Method: OpenAI::Resources::Beta::Threads::Runs#create_stream_raw

Defined in:

lib/openai/resources/beta/threads/runs.rb

#create_stream_raw(thread_id, assistant_id: , include: nil, additional_instructions: nil, additional_messages: nil, instructions: nil, max_completion_tokens: nil, max_prompt_tokens: nil, metadata: nil, model: nil, parallel_tool_calls: nil, reasoning_effort: nil, response_format: nil, temperature: nil, tool_choice: nil, tools: nil, top_p: nil, truncation_strategy: nil, request_options: {}) ⇒ OpenAI::Internal::Stream<OpenAI::Models::Beta::AssistantStreamEvent::ThreadCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunQueued, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunRequiresAction, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunIncomplete, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunFailed, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCancelling, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCancelled, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunExpired, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepDelta, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepFailed, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCancelled, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepExpired, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageDelta, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageIncomplete, OpenAI::Models::Beta::AssistantStreamEvent::ErrorEvent>

Deprecated.

The Assistants API is deprecated in favor of the Responses API

See #create for non-streaming counterpart.

Some parameter documentations has been truncated, see Models::Beta::Threads::RunCreateParams for more details.

Create a run.

Parameters:

• thread_id (String) —

  Path param: The ID of the thread to run.

• assistant_id (String) —

  Body param: The ID of the [assistant](https://platform.openai.com/docs/api-refer

• include (Array<Symbol, OpenAI::Models::Beta::Threads::Runs::RunStepInclude>) —

  Query param: A list of additional fields to include in the response. Currently t

• additional_instructions (String, nil) —

  Body param: Appends additional instructions at the end of the instructions for t

• additional_messages (Array<OpenAI::Models::Beta::Threads::RunCreateParams::AdditionalMessage>, nil) —

  Body param: Adds additional messages to the thread before creating the run.

• instructions (String, nil) —

  Body param: Overrides the [instructions](https://platform.openai.com/docs/api-re

• max_completion_tokens (Integer, nil) —

  Body param: The maximum number of completion tokens that may be used over the co

• max_prompt_tokens (Integer, nil) —

  Body param: The maximum number of prompt tokens that may be used over the course

• metadata (Hash{Symbol=>String}, nil) —

  Body param: Set of 16 key-value pairs that can be attached to an object. This ca

• model (String, Symbol, OpenAI::Models::ChatModel, nil) —

  Body param: The ID of the [Model](https://platform.openai.com/docs/api-reference

• parallel_tool_calls (Boolean) —

  Body param: Whether to enable [parallel function calling](https://platform.opena

• reasoning_effort (Symbol, OpenAI::Models::ReasoningEffort, nil) —

  Body param: o-series models only

• response_format (Symbol, :auto, OpenAI::Models::ResponseFormatText, OpenAI::Models::ResponseFormatJSONObject, OpenAI::Models::ResponseFormatJSONSchema, nil) —

  Body param: Specifies the format that the model must output. Compatible with [GP

• temperature (Float, nil) —

  Body param: What sampling temperature to use, between 0 and 2. Higher values lik

• tool_choice (Symbol, OpenAI::Models::Beta::AssistantToolChoiceOption::Auto, OpenAI::Models::Beta::AssistantToolChoice, nil) —

  Body param: Controls which (if any) tool is called by the model.

• tools (Array<OpenAI::Models::Beta::CodeInterpreterTool, OpenAI::Models::Beta::FileSearchTool, OpenAI::Models::Beta::FunctionTool>, nil) —

  Body param: Override the tools the assistant can use for this run. This is usefu

• top_p (Float, nil) —

  Body param: An alternative to sampling with temperature, called nucleus sampling

• truncation_strategy (OpenAI::Models::Beta::Threads::RunCreateParams::TruncationStrategy, nil) —

  Body param: Controls for how a thread will be truncated prior to the run. Use th

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

Returns:

• (OpenAI::Internal::Stream<OpenAI::Models::Beta::AssistantStreamEvent::ThreadCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunQueued, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunRequiresAction, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunIncomplete, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunFailed, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCancelling, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunCancelled, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunExpired, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepDelta, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepFailed, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepCancelled, OpenAI::Models::Beta::AssistantStreamEvent::ThreadRunStepExpired, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageCreated, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageInProgress, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageDelta, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageCompleted, OpenAI::Models::Beta::AssistantStreamEvent::ThreadMessageIncomplete, OpenAI::Models::Beta::AssistantStreamEvent::ErrorEvent>)

See Also:

• Models::Beta::Threads::RunCreateParams

# File 'lib/openai/resources/beta/threads/runs.rb', line 135

def create_stream_raw(thread_id, params)
  parsed, options = OpenAI::Beta::Threads::RunCreateParams.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)
  query_params = [:include]
  @client.request(
    method: :post,
    path: ["threads/%1$s/runs", thread_id],
    query: parsed.slice(*query_params),
    headers: {"accept" => "text/event-stream"},
    body: parsed.except(*query_params),
    stream: OpenAI::Internal::Stream,
    model: OpenAI::Beta::AssistantStreamEvent,
    options: {extra_headers: {"OpenAI-Beta" => "assistants=v2"}, **options}
  )
end