GuardrailsSettingsCreateRequest

Properties

Name	Type	Description	Notes
action	str	What to do when detecting PII, either "redact" or "fail" ("allow" would keep PII intact). Guardrails models always fail upon detecting safety violations.	[optional] [default to ‘redact’]
sensitive	bool	Whether to include the most sensitive PII entities like SSN, bank account info.	[optional] [default to True]
non_sensitive	bool	Whether to include all non-sensitive PII entities, such as IP addresses, locations, names, e-mail addresses etc.	[optional] [default to True]
all_guardrails	bool	Whether to include all possible entities for prompt guard and guardrails models, or just system defaults.	[optional] [default to True]
guardrails_settings	GuardrailsSettings	Existing guardrails settings (e.g., from collection settings) to obtain guardrails entities, guardrails_entities_to_flag, column redaction custom_pii_entities, column_redaction_pii_to_flag from instead of system defaults	[optional]

Example

from h2ogpte.rest_async.models.guardrails_settings_create_request import GuardrailsSettingsCreateRequest

# TODO update the JSON string below
json = "{}"
# create an instance of GuardrailsSettingsCreateRequest from a JSON string
guardrails_settings_create_request_instance = GuardrailsSettingsCreateRequest.from_json(json)
# print the JSON string representation of the object
print(GuardrailsSettingsCreateRequest.to_json())

# convert the object into a dict
guardrails_settings_create_request_dict = guardrails_settings_create_request_instance.to_dict()
# create an instance of GuardrailsSettingsCreateRequest from a dict
guardrails_settings_create_request_from_dict = GuardrailsSettingsCreateRequest.from_dict(guardrails_settings_create_request_dict)