Class: OpenAI::Models::Realtime::RealtimeResponse

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/realtime/realtime_response.rb

Defined Under Namespace

Modules: MaxOutputTokens, Modality, Object, OutputAudioFormat, Status, Voice

Instance Attribute Summary collapse

Class Method 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(id: nil, conversation_id: nil, max_output_tokens: nil, metadata: nil, modalities: nil, object: nil, output: nil, output_audio_format: nil, status: nil, status_details: nil, temperature: nil, usage: nil, voice: nil) ⇒ Object

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

The response resource.

Parameters:




# File 'lib/openai/models/realtime/realtime_response.rb', line 105

Instance Attribute Details

#conversation_id ⇒ String?

Which conversation the response is added to, determined by the ‘conversation` field in the `response.create` event. If `auto`, the response will be added to the default conversation and the value of `conversation_id` will be an id like `conv_1234`. If `none`, the response will not be added to any conversation and the value of `conversation_id` will be `null`. If responses are being triggered by server VAD, the response will be added to the default conversation, thus the `conversation_id` will be an id like `conv_1234`.

Returns:

  • (String, nil) 


23
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 23

optional :conversation_id, String

#id ⇒ String?

The unique ID of the response.

Returns:

  • (String, nil) 


11
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 11

optional :id, String

#max_output_tokens ⇒ Integer, ...

Maximum number of output tokens for a single assistant response, inclusive of tool calls, that was used in this response.

Returns:

  • (Integer, Symbol, :inf, nil) 


30
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 30

optional :max_output_tokens, union: -> { OpenAI::Realtime::RealtimeResponse::MaxOutputTokens }

#metadata ⇒ Hash{Symbol=>String}?

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Returns:

  • (Hash{Symbol=>String}, nil) 


41
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 41

optional :metadata, OpenAI::Internal::Type::HashOf[String], nil?: true

#modalities ⇒ Array<Symbol, OpenAI::Models::Realtime::RealtimeResponse::Modality>?

The set of modalities the model used to respond. If there are multiple modalities, the model will pick one, for example if ‘modalities` is `[“text”, “audio”]`, the model could be responding in either text or audio.

Returns:



49
50
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 49

optional :modalities,
-> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Realtime::RealtimeResponse::Modality] }

#object ⇒ Symbol, ...

The object type, must be ‘realtime.response`.

Returns:



56
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 56

optional :object, enum: -> { OpenAI::Realtime::RealtimeResponse::Object }

#output ⇒ Array<OpenAI::Models::Realtime::RealtimeConversationItemSystemMessage, OpenAI::Models::Realtime::RealtimeConversationItemUserMessage, OpenAI::Models::Realtime::RealtimeConversationItemAssistantMessage, OpenAI::Models::Realtime::RealtimeConversationItemFunctionCall, OpenAI::Models::Realtime::RealtimeConversationItemFunctionCallOutput, OpenAI::Models::Realtime::RealtimeMcpApprovalResponse, OpenAI::Models::Realtime::RealtimeMcpListTools, OpenAI::Models::Realtime::RealtimeMcpToolCall, OpenAI::Models::Realtime::RealtimeMcpApprovalRequest>?

The list of output items generated by the response.

Returns:



62
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 62

optional :output, -> { OpenAI::Internal::Type::ArrayOf[union: OpenAI::Realtime::ConversationItem] }

#output_audio_format ⇒ Symbol, ...

The format of output audio. Options are ‘pcm16`, `g711_ulaw`, or `g711_alaw`.

Returns:



68
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 68

optional :output_audio_format, enum: -> { OpenAI::Realtime::RealtimeResponse::OutputAudioFormat }

#status ⇒ Symbol, ...

The final status of the response (‘completed`, `cancelled`, `failed`, or `incomplete`, `in_progress`).

Returns:



75
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 75

optional :status, enum: -> { OpenAI::Realtime::RealtimeResponse::Status }

#status_details ⇒ OpenAI::Models::Realtime::RealtimeResponseStatus?

Additional details about the status.

Returns:



81
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 81

optional :status_details, -> { OpenAI::Realtime::RealtimeResponseStatus }

#temperature ⇒ Float?

Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.

Returns:

  • (Float, nil) 


87
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 87

optional :temperature, Float

#usage ⇒ OpenAI::Models::Realtime::RealtimeResponseUsage?

Usage statistics for the Response, this will correspond to billing. A Realtime API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.

Returns:



96
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 96

optional :usage, -> { OpenAI::Realtime::RealtimeResponseUsage }

#voice ⇒ String, ...

The voice the model used to respond. Current voice options are ‘alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, and `verse`.

Returns:



103
 
# File 'lib/openai/models/realtime/realtime_response.rb', line 103

optional :voice, union: -> { OpenAI::Realtime::RealtimeResponse::Voice }

Class Method Details

.values ⇒ Array<Symbol>

Returns:

  • (Array<Symbol>) 



# File 'lib/openai/models/realtime/realtime_response.rb', line 158

.variants ⇒ Array(Integer, Symbol, :inf)

Returns:

  • (Array(Integer, Symbol, :inf)) 



# File 'lib/openai/models/realtime/realtime_response.rb', line 148