Class RagFileParsingConfig.LlmParser.Builder (1.43.0)

public static final class RagFileParsingConfig.LlmParser.Builder extends GeneratedMessage.Builder<RagFileParsingConfig.LlmParser.Builder> implements RagFileParsingConfig.LlmParserOrBuilder

Specifies the advanced parsing for RagFiles.

Protobuf type google.cloud.vertexai.v1.RagFileParsingConfig.LlmParser

Static Methods

getDescriptor()

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

Methods

build()

public RagFileParsingConfig.LlmParser build()
Returns
Type Description
RagFileParsingConfig.LlmParser

buildPartial()

public RagFileParsingConfig.LlmParser buildPartial()
Returns
Type Description
RagFileParsingConfig.LlmParser

clear()

public RagFileParsingConfig.LlmParser.Builder clear()
Returns
Type Description
RagFileParsingConfig.LlmParser.Builder
Overrides

clearCustomParsingPrompt()

public RagFileParsingConfig.LlmParser.Builder clearCustomParsingPrompt()

The prompt to use for parsing. If not specified, a default prompt will be used.

string custom_parsing_prompt = 3;

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

clearMaxParsingRequestsPerMin()

public RagFileParsingConfig.LlmParser.Builder clearMaxParsingRequestsPerMin()

The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.

int32 max_parsing_requests_per_min = 2;

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

clearModelName()

public RagFileParsingConfig.LlmParser.Builder clearModelName()

The name of a LLM model used for parsing. Format:

  • projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}

string model_name = 1;

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

getCustomParsingPrompt()

public String getCustomParsingPrompt()

The prompt to use for parsing. If not specified, a default prompt will be used.

string custom_parsing_prompt = 3;

Returns
Type Description
String

The customParsingPrompt.

getCustomParsingPromptBytes()

public ByteString getCustomParsingPromptBytes()

The prompt to use for parsing. If not specified, a default prompt will be used.

string custom_parsing_prompt = 3;

Returns
Type Description
ByteString

The bytes for customParsingPrompt.

getDefaultInstanceForType()

public RagFileParsingConfig.LlmParser getDefaultInstanceForType()
Returns
Type Description
RagFileParsingConfig.LlmParser

getDescriptorForType()

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

getMaxParsingRequestsPerMin()

public int getMaxParsingRequestsPerMin()

The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.

int32 max_parsing_requests_per_min = 2;

Returns
Type Description
int

The maxParsingRequestsPerMin.

getModelName()

public String getModelName()

The name of a LLM model used for parsing. Format:

  • projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}

string model_name = 1;

Returns
Type Description
String

The modelName.

getModelNameBytes()

public ByteString getModelNameBytes()

The name of a LLM model used for parsing. Format:

  • projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}

string model_name = 1;

Returns
Type Description
ByteString

The bytes for modelName.

internalGetFieldAccessorTable()

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

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeFrom(RagFileParsingConfig.LlmParser other)

public RagFileParsingConfig.LlmParser.Builder mergeFrom(RagFileParsingConfig.LlmParser other)
Parameter
Name Description
other RagFileParsingConfig.LlmParser
Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

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

mergeFrom(Message other)

public RagFileParsingConfig.LlmParser.Builder mergeFrom(Message other)
Parameter
Name Description
other Message
Returns
Type Description
RagFileParsingConfig.LlmParser.Builder
Overrides

setCustomParsingPrompt(String value)

public RagFileParsingConfig.LlmParser.Builder setCustomParsingPrompt(String value)

The prompt to use for parsing. If not specified, a default prompt will be used.

string custom_parsing_prompt = 3;

Parameter
Name Description
value String

The customParsingPrompt to set.

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

setCustomParsingPromptBytes(ByteString value)

public RagFileParsingConfig.LlmParser.Builder setCustomParsingPromptBytes(ByteString value)

The prompt to use for parsing. If not specified, a default prompt will be used.

string custom_parsing_prompt = 3;

Parameter
Name Description
value ByteString

The bytes for customParsingPrompt to set.

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

setMaxParsingRequestsPerMin(int value)

public RagFileParsingConfig.LlmParser.Builder setMaxParsingRequestsPerMin(int value)

The maximum number of requests the job is allowed to make to the LLM model per minute. Consult https://cloud.google.com/vertex-ai/generative-ai/docs/quotas and your document size to set an appropriate value here. If unspecified, a default value of 5000 QPM would be used.

int32 max_parsing_requests_per_min = 2;

Parameter
Name Description
value int

The maxParsingRequestsPerMin to set.

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

setModelName(String value)

public RagFileParsingConfig.LlmParser.Builder setModelName(String value)

The name of a LLM model used for parsing. Format:

  • projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}

string model_name = 1;

Parameter
Name Description
value String

The modelName to set.

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.

setModelNameBytes(ByteString value)

public RagFileParsingConfig.LlmParser.Builder setModelNameBytes(ByteString value)

The name of a LLM model used for parsing. Format:

  • projects/{project_id}/locations/{location}/publishers/{publisher}/models/{model}

string model_name = 1;

Parameter
Name Description
value ByteString

The bytes for modelName to set.

Returns
Type Description
RagFileParsingConfig.LlmParser.Builder

This builder for chaining.