Optional
baseOptional
cacheOptional
callbackOptional
callbacksOptional
concurrencyOptional
embeddingOptional
f16Optional
formatOptional
frequencyOptional
keepOptional
logitsOptional
lowOptional
mainOptional
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
metadataOptional
mirostatOptional
mirostatOptional
mirostatOptional
modelThe model to use when making requests.
Optional
numOptional
numOptional
numOptional
numOptional
numOptional
numOptional
numaOptional
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
penalizeOptional
presenceOptional
repeatOptional
repeatOptional
seedOptional
stopOptional
tagsOptional
temperatureOptional
tfsZOptional
topKOptional
topPOptional
typicalPOptional
useOptional
useOptional
verboseOptional
vocab
Optionally override the base URL to make request to. This should only be set if your Ollama instance is being server from a non-standard location.