Skip to contents

ModelResponse R6 Class

Source: R/responses.R
ModelResponse.Rd

The ModelResponse class represents a model response object in the OpenAI API.

Super class

openaiapi::Utils -> ModelResponse

Public fields

background

Logical. Whether to run the model response in the background.

id

Character. Unique identifier for this Response.

error

List or NULL. An error object returned when the model fails to generate a Response.

incomplete_details

List or NULL. Details about why the response is incomplete.

created_at

Numeric. Unix timestamp (in seconds) of when this Response was created.

instructions

Character or NULL. Inserts a system (or developer) message as the first item in the model's context.

max_output_tokens

Integer or NULL. An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

max_tool_calls

Integer or NULL. The maximum number of total calls to built-in tools that can be processed in a response.

metadata

List. Set of 16 key-value pairs that can be attached to an object.

model

Character. Model ID used to generate the response, like gpt-4o or o1.

output

List. An array of content items generated by the model.

output_text

Character or NULL. SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present.

parallel_tool_calls

Logical. Whether to allow the model to run tool calls in parallel.

previous_response_id

Character or NULL. The unique ID of the previous response to the model.

prompt

List or NULL. Reference to a prompt template and its variables.

prompt_cache_key

Character or NULL. Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field.

reasoning

List or NULL. Configuration options for reasoning models.

safety_identifier

Character or NULL. A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies.

service_tier

Character or NULL. The latency tier to use for processing the request.

status

Character. The status of the response generation.

temperature

Numeric or NULL. What sampling temperature to use, between 0 and 2.

text

List. Configuration options for a text response from the model.

tool_choice

Character or List. How the model should select which tool (or tools) to use when generating a response.

tools

List. An array of tools the model may call while generating a response.

top_logprobs

Integer or NULL. An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.

top_p

Numeric or NULL. An alternative to sampling with temperature, called nucleus sampling.

truncation

Character or NULL. The truncation strategy to use for the model response.

usage

List. Represents token usage details including input tokens, output tokens, a breakdown of output tokens, and the total tokens used.

user

Character. A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

verbosity

Character or NULL. Constrains the verbosity of the model's response.

Methods

Public methods

Method new()

Initialize a ModelResponse object.

Usage

ModelResponse$new(
  response_id = NULL,
  input = NULL,
  ...,
  resp = NULL,
  .async = TRUE
)

Arguments

response_id

Character. Unique identifier for this Response.

input

Character or List. Text, image, or file inputs to the model, used to generate a response.

...

Additional parameters to pass to the model.

resp

List. The response object returned by the OpenAI API.

.async

Logical. Whether to retrieve the response asynchronously.

Method get()

Get a fresh copy of the model response.

Usage

ModelResponse$get(...)

Arguments

...

Additional parameters to pass to the model.

Method delete()

Store the model response.

Usage

ModelResponse$delete()

Method list_input_items()

List input items for the model response.

Usage

ModelResponse$list_input_items(...)

Arguments

...

Additional parameters to pass to the oai_list_items() function.

Method do_tool_calls()

Do all tool calls in the model response and return the results.

Usage

ModelResponse$do_tool_calls(env = parent.frame())

Arguments

env

Environment. The environment in which to evaluate the tool calls.

Method respond()

Create a new model response based on the previous response.

Usage

ModelResponse$respond(input, ...)

Arguments

input

Character or List. Text, image, or file inputs to the model, used to generate a response.

...

Additional parameters to pass to the model.

Method submit_tool_outputs()

Submit tool outputs to generate a new model response.

Usage

ModelResponse$submit_tool_outputs(tool_outputs)

Arguments

tool_outputs

List. The tool outputs to submit.

Method wait()

Submit tool outputs to generate a new model response.

Usage

ModelResponse$wait(env = parent.frame())

Arguments

env

Environment. The environment in which to evaluate the tool calls.

Method await()

Wait for the model response to complete.

Usage

ModelResponse$await(env = parent.frame())

Arguments

env

Environment. The environment in which to evaluate the tool calls.

Method clone()

The objects of this class are cloneable with this method.

Usage

ModelResponse$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.