Class: OpenAI::Models::Realtime::RealtimeSessionCreateResponse

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

Defined Under Namespace

Modules: Include, MaxOutputTokens, Model, OutputModality, Tool, ToolChoice, Tracing Classes: Audio

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(client_secret: , audio: nil, include: nil, instructions: nil, max_output_tokens: nil, model: nil, output_modalities: nil, prompt: nil, tool_choice: nil, tools: nil, tracing: nil, truncation: nil, type: :realtime) ⇒ Object

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

A new Realtime session configuration, with an ephemeral key. Default TTL for keys is one minute.




# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 131

Instance Attribute Details

#audio ⇒ OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Audio?

Configuration for input and output audio.



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

optional :audio, -> { OpenAI::Realtime::RealtimeSessionCreateResponse::Audio }

#client_secret ⇒ OpenAI::Models::Realtime::RealtimeSessionClientSecret

Ephemeral key returned by the API.



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

required :client_secret, -> { OpenAI::Realtime::RealtimeSessionClientSecret }

#include ⇒ Array<Symbol, OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Include>?

Additional fields to include in server outputs.

‘item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.



32
33
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 32

optional :include,
-> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Realtime::RealtimeSessionCreateResponse::Include] }

#instructions ⇒ String?

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the ‘session.created` event at the start of the session.



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

optional :instructions, String

#max_output_tokens ⇒ Integer, ...

Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or ‘inf` for the maximum available tokens for a given model. Defaults to `inf`.



57
58
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 57

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

#model ⇒ String, ...

The Realtime model used for this session.



64
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 64

optional :model, union: -> { OpenAI::Realtime::RealtimeSessionCreateResponse::Model }

#output_modalities ⇒ Array<Symbol, OpenAI::Models::Realtime::RealtimeSessionCreateResponse::OutputModality>?

The set of modalities the model can respond with. It defaults to ‘[“audio”]`, indicating that the model will respond with audio plus a transcript. `[“text”]` can be used to make the model respond with text only. It is not possible to request both `text` and `audio` at the same time.



73
74
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 73

optional :output_modalities,
-> { OpenAI::Internal::Type::ArrayOf[enum: OpenAI::Realtime::RealtimeSessionCreateResponse::OutputModality] }

#prompt ⇒ OpenAI::Models::Responses::ResponsePrompt?

Reference to a prompt template and its variables. [Learn more](platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts).



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

optional :prompt, -> { OpenAI::Responses::ResponsePrompt }, nil?: true

#tool_choice ⇒ Symbol, ...

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.



88
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 88

optional :tool_choice, union: -> { OpenAI::Realtime::RealtimeSessionCreateResponse::ToolChoice }

#tools ⇒ Array<OpenAI::Models::Realtime::RealtimeFunctionTool, OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Tool::McpTool>?

Tools available to the model.



94
95
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 94

optional :tools,
-> { OpenAI::Internal::Type::ArrayOf[union: OpenAI::Realtime::RealtimeSessionCreateResponse::Tool] }

#tracing ⇒ Symbol, ...

Realtime API can write session traces to the [Traces Dashboard](/logs?api=traces). Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

‘auto` will create a trace for the session with default values for the workflow name, group id, and metadata.



106
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 106

optional :tracing, union: -> { OpenAI::Realtime::RealtimeSessionCreateResponse::Tracing }, nil?: true

#truncation ⇒ Symbol, ...

When the number of tokens in a conversation exceeds the model’s input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model’s context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs.

Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost.

Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate.

Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model’s input token limit.



129
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 129

optional :truncation, union: -> { OpenAI::Realtime::RealtimeTruncation }

#type ⇒ Symbol, :realtime

The type of session to create. Always ‘realtime` for the Realtime API.



17
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 17

required :type, const: :realtime

Class Method Details

.values ⇒ Array<Symbol> 




# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 567

.variants ⇒ Array(OpenAI::Models::Realtime::RealtimeFunctionTool, OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Tool::McpTool) 




# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 583