Class Generator.ModelParameter.Builder (0.65.0)

public static final class Generator.ModelParameter.Builder extends GeneratedMessageV3.Builder<Generator.ModelParameter.Builder> implements Generator.ModelParameterOrBuilder

Parameters to be passed to the LLM. If not set, default values will be used.

Protobuf type google.cloud.dialogflow.cx.v3.Generator.ModelParameter

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public Generator.ModelParameter.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

build()

public Generator.ModelParameter build()
Returns
Type Description
Generator.ModelParameter

buildPartial()

public Generator.ModelParameter buildPartial()
Returns
Type Description
Generator.ModelParameter

clear()

public Generator.ModelParameter.Builder clear()
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

clearField(Descriptors.FieldDescriptor field)

public Generator.ModelParameter.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
Name Description
field FieldDescriptor
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

clearMaxDecodeSteps()

public Generator.ModelParameter.Builder clearMaxDecodeSteps()

The maximum number of tokens to generate.

optional int32 max_decode_steps = 2;

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

public Generator.ModelParameter.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
Name Description
oneof OneofDescriptor
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

clearTemperature()

public Generator.ModelParameter.Builder clearTemperature()

The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.

optional float temperature = 1;

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

clearTopK()

public Generator.ModelParameter.Builder clearTopK()

If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.

optional int32 top_k = 4;

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

clearTopP()

public Generator.ModelParameter.Builder clearTopP()

If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.

optional float top_p = 3;

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

clone()

public Generator.ModelParameter.Builder clone()
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

getDefaultInstanceForType()

public Generator.ModelParameter getDefaultInstanceForType()
Returns
Type Description
Generator.ModelParameter

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
Type Description
Descriptor
Overrides

getMaxDecodeSteps()

public int getMaxDecodeSteps()

The maximum number of tokens to generate.

optional int32 max_decode_steps = 2;

Returns
Type Description
int

The maxDecodeSteps.

getTemperature()

public float getTemperature()

The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.

optional float temperature = 1;

Returns
Type Description
float

The temperature.

getTopK()

public int getTopK()

If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.

optional int32 top_k = 4;

Returns
Type Description
int

The topK.

getTopP()

public float getTopP()

If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.

optional float top_p = 3;

Returns
Type Description
float

The topP.

hasMaxDecodeSteps()

public boolean hasMaxDecodeSteps()

The maximum number of tokens to generate.

optional int32 max_decode_steps = 2;

Returns
Type Description
boolean

Whether the maxDecodeSteps field is set.

hasTemperature()

public boolean hasTemperature()

The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.

optional float temperature = 1;

Returns
Type Description
boolean

Whether the temperature field is set.

hasTopK()

public boolean hasTopK()

If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.

optional int32 top_k = 4;

Returns
Type Description
boolean

Whether the topK field is set.

hasTopP()

public boolean hasTopP()

If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.

optional float top_p = 3;

Returns
Type Description
boolean

Whether the topP field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeFrom(Generator.ModelParameter other)

public Generator.ModelParameter.Builder mergeFrom(Generator.ModelParameter other)
Parameter
Name Description
other Generator.ModelParameter
Returns
Type Description
Generator.ModelParameter.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public Generator.ModelParameter.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Generator.ModelParameter.Builder
Overrides
Exceptions
Type Description
IOException

mergeFrom(Message other)

public Generator.ModelParameter.Builder mergeFrom(Message other)
Parameter
Name Description
other Message
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final Generator.ModelParameter.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

setField(Descriptors.FieldDescriptor field, Object value)

public Generator.ModelParameter.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

setMaxDecodeSteps(int value)

public Generator.ModelParameter.Builder setMaxDecodeSteps(int value)

The maximum number of tokens to generate.

optional int32 max_decode_steps = 2;

Parameter
Name Description
value int

The maxDecodeSteps to set.

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public Generator.ModelParameter.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
Name Description
field FieldDescriptor
index int
value Object
Returns
Type Description
Generator.ModelParameter.Builder
Overrides

setTemperature(float value)

public Generator.ModelParameter.Builder setTemperature(float value)

The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.

optional float temperature = 1;

Parameter
Name Description
value float

The temperature to set.

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

setTopK(int value)

public Generator.ModelParameter.Builder setTopK(int value)

If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.

optional int32 top_k = 4;

Parameter
Name Description
value int

The topK to set.

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

setTopP(float value)

public Generator.ModelParameter.Builder setTopP(float value)

If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.

optional float top_p = 3;

Parameter
Name Description
value float

The topP to set.

Returns
Type Description
Generator.ModelParameter.Builder

This builder for chaining.

setUnknownFields(UnknownFieldSet unknownFields)

public final Generator.ModelParameter.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
Generator.ModelParameter.Builder
Overrides