Class: Openlayer::Models::InferencePipelines::DataStreamParams::Config::LlmData::Prompt

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openlayer/models/inference_pipelines/data_stream_params.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, inspect, #inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(output_column_name: , context_column_name: nil, cost_column_name: nil, ground_truth_column_name: nil, inference_id_column_name: nil, input_variable_names: nil, latency_column_name: nil, metadata: nil, num_of_token_column_name: nil, prompt: nil, question_column_name: nil, session_id_column_name: nil, timestamp_column_name: nil, user_id_column_name: nil) ⇒ Object

Some parameter documentations has been truncated, see Openlayer::Models::InferencePipelines::DataStreamParams::Config::LlmData for more details.

Parameters:

  • output_column_name (String) (defaults to: ) —

    Name of the column with the model outputs.

  • context_column_name (String) (defaults to: nil) —

    Name of the column with the context retrieved. Applies to RAG use cases. Providi

  • cost_column_name (String) (defaults to: nil) —

    Name of the column with the cost associated with each row.

  • ground_truth_column_name (String) (defaults to: nil) —

    Name of the column with the ground truths.

  • inference_id_column_name (String) (defaults to: nil) —

    Name of the column with the inference ids. This is useful if you want to update

  • input_variable_names (Array<String>) (defaults to: nil) —

    Array of input variable names. Each input variable should be a dataset column.

  • latency_column_name (String) (defaults to: nil) —

    Name of the column with the latencies.

  • metadata (Object) (defaults to: nil) —

    Object with metadata.

  • num_of_token_column_name (String, nil) (defaults to: nil) —

    Name of the column with the total number of tokens.

  • prompt (Array<Openlayer::Models::InferencePipelines::DataStreamParams::Config::LlmData::Prompt>) (defaults to: nil) —

    Prompt for the LLM.

  • question_column_name (String) (defaults to: nil) —

    Name of the column with the questions. Applies to RAG use cases. Providing the q

  • session_id_column_name (String, nil) (defaults to: nil) —

    Name of the column with the session id.

  • timestamp_column_name (String) (defaults to: nil) —

    Name of the column with the timestamps. Timestamps must be in UNIX sec format. I

  • user_id_column_name (String, nil) (defaults to: nil) —

    Name of the column with the user id.



175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
 
# File 'lib/openlayer/models/inference_pipelines/data_stream_params.rb', line 175

class Prompt < Openlayer::Internal::Type::BaseModel
  # @!attribute content
  #   Content of the prompt.
  #
  #   @return [String, nil]
  optional :content, String

  # @!attribute role
  #   Role of the prompt.
  #
  #   @return [String, nil]
  optional :role, String

  # @!method initialize(content: nil, role: nil)
  #   @param content [String] Content of the prompt.
  #
  #   @param role [String] Role of the prompt.
end

Instance Attribute Details

#content ⇒ String?

Content of the prompt.

Returns:

  • (String, nil) 


180
 
# File 'lib/openlayer/models/inference_pipelines/data_stream_params.rb', line 180

optional :content, String

#role ⇒ String?

Role of the prompt.

Returns:

  • (String, nil) 


186
 
# File 'lib/openlayer/models/inference_pipelines/data_stream_params.rb', line 186

optional :role, String