Class: OpenAI::Models::Realtime::RealtimeTruncation::RetentionRatioTruncation

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• OpenAI::Models::Realtime::RealtimeTruncation::RetentionRatioTruncation

Defined in:

lib/openai/models/realtime/realtime_truncation.rb

Instance Attribute Summary

• #post_instructions_token_limit ⇒ Integer^?

  Optional cap on tokens allowed after the instructions.

• #retention_ratio ⇒ Float

  Fraction of pre-instruction conversation tokens to retain (0.0 - 1.0).

• #type ⇒ Symbol, :retention_ratio

  Use retention ratio truncation.

Instance Method Summary

• #initialize(retention_ratio: , post_instructions_token_limit: nil, type: :retention_ratio) ⇒ Object constructor

  Some parameter documentations has been truncated, see RetentionRatioTruncation for more details.

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(retention_ratio: , post_instructions_token_limit: nil, type: :retention_ratio) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Realtime::RealtimeTruncation::RetentionRatioTruncation for more details.

Retain a fraction of the conversation tokens.

Parameters:

• retention_ratio (Float) (defaults to: ) —

  Fraction of pre-instruction conversation tokens to retain (0.0 - 1.0).

• post_instructions_token_limit (Integer, nil) (defaults to: nil) —

  Optional cap on tokens allowed after the instructions.

• type (Symbol, :retention_ratio) (defaults to: :retention_ratio) —

  Use retention ratio truncation.

# File 'lib/openai/models/realtime/realtime_truncation.rb', line 48

Instance Attribute Details

#post_instructions_token_limit ⇒ Integer^?

Optional cap on tokens allowed after the instructions.

Returns:

• (Integer, nil)

# File 'lib/openai/models/realtime/realtime_truncation.rb', line 46

optional :post_instructions_token_limit, Integer, nil?: true

#retention_ratio ⇒ Float

Fraction of pre-instruction conversation tokens to retain (0.0 - 1.0).

Returns:

• (Float)

# File 'lib/openai/models/realtime/realtime_truncation.rb', line 34

required :retention_ratio, Float

#type ⇒ Symbol, :retention_ratio

Use retention ratio truncation.

Returns:

• (Symbol, :retention_ratio)

# File 'lib/openai/models/realtime/realtime_truncation.rb', line 40

required :type, const: :retention_ratio