Class: Deeprails::Models::DefendSubmitEventParams

Inherits:
Internal::Type::BaseModel show all
Extended by:
Internal::Type::RequestParameters::Converter
Includes:
Internal::Type::RequestParameters
Defined in:
lib/deeprails/models/defend_submit_event_params.rb

Overview

See Also:

Defined Under Namespace

Modules: RunMode Classes: ModelInput

Instance Attribute Summary collapse

Attributes included from Internal::Type::RequestParameters

#request_options

Instance Method Summary collapse

Methods included from Internal::Type::RequestParameters::Converter

dump_request

Methods included from Internal::Type::RequestParameters

included

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(ground_truth: nil, system_prompt: nil, user_prompt: nil) ⇒ Object

A dictionary of inputs sent to the LLM to generate output. The dictionary must contain at least a ‘user_prompt` field or a `system_prompt` field. For the ground_truth_adherence guardrail metric, `ground_truth` should be provided.

Parameters:

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

    The ground truth for evaluating the Ground Truth Adherence guardrail.

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

    The system prompt used to generate the output.

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

    The user prompt used to generate the output.




# File 'lib/deeprails/models/defend_submit_event_params.rb', line 80

Instance Attribute Details

#model_input ⇒ Deeprails::Models::DefendSubmitEventParams::ModelInput

A dictionary of inputs sent to the LLM to generate output. The dictionary must contain at least a ‘user_prompt` field or a `system_prompt` field. For the ground_truth_adherence guardrail metric, `ground_truth` should be provided.

Returns:



16
 
# File 'lib/deeprails/models/defend_submit_event_params.rb', line 16

required :model_input, -> { Deeprails::DefendSubmitEventParams::ModelInput }

#model_output ⇒ String

Output generated by the LLM to be evaluated.

Returns:

  • (String) 


22
 
# File 'lib/deeprails/models/defend_submit_event_params.rb', line 22

required :model_output, String

#model_used ⇒ String

Model ID used to generate the output, like ‘gpt-4o` or `o3`.

Returns:

  • (String) 


28
 
# File 'lib/deeprails/models/defend_submit_event_params.rb', line 28

required :model_used, String

#nametag ⇒ String?

An optional, user-defined tag for the event.

Returns:

  • (String, nil) 


43
 
# File 'lib/deeprails/models/defend_submit_event_params.rb', line 43

optional :nametag, String

#run_mode ⇒ Symbol, Deeprails::Models::DefendSubmitEventParams::RunMode

Run mode for the workflow event. The run mode allows the user to optimize for speed, accuracy, and cost by determining which models are used to evaluate the event. Available run modes include ‘precision_plus`, `precision`, `smart`, and `economy`. Defaults to `smart`.

Returns:



37
 
# File 'lib/deeprails/models/defend_submit_event_params.rb', line 37

required :run_mode, enum: -> { Deeprails::DefendSubmitEventParams::RunMode }