Interface SamplingParams

interface SamplingParams {
    max_completion_tokens?: number;
    seed?: number;
    temperature?: number;
    text?: OpenAIClient.Evals.Runs.RunListResponse.Responses.SamplingParams.Text;
    tools?: OpenAIClient.Responses.Tool[];
    top_p?: number;
}

Properties

max_completion_tokens? seed? temperature? text? tools? top_p?

Properties

Optionalmax_completion_tokens

max_completion_tokens?: number

The maximum number of tokens in the generated output.

Optionalseed

seed?: number

A seed value to initialize the randomness, during sampling.

Optionaltemperature

temperature?: number

A higher temperature increases randomness in the outputs.

Optionaltext

text?: OpenAIClient.Evals.Runs.RunListResponse.Responses.SamplingParams.Text

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

Optionaltools

tools?: OpenAIClient.Responses.Tool[]

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

  • Built-in tools: Tools that are provided by OpenAI that extend the model's capabilities, like web search or file search. Learn more about built-in tools.
  • Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

Optionaltop_p

top_p?: number

An alternative to temperature for nucleus sampling; 1.0 includes all tokens.

Settings

Member Visibility

On This Page

Properties