Class GuardrailLlmPromptSecurity

Guardrail that blocks the conversation if the input is considered unsafe based on the LLM classification.

Inheritance

object

GuardrailLlmPromptSecurity

Implements

IDirectResponseSchema

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Namespace: Google.Apis.CustomerEngagementSuite.v1beta.Data

Assembly: Google.Apis.CustomerEngagementSuite.v1beta.dll

Syntax

public class GuardrailLlmPromptSecurity : IDirectResponseSchema

Properties

CustomPolicy

Optional. Use a user-defined LlmPolicy to configure the security guardrail.

Declaration

[JsonProperty("customPolicy")]
public virtual GuardrailLlmPolicy CustomPolicy { get; set; }

Property Value

Type	Description
GuardrailLlmPolicy

DefaultSettings

Optional. Use the system's predefined default security settings. To select this mode, include an empty 'default_settings' message in the request. The 'default_prompt_template' field within will be populated by the server in the response.

Declaration

[JsonProperty("defaultSettings")]
public virtual GuardrailLlmPromptSecurityDefaultSecuritySettings DefaultSettings { get; set; }

Property Value

Type	Description
GuardrailLlmPromptSecurityDefaultSecuritySettings

ETag

The ETag of the item.

Declaration

public virtual string ETag { get; set; }

Property Value

Type	Description
string

FailOpen

Optional. Determines the behavior when the guardrail encounters an LLM error. - If true: the guardrail is bypassed. - If false (default): the guardrail triggers/blocks. Note: If a custom policy is provided, this field is ignored in favor of the policy's 'fail_open' configuration.

Declaration

[JsonProperty("failOpen")]
public virtual bool? FailOpen { get; set; }

Property Value

Type	Description
bool?

Implements

IDirectResponseSchema