public static final class Guardrail.LlmPolicy.Builder extends GeneratedMessage.Builder<Guardrail.LlmPolicy.Builder> implements Guardrail.LlmPolicyOrBuilderGuardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.
Protobuf type google.cloud.ces.v1.Guardrail.LlmPolicy
Inheritance
java.lang.Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessage.Builder > Guardrail.LlmPolicy.BuilderImplements
Guardrail.LlmPolicyOrBuilderStatic Methods
getDescriptor()
public static final Descriptors.Descriptor getDescriptor()| Returns | |
|---|---|
| Type | Description |
Descriptor |
|
Methods
build()
public Guardrail.LlmPolicy build()| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy |
|
buildPartial()
public Guardrail.LlmPolicy buildPartial()| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy |
|
clear()
public Guardrail.LlmPolicy.Builder clear()| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
clearAllowShortUtterance()
public Guardrail.LlmPolicy.Builder clearAllowShortUtterance()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.
bool allow_short_utterance = 6 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
clearFailOpen()
public Guardrail.LlmPolicy.Builder clearFailOpen()Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.
bool fail_open = 5 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
clearMaxConversationMessages()
public Guardrail.LlmPolicy.Builder clearMaxConversationMessages()Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.
int32 max_conversation_messages = 1 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
clearModelSettings()
public Guardrail.LlmPolicy.Builder clearModelSettings()Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
clearPolicyScope()
public Guardrail.LlmPolicy.Builder clearPolicyScope() 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.
.google.cloud.ces.v1.Guardrail.LlmPolicy.PolicyScope policy_scope = 4 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
clearPrompt()
public Guardrail.LlmPolicy.Builder clearPrompt()Required. Policy prompt.
string prompt = 3 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
getAllowShortUtterance()
public boolean getAllowShortUtterance()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.
bool allow_short_utterance = 6 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
boolean |
The allowShortUtterance. |
getDefaultInstanceForType()
public Guardrail.LlmPolicy getDefaultInstanceForType()| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy |
|
getDescriptorForType()
public Descriptors.Descriptor getDescriptorForType()| Returns | |
|---|---|
| Type | Description |
Descriptor |
|
getFailOpen()
public boolean getFailOpen()Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.
bool fail_open = 5 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
boolean |
The failOpen. |
getMaxConversationMessages()
public int getMaxConversationMessages()Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.
int32 max_conversation_messages = 1 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
int |
The maxConversationMessages. |
getModelSettings()
public ModelSettings getModelSettings()Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
ModelSettings |
The modelSettings. |
getModelSettingsBuilder()
public ModelSettings.Builder getModelSettingsBuilder()Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
ModelSettings.Builder |
|
getModelSettingsOrBuilder()
public ModelSettingsOrBuilder getModelSettingsOrBuilder()Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
ModelSettingsOrBuilder |
|
getPolicyScope()
public Guardrail.LlmPolicy.PolicyScope getPolicyScope() 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.
.google.cloud.ces.v1.Guardrail.LlmPolicy.PolicyScope policy_scope = 4 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.PolicyScope |
The policyScope. |
getPolicyScopeValue()
public int getPolicyScopeValue() 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.
.google.cloud.ces.v1.Guardrail.LlmPolicy.PolicyScope policy_scope = 4 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
int |
The enum numeric value on the wire for policyScope. |
getPrompt()
public String getPrompt()Required. Policy prompt.
string prompt = 3 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
String |
The prompt. |
getPromptBytes()
public ByteString getPromptBytes()Required. Policy prompt.
string prompt = 3 [(.google.api.field_behavior) = REQUIRED];
| Returns | |
|---|---|
| Type | Description |
ByteString |
The bytes for prompt. |
hasModelSettings()
public boolean hasModelSettings()Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Returns | |
|---|---|
| Type | Description |
boolean |
Whether the modelSettings field is set. |
internalGetFieldAccessorTable()
protected GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()| Returns | |
|---|---|
| Type | Description |
FieldAccessorTable |
|
isInitialized()
public final boolean isInitialized()| Returns | |
|---|---|
| Type | Description |
boolean |
|
mergeFrom(Guardrail.LlmPolicy other)
public Guardrail.LlmPolicy.Builder mergeFrom(Guardrail.LlmPolicy other)| Parameter | |
|---|---|
| Name | Description |
other |
Guardrail.LlmPolicy |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public Guardrail.LlmPolicy.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)| Parameters | |
|---|---|
| Name | Description |
input |
CodedInputStream |
extensionRegistry |
ExtensionRegistryLite |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
| Exceptions | |
|---|---|
| Type | Description |
IOException |
|
mergeFrom(Message other)
public Guardrail.LlmPolicy.Builder mergeFrom(Message other)| Parameter | |
|---|---|
| Name | Description |
other |
Message |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
mergeModelSettings(ModelSettings value)
public Guardrail.LlmPolicy.Builder mergeModelSettings(ModelSettings value)Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
value |
ModelSettings |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
setAllowShortUtterance(boolean value)
public Guardrail.LlmPolicy.Builder setAllowShortUtterance(boolean value)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.
bool allow_short_utterance = 6 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
value |
booleanThe allowShortUtterance to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setFailOpen(boolean value)
public Guardrail.LlmPolicy.Builder setFailOpen(boolean value)Optional. If an error occurs during the policy check, fail open and do not trigger the guardrail.
bool fail_open = 5 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
value |
booleanThe failOpen to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setMaxConversationMessages(int value)
public Guardrail.LlmPolicy.Builder setMaxConversationMessages(int value)Optional. When checking this policy, consider the last 'n' messages in the conversation. When not set a default value of 10 will be used.
int32 max_conversation_messages = 1 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
value |
intThe maxConversationMessages to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setModelSettings(ModelSettings value)
public Guardrail.LlmPolicy.Builder setModelSettings(ModelSettings value)Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
value |
ModelSettings |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
setModelSettings(ModelSettings.Builder builderForValue)
public Guardrail.LlmPolicy.Builder setModelSettings(ModelSettings.Builder builderForValue)Optional. Model settings.
.google.cloud.ces.v1.ModelSettings model_settings = 2 [(.google.api.field_behavior) = OPTIONAL];
| Parameter | |
|---|---|
| Name | Description |
builderForValue |
ModelSettings.Builder |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
|
setPolicyScope(Guardrail.LlmPolicy.PolicyScope value)
public Guardrail.LlmPolicy.Builder setPolicyScope(Guardrail.LlmPolicy.PolicyScope value) 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.
.google.cloud.ces.v1.Guardrail.LlmPolicy.PolicyScope policy_scope = 4 [(.google.api.field_behavior) = REQUIRED];
| Parameter | |
|---|---|
| Name | Description |
value |
Guardrail.LlmPolicy.PolicyScopeThe policyScope to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setPolicyScopeValue(int value)
public Guardrail.LlmPolicy.Builder setPolicyScopeValue(int value) 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.
.google.cloud.ces.v1.Guardrail.LlmPolicy.PolicyScope policy_scope = 4 [(.google.api.field_behavior) = REQUIRED];
| Parameter | |
|---|---|
| Name | Description |
value |
intThe enum numeric value on the wire for policyScope to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setPrompt(String value)
public Guardrail.LlmPolicy.Builder setPrompt(String value)Required. Policy prompt.
string prompt = 3 [(.google.api.field_behavior) = REQUIRED];
| Parameter | |
|---|---|
| Name | Description |
value |
StringThe prompt to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |
setPromptBytes(ByteString value)
public Guardrail.LlmPolicy.Builder setPromptBytes(ByteString value)Required. Policy prompt.
string prompt = 3 [(.google.api.field_behavior) = REQUIRED];
| Parameter | |
|---|---|
| Name | Description |
value |
ByteStringThe bytes for prompt to set. |
| Returns | |
|---|---|
| Type | Description |
Guardrail.LlmPolicy.Builder |
This builder for chaining. |