ENUM_VALUE’.
- Returns
The output_guardrail_mode of this ContentModerationGuardrailConfig.
- Return type
str