Class: Google::Apis::AiplatformV1beta1::GoogleCloudAiplatformV1beta1RagFileParsingConfigLlmParser

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1beta1/classes.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb,
lib/google/apis/aiplatform_v1beta1/representations.rb

Overview

Specifies the LLM parsing for RagFiles.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1beta1RagFileParsingConfigLlmParser

Returns a new instance of GoogleCloudAiplatformV1beta1RagFileParsingConfigLlmParser.



37455
37456
37457
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37455

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#custom_parsing_prompt ⇒ String

The prompt to use for parsing. If not specified, a default prompt will be used. Corresponds to the JSON property customParsingPrompt

Returns:

  • (String) 


37430
37431
37432
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37430

def custom_parsing_prompt
  @custom_parsing_prompt
end

#global_max_parsing_requests_per_min ⇒ Fixnum

The maximum number of requests the job is allowed to make to the LLM model per minute in this project. Consult https://cloud.google.com/vertex-ai/generative- ai/docs/quotas and your document size to set an appropriate value here. If this value is not specified, max_parsing_requests_per_min will be used by indexing pipeline job as the global limit. Corresponds to the JSON property globalMaxParsingRequestsPerMin

Returns:

  • (Fixnum) 


37439
37440
37441
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37439

def global_max_parsing_requests_per_min
  @global_max_parsing_requests_per_min
end

#max_parsing_requests_per_min ⇒ Fixnum

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. Corresponds to the JSON property maxParsingRequestsPerMin

Returns:

  • (Fixnum) 


37447
37448
37449
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37447

def max_parsing_requests_per_min
  @max_parsing_requests_per_min
end

#model_name ⇒ String

The name of a LLM model used for parsing. Format: * projects/project_id/ locations/location/publishers/publisher/models/model` Corresponds to the JSON propertymodelName`

Returns:

  • (String) 


37453
37454
37455
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37453

def model_name
  @model_name
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



37460
37461
37462
37463
37464
37465
 
# File 'lib/google/apis/aiplatform_v1beta1/classes.rb', line 37460

def update!(**args)
  @custom_parsing_prompt = args[:custom_parsing_prompt] if args.key?(:custom_parsing_prompt)
  @global_max_parsing_requests_per_min = args[:global_max_parsing_requests_per_min] if args.key?(:global_max_parsing_requests_per_min)
  @max_parsing_requests_per_min = args[:max_parsing_requests_per_min] if args.key?(:max_parsing_requests_per_min)
  @model_name = args[:model_name] if args.key?(:model_name)
end