Class: OpenAI::Resources::Responses

Inherits:
Object
  • Object
show all
Includes:
Helpers::ResponsesWebSocket::Connections
Defined in:
lib/openai/resources/responses.rb,
lib/openai/resources/responses/input_items.rb,
lib/openai/resources/responses/input_tokens.rb,
sig/openai/helpers/sorbet.rbs,
sig/openai/resources/responses.rbs,
sig/openai/resources/responses/input_items.rbs,
sig/openai/resources/responses/input_tokens.rbs,
sig/openai/helpers/responses_websocket/extensions.rbs

Overview

Create and manage model responses.

Defined Under Namespace

Classes: InputItems, InputTokens

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(client:) ⇒ Responses

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of Responses.

Parameters:



916
917
918
919
920
 
# File 'lib/openai/resources/responses.rb', line 916

def initialize(client:)
  @client = client
  @input_items = OpenAI::Resources::Responses::InputItems.new(client: client)
  @input_tokens = OpenAI::Resources::Responses::InputTokens.new(client: client)
end

Instance Attribute Details

#input_items ⇒ OpenAI::Resources::Responses::InputItems (readonly)

Create and manage model responses.

Returns:



11
12
13
 
# File 'lib/openai/resources/responses.rb', line 11

def input_items
  @input_items
end

#input_tokens ⇒ OpenAI::Resources::Responses::InputTokens (readonly)

Create and manage model responses.

Returns:



15
16
17
 
# File 'lib/openai/resources/responses.rb', line 15

def input_tokens
  @input_tokens
end

Instance Method Details

#cancel(response_id, request_options: {}) ⇒ OpenAI::Models::Responses::Response

Cancels a model response with the given ID. Only responses created with the background parameter set to true can be cancelled. Learn more.

Parameters:

  • response_id (String) —

    The ID of the response to cancel.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



820
821
822
823
824
825
826
827
828
 
# File 'lib/openai/resources/responses.rb', line 820

def cancel(response_id, params = {})
  @client.request(
    method: :post,
    path: ["responses/%1$s/cancel", response_id],
    model: OpenAI::Responses::Response,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end

#compact(model:, input: nil, instructions: nil, previous_response_id: nil, prompt_cache_key: nil, prompt_cache_options: nil, prompt_cache_retention: nil, service_tier: nil, request_options: {}) ⇒ OpenAI::Models::Responses::CompactedResponse

Compact a conversation. Returns a compacted response object.

Learn when and how to compact long-running conversations in the conversation state guide. For ZDR-compatible compaction details, see Compaction (advanced).

Parameters:

Returns:

See Also:



901
902
903
904
905
906
907
908
909
910
911
 
# File 'lib/openai/resources/responses.rb', line 901

def compact(params)
  parsed, options = OpenAI::Responses::ResponseCompactParams.dump_request(params)
  @client.request(
    method: :post,
    path: "responses/compact",
    body: parsed,
    model: OpenAI::Responses::CompactedResponse,
    security: {bearer_auth: true},
    options: options
  )
end

#connect ⇒ Object 



45
 
# File 'sig/openai/helpers/responses_websocket/extensions.rbs', line 45

def connect: (

#create(access_programs: nil, background: nil, context_management: nil, conversation: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, moderation: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, prompt_cache_key: nil, prompt_cache_options: nil, prompt_cache_retention: nil, reasoning: nil, safety_identifier: nil, service_tier: nil, store: nil, stream_options: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, request_options: {}) ⇒ OpenAI::Models::Responses::Response

See OpenAI::Resources::Responses#stream_raw for streaming counterpart.

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.

Parameters:

Returns:

See Also:



286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
 
# File 'lib/openai/resources/responses.rb', line 286

def create(params = {})
  parsed, options = OpenAI::Responses::ResponseCreateParams.dump_request(params)
  if parsed[:stream]
    message = "Please use `#stream` for the streaming use case."
    raise ArgumentError.new(message)
  end

  model, tool_models = get_structured_output_models(parsed)

  unwrap = -> (raw) do
    parse_structured_outputs!(raw, model, tool_models)
  end

  @client.request(
    method: :post,
    path: "responses",
    body: parsed,
    unwrap: unwrap,
    model: OpenAI::Responses::Response,
    security: {bearer_auth: true},
    options: options
  )
end

#delete(response_id, request_options: {}) ⇒ nil

Deletes a model response with the given ID.

Parameters:

  • response_id (String) —

    The ID of the response to delete.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

  • (nil)

See Also:



796
797
798
799
800
801
802
803
804
 
# File 'lib/openai/resources/responses.rb', line 796

def delete(response_id, params = {})
  @client.request(
    method: :delete,
    path: ["responses/%1$s", response_id],
    model: NilClass,
    security: {bearer_auth: true},
    options: params[:request_options]
  )
end

#retrieve(response_id, include: nil, include_obfuscation: nil, starting_after: nil, text: nil, tools: nil, request_options: {}) ⇒ OpenAI::Models::Responses::Response

See OpenAI::Resources::Responses#retrieve_streaming for streaming counterpart.

Retrieves a model response with the given ID.

Parameters:

  • response_id (String) —

    The ID of the response to retrieve.

  • include (Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>) —

    Additional fields to include in the response. See the include parameter for Response creation above for more information.

  • include_obfuscation (Boolean) —

    When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

  • starting_after (Integer) —

    The sequence number of the event after which to start streaming.

  • text (OpenAI::Responses::ResponseTextConfig, OpenAI::StructuredOutput::JsonSchemaConverter, Hash, nil) —

    The structured-output model, or the same typed/hash text configuration accepted by creation, used to parse retrieved text output. This is a local parsing hint and is not sent to the API.

  • tools (Array<OpenAI::Responses::FunctionTool, OpenAI::StructuredOutput::JsonSchemaConverter, Hash>, nil) —

    Structured-output models, or the same typed/hash function-tool definitions accepted by creation, used to parse retrieved function tool calls. These are local parsing hints and are not sent to the API.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
 
# File 'lib/openai/resources/responses.rb', line 688

def retrieve(response_id, params = {})
  parsed, options = OpenAI::Responses::ResponseRetrieveParams.dump_request(params)
  structured_output_params = parsed.slice(:text, :tools)
  parsed.delete(:text)
  parsed.delete(:tools)
  query = OpenAI::Internal::Util.encode_query_params(parsed)
  if parsed[:stream]
    message = "Please use `#retrieve_streaming` for the streaming use case."
    raise ArgumentError.new(message)
  end

  model, tool_models = get_retrieval_structured_output_models(structured_output_params)

  unwrap = if model || !tool_models.empty?
    -> (raw) do
      parse_retrieved_structured_outputs!(raw, model, tool_models)
    end
  end

  @client.request(
    method: :get,
    path: ["responses/%1$s", response_id],
    query: query,
    unwrap: unwrap,
    model: OpenAI::Responses::Response,
    security: {bearer_auth: true},
    options: options
  )
end

#retrieve_streaming(response_id, include: nil, include_obfuscation: nil, starting_after: nil, request_options: {}) ⇒ OpenAI::Internal::Stream<OpenAI::Models::Responses::ResponseAudioDeltaEvent, OpenAI::Models::Responses::ResponseAudioDoneEvent, OpenAI::Models::Responses::ResponseAudioTranscriptDeltaEvent, OpenAI::Models::Responses::ResponseAudioTranscriptDoneEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCodeDeltaEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCodeDoneEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCompletedEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallInProgressEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallInterpretingEvent, OpenAI::Models::Responses::ResponseCompactionCompactingEvent, OpenAI::Models::Responses::ResponseCompletedEvent, OpenAI::Models::Responses::ResponseContentPartAddedEvent, OpenAI::Models::Responses::ResponseContentPartDoneEvent, OpenAI::Models::Responses::ResponseCreatedEvent, OpenAI::Models::Responses::ResponseErrorEvent, OpenAI::Models::Responses::ResponseFileSearchCallCompletedEvent, OpenAI::Models::Responses::ResponseFileSearchCallInProgressEvent, OpenAI::Models::Responses::ResponseFileSearchCallSearchingEvent, OpenAI::Models::Responses::ResponseFunctionCallArgumentsDeltaEvent, OpenAI::Models::Responses::ResponseFunctionCallArgumentsDoneEvent, OpenAI::Models::Responses::ResponseShellCallCommandAddedEvent, OpenAI::Models::Responses::ResponseShellCallCommandDeltaEvent, OpenAI::Models::Responses::ResponseShellCallCommandDoneEvent, OpenAI::Models::Responses::ResponseShellCallOutputContentDeltaEvent, OpenAI::Models::Responses::ResponseShellCallOutputContentDoneEvent, OpenAI::Models::Responses::ResponseInProgressEvent, OpenAI::Models::Responses::ResponseFailedEvent, OpenAI::Models::Responses::ResponseIncompleteEvent, OpenAI::Models::Responses::ResponseOutputItemAddedEvent, OpenAI::Models::Responses::ResponseOutputItemDoneEvent, OpenAI::Models::Responses::ResponseReasoningSummaryPartAddedEvent, OpenAI::Models::Responses::ResponseReasoningSummaryPartDoneEvent, OpenAI::Models::Responses::ResponseReasoningSummaryTextDeltaEvent, OpenAI::Models::Responses::ResponseReasoningSummaryTextDoneEvent, OpenAI::Models::Responses::ResponseReasoningTextDeltaEvent, OpenAI::Models::Responses::ResponseReasoningTextDoneEvent, OpenAI::Models::Responses::ResponseRefusalDeltaEvent, OpenAI::Models::Responses::ResponseRefusalDoneEvent, OpenAI::Models::Responses::ResponseTextDeltaEvent, OpenAI::Models::Responses::ResponseTextDoneEvent, OpenAI::Models::Responses::ResponseWebSearchCallCompletedEvent, OpenAI::Models::Responses::ResponseWebSearchCallInProgressEvent, OpenAI::Models::Responses::ResponseWebSearchCallSearchingEvent, OpenAI::Models::Responses::ResponseImageGenCallCompletedEvent, OpenAI::Models::Responses::ResponseImageGenCallGeneratingEvent, OpenAI::Models::Responses::ResponseImageGenCallInProgressEvent, OpenAI::Models::Responses::ResponseImageGenCallPartialImageEvent, OpenAI::Models::Responses::ResponseMcpCallArgumentsDeltaEvent, OpenAI::Models::Responses::ResponseMcpCallArgumentsDoneEvent, OpenAI::Models::Responses::ResponseMcpCallCompletedEvent, OpenAI::Models::Responses::ResponseMcpCallFailedEvent, OpenAI::Models::Responses::ResponseMcpCallInProgressEvent, OpenAI::Models::Responses::ResponseMcpListToolsCompletedEvent, OpenAI::Models::Responses::ResponseMcpListToolsFailedEvent, OpenAI::Models::Responses::ResponseMcpListToolsInProgressEvent, OpenAI::Models::Responses::ResponseOutputTextAnnotationAddedEvent, OpenAI::Models::Responses::ResponseQueuedEvent, OpenAI::Models::Responses::ResponseCustomToolCallInputDeltaEvent, OpenAI::Models::Responses::ResponseCustomToolCallInputDoneEvent, OpenAI::Streaming::UnknownStreamEvent>

See OpenAI::Resources::Responses#retrieve for non-streaming counterpart.

Retrieves a model response with the given ID.

Parameters:

  • response_id (String) —

    The ID of the response to retrieve.

  • include (Array<Symbol, OpenAI::Models::Responses::ResponseIncludable>) —

    Additional fields to include in the response. See the include parameter for Response creation above for more information.

  • include_obfuscation (Boolean) —

    When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set include_obfuscation to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API.

  • starting_after (Integer) —

    The sequence number of the event after which to start streaming.

  • request_options (OpenAI::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

See Also:



747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
 
# File 'lib/openai/resources/responses.rb', line 747

def retrieve_streaming(response_id, params = {})
  parsed, options = OpenAI::Responses::ResponseRetrieveParams.dump_request(params)
  unless parsed.fetch(:stream, true)
    message = "Please use `#retrieve` for the non-streaming use case."
    raise ArgumentError.new(message)
  end

  parsed.store(:stream, true)
  query = OpenAI::Internal::Util.encode_query_params(parsed)
  @client.request(
    method: :get,
    path: ["responses/%1$s", response_id],
    query: query,
    headers: {"accept" => "text/event-stream", "accept-encoding" => "identity"},
    stream: OpenAI::Internal::Stream,
    model: OpenAI::Responses::ResponseStreamEvent,
    security: {bearer_auth: true},
    options: options
  )
end

#stream(access_programs: nil, **params) ⇒ Object

Creates or resumes a streaming response and parses structured outputs.

Parameters:



315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
 
# File 'lib/openai/resources/responses.rb', line 315

def stream(params)
  parsed, options = OpenAI::Responses::ResponseCreateParams.dump_request(params)
  starting_after, response_id = parsed.values_at(:starting_after, :response_id)

  if starting_after && !response_id
    raise ArgumentError, "starting_after can only be used with response_id"
  end

  model, tool_models = get_structured_output_models(parsed)

  unwrap = -> (raw) do
    if raw[:type] == "response.completed" && raw[:response]
      parse_structured_outputs!(raw[:response], model, tool_models)
    end

    raw
  end

  if response_id
    retrieve_params = parsed.slice(:include, :starting_after)
    retrieve_params[:request_options] = options

    raw_stream = retrieve_streaming_internal(
      response_id,
      params: retrieve_params,
      unwrap: unwrap
    )
  else
    parsed[:stream] = true

    raw_stream = @client.request(
      method: :post,
      path: "responses",
      headers: {"accept" => "text/event-stream"},
      body: parsed,
      stream: OpenAI::Internal::Stream,
      model: OpenAI::Models::Responses::ResponseStreamEvent,
      unwrap: unwrap,
      security: {bearer_auth: true},
      options: options
    )
  end

  OpenAI::Streaming::ResponseStream.new(
    raw_stream: raw_stream,
    text_format: model,
    starting_after: starting_after
  )
end

#stream(background: nil, context_management: nil, conversation: nil, include: nil, input: nil, instructions: nil, max_output_tokens: nil, max_tool_calls: nil, metadata: nil, model: nil, moderation: nil, parallel_tool_calls: nil, previous_response_id: nil, prompt: nil, prompt_cache_key: nil, prompt_cache_options: nil, prompt_cache_retention: nil, reasoning: nil, response_id: nil, safety_identifier: nil, service_tier: nil, starting_after: nil, store: nil, stream_options: nil, temperature: nil, text: nil, tool_choice: nil, tools: nil, top_logprobs: nil, top_p: nil, truncation: nil, user: nil, request_options: {}) ⇒ OpenAI::Internal::Stream<OpenAI::Models::Responses::ResponseAudioDeltaEvent, OpenAI::Models::Responses::ResponseAudioDoneEvent, OpenAI::Models::Responses::ResponseAudioTranscriptDeltaEvent, OpenAI::Models::Responses::ResponseAudioTranscriptDoneEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCodeDeltaEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCodeDoneEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallCompletedEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallInProgressEvent, OpenAI::Models::Responses::ResponseCodeInterpreterCallInterpretingEvent, OpenAI::Models::Responses::ResponseCompactionCompactingEvent, OpenAI::Models::Responses::ResponseCompletedEvent, OpenAI::Models::Responses::ResponseContentPartAddedEvent, OpenAI::Models::Responses::ResponseContentPartDoneEvent, OpenAI::Models::Responses::ResponseCreatedEvent, OpenAI::Models::Responses::ResponseErrorEvent, OpenAI::Models::Responses::ResponseFileSearchCallCompletedEvent, OpenAI::Models::Responses::ResponseFileSearchCallInProgressEvent, OpenAI::Models::Responses::ResponseFileSearchCallSearchingEvent, OpenAI::Models::Responses::ResponseFunctionCallArgumentsDeltaEvent, OpenAI::Models::Responses::ResponseFunctionCallArgumentsDoneEvent, OpenAI::Models::Responses::ResponseShellCallCommandAddedEvent, OpenAI::Models::Responses::ResponseShellCallCommandDeltaEvent, OpenAI::Models::Responses::ResponseShellCallCommandDoneEvent, OpenAI::Models::Responses::ResponseShellCallOutputContentDeltaEvent, OpenAI::Models::Responses::ResponseShellCallOutputContentDoneEvent, OpenAI::Models::Responses::ResponseInProgressEvent, OpenAI::Models::Responses::ResponseFailedEvent, OpenAI::Models::Responses::ResponseIncompleteEvent, OpenAI::Models::Responses::ResponseOutputItemAddedEvent, OpenAI::Models::Responses::ResponseOutputItemDoneEvent, OpenAI::Models::Responses::ResponseReasoningSummaryPartAddedEvent, OpenAI::Models::Responses::ResponseReasoningSummaryPartDoneEvent, OpenAI::Models::Responses::ResponseReasoningSummaryTextDeltaEvent, OpenAI::Models::Responses::ResponseReasoningSummaryTextDoneEvent, OpenAI::Models::Responses::ResponseReasoningTextDeltaEvent, OpenAI::Models::Responses::ResponseReasoningTextDoneEvent, OpenAI::Models::Responses::ResponseRefusalDeltaEvent, OpenAI::Models::Responses::ResponseRefusalDoneEvent, OpenAI::Models::Responses::ResponseTextDeltaEvent, OpenAI::Models::Responses::ResponseTextDoneEvent, OpenAI::Models::Responses::ResponseWebSearchCallCompletedEvent, OpenAI::Models::Responses::ResponseWebSearchCallInProgressEvent, OpenAI::Models::Responses::ResponseWebSearchCallSearchingEvent, OpenAI::Models::Responses::ResponseImageGenCallCompletedEvent, OpenAI::Models::Responses::ResponseImageGenCallGeneratingEvent, OpenAI::Models::Responses::ResponseImageGenCallInProgressEvent, OpenAI::Models::Responses::ResponseImageGenCallPartialImageEvent, OpenAI::Models::Responses::ResponseMcpCallArgumentsDeltaEvent, OpenAI::Models::Responses::ResponseMcpCallArgumentsDoneEvent, OpenAI::Models::Responses::ResponseMcpCallCompletedEvent, OpenAI::Models::Responses::ResponseMcpCallFailedEvent, OpenAI::Models::Responses::ResponseMcpCallInProgressEvent, OpenAI::Models::Responses::ResponseMcpListToolsCompletedEvent, OpenAI::Models::Responses::ResponseMcpListToolsFailedEvent, OpenAI::Models::Responses::ResponseMcpListToolsInProgressEvent, OpenAI::Models::Responses::ResponseOutputTextAnnotationAddedEvent, OpenAI::Models::Responses::ResponseQueuedEvent, OpenAI::Models::Responses::ResponseCustomToolCallInputDeltaEvent, OpenAI::Models::Responses::ResponseCustomToolCallInputDoneEvent, OpenAI::Streaming::UnknownStreamEvent>

See OpenAI::Resources::Responses#create for non-streaming counterpart.

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.

Parameters:

Returns:

See Also:



631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
 
# File 'lib/openai/resources/responses.rb', line 631

def stream_raw(params = {})
  parsed, options = OpenAI::Responses::ResponseCreateParams.dump_request(params)
  unless parsed.fetch(:stream, true)
    message = "Please use `#create` for the non-streaming use case."
    raise ArgumentError.new(message)
  end

  parsed.store(:stream, true)
  @client.request(
    method: :post,
    path: "responses",
    headers: {"accept" => "text/event-stream", "accept-encoding" => "identity"},
    body: parsed,
    stream: OpenAI::Internal::Stream,
    model: OpenAI::Responses::ResponseStreamEvent,
    security: {bearer_auth: true},
    options: options
  )
end