text [required]

string

Text to send to the GPT model to summarize.

maxTokens

number

The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Defaults to 256. Learn more about tokens here.

default: 256

targetLength

number

The number of words to shorten the text to. Defaults to 25.

default: 25

randomness

number

The level of randomness, between 0 and 2, to use when generating the summary. This directly affects the temperature. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Defaults to 1.

default: 1

model

enum

The model to use for the summary. Defaults to gpt-3.5-turbo. Learn more about each of the models, and their strengths, here. Allowed enum values: gpt-3.5-turbo,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613

default: gpt-3.5-turbo