Optional
apiWriter API key
Optional
bestGenerates this many completions server-side and returns the "best"."
Optional
cacheOptional
callbackOptional
callbacksOptional
concurrencyOptional
frequencyPenalizes repeated tokens according to frequency.
Optional
logprobsWhether to return log probabilities.
Optional
maxThe maximum number of concurrent calls that can be made.
Defaults to Infinity
, which means no limit.
Optional
maxThe maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.
Optional
maxMaximum number of tokens to generate in the completion.
Optional
metadataOptional
minMinimum number of tokens to generate.
Optional
modelModel to use
Optional
nNumber of completions to generate.
Optional
onCustom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.
Optional
orgWriter organization ID
Optional
presencePenalizes repeated tokens regardless of frequency.
Optional
tagsOptional
temperatureSampling temperature to use
Optional
topPTotal probability mass of tokens to consider at each step.
Optional
verbose
Interface for the input parameters specific to the Writer model.