Gemini Enterprise for Customer Experience v1 API - Class Guardrail.Types.LlmPolicy (1.0.0-beta01)

public sealed class Guardrail.Types.LlmPolicy : IMessage<Guardrail.Types.LlmPolicy>, IEquatable<Guardrail.Types.LlmPolicy>, IDeepCloneable<Guardrail.Types.LlmPolicy>, IBufferMessage, IMessage

Reference documentation and code samples for the Gemini Enterprise for Customer Experience v1 API class Guardrail.Types.LlmPolicy.

Guardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.

Inheritance

object > Guardrail.Types.LlmPolicy

Implements

IMessageGuardrailTypesLlmPolicy, IEquatableGuardrailTypesLlmPolicy, IDeepCloneableGuardrailTypesLlmPolicy, IBufferMessage, IMessage

Inherited Members

object.GetHashCode()

object.GetType()

object.ToString()

Namespace

Google.Cloud.Ces.V1

Assembly

Google.Cloud.Ces.V1.dll

Constructors

LlmPolicy()

public LlmPolicy()

LlmPolicy(LlmPolicy)

public LlmPolicy(Guardrail.Types.LlmPolicy other)

Parameter
Name	Description
other	GuardrailTypesLlmPolicy

Properties

AllowShortUtterance

public bool AllowShortUtterance { get; set; }

Optional. By default, the LLM policy check is bypassed for short utterances. Enabling this setting applies the policy check to all utterances, including those that would normally be skipped.

Property Value
Type	Description
bool

FailOpen

public bool FailOpen { get; set; }

Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.

Property Value
Type	Description
bool

MaxConversationMessages

public int MaxConversationMessages { get; set; }

Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.

Property Value
Type	Description
int

ModelSettings

public ModelSettings ModelSettings { get; set; }

Optional. Model settings.

Property Value
Type	Description
ModelSettings

PolicyScope

public Guardrail.Types.LlmPolicy.Types.PolicyScope PolicyScope { get; set; }

Required. Defines when to apply the policy check during the conversation. If set to POLICY_SCOPE_UNSPECIFIED, the policy will be applied to the user input. When applying the policy to the agent response, additional latency will be introduced before the agent can respond.

Property Value
Type	Description
GuardrailTypesLlmPolicyTypesPolicyScope

Prompt

public string Prompt { get; set; }

Required. Policy prompt.

Property Value
Type	Description
string