View Source ExOpenAI.Components.Response (ex_openai.ex v2.0.0-beta2)

Module for representing the OpenAI schema Response.

Fields

  • :background - optional - boolean() | any()

  • :completed_at - optional - number() | any()

  • :conversation - optional - :"Elixir.ExOpenAI.Components.Conversation-2".t() | any()

  • :created_at - required - number()
    Unix timestamp (in seconds) of when this Response was created.

  • :error - required - ExOpenAI.Components.ResponseError.t()

  • :id - required - String.t()
    Unique identifier for this Response.

  • :incomplete_details - required - {:%{}, [], [{{:optional, [], [:reason]}, {:|, [], [:max_output_tokens, :content_filter]}}]} | any()

  • :instructions - required - String.t() | [ExOpenAI.Components.InputItem.t()] | any()

  • :max_output_tokens - optional - integer() | any()

  • :max_tool_calls - optional - integer() | any()

  • :metadata - required - ExOpenAI.Components.Metadata.t()

  • :model - required - ExOpenAI.Components.ModelIdsResponses.t()
    Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

  • :object - required - :response
    The object type of this resource - always set to response.
    Allowed values: "response"

  • :output - required - [ExOpenAI.Components.OutputItem.t()]
    An array of content items generated by the model.

  • The length and order of items in the output array is dependent on the model's response.
  • Rather than accessing the first item in the output array and assuming it's an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

  • :output_text - optional - String.t() | any()

  • :parallel_tool_calls - required - boolean()
    Whether to allow the model to run tool calls in parallel.
    Default: true

  • :previous_response_id - optional - String.t() | any()

  • :prompt - optional - ExOpenAI.Components.Prompt.t()

  • :prompt_cache_key - optional - String.t()
    Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

  • :prompt_cache_retention - optional - :"in-memory" | :"24h" | any()

  • :reasoning - optional - ExOpenAI.Components.Reasoning.t() | any()

  • :safety_identifier - optional - String.t()
    A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
    Constraints: maxLength: 64

  • :service_tier - optional - ExOpenAI.Components.ServiceTier.t()

  • :status - optional - :completed | :failed | :in_progress | :cancelled | :queued | :incomplete
    The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
    Allowed values: "completed", "failed", "in_progress", "cancelled", "queued", "incomplete"

  • :temperature - required - number() | any()

  • :text - optional - ExOpenAI.Components.ResponseTextParam.t()

  • :tool_choice - required - ExOpenAI.Components.ToolChoiceParam.t()

  • :tools - required - ExOpenAI.Components.ToolsArray.t()

  • :top_logprobs - optional - integer() | any()

  • :top_p - required - number() | any()

  • :truncation - optional - :auto | :disabled | any()

  • :usage - optional - ExOpenAI.Components.ResponseUsage.t()

  • :user - optional - String.t()
    This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

Summary

Types

t()

Types

Link to this type

t()

View Source 
@type t() :: %ExOpenAI.Components.Response{
  background: (boolean() | any()) | nil,
  completed_at: (number() | any()) | nil,
  conversation:
    (:"Elixir.ExOpenAI.Components.Conversation-2".t() | any()) | nil,
  created_at: number(),
  error: ExOpenAI.Components.ResponseError.t(),
  id: String.t(),
  incomplete_details:
    %{optional(:reason) => :max_output_tokens | :content_filter} | any(),
  instructions: (String.t() | [ExOpenAI.Components.InputItem.t()]) | any(),
  max_output_tokens: (integer() | any()) | nil,
  max_tool_calls: (integer() | any()) | nil,
  metadata: ExOpenAI.Components.Metadata.t(),
  model: ExOpenAI.Components.ModelIdsResponses.t(),
  object: :response,
  output: [ExOpenAI.Components.OutputItem.t()],
  output_text: (String.t() | any()) | nil,
  parallel_tool_calls: boolean(),
  previous_response_id: (String.t() | any()) | nil,
  prompt: ExOpenAI.Components.Prompt.t() | nil,
  prompt_cache_key: String.t() | nil,
  prompt_cache_retention: ((:"in-memory" | :"24h") | any()) | nil,
  reasoning: (ExOpenAI.Components.Reasoning.t() | any()) | nil,
  safety_identifier: String.t() | nil,
  service_tier: ExOpenAI.Components.ServiceTier.t() | nil,
  status:
    (((((:completed | :failed) | :in_progress) | :cancelled) | :queued)
     | :incomplete)
    | nil,
  temperature: number() | any(),
  text: ExOpenAI.Components.ResponseTextParam.t() | nil,
  tool_choice: ExOpenAI.Components.ToolChoiceParam.t(),
  tools: ExOpenAI.Components.ToolsArray.t(),
  top_logprobs: (integer() | any()) | nil,
  top_p: number() | any(),
  truncation: ((:auto | :disabled) | any()) | nil,
  usage: ExOpenAI.Components.ResponseUsage.t() | nil,
  user: String.t() | nil
}