Constructor for the ChatCompletionCreateRequest.
can contain the following fields, but must contain messages and model.
Optional
frequency_Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
Optional
max_The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
messages - An array of ChatCompletionRequestMessage comprising the conversation so far.
ID of the model to use.
Optional
presence_Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Optional
response_Optional
stopup to 4 sequences where the API will stop generating further tokens.
Optional
streamIf set, partial message deltas will be sent. Tokens will be
sent as data-only. Defaults to false.
server-sent events
as they become available, with the stream terminated by a data: [DONE]
message. This output is processed through Stream and returns
CreateChatCompletionStreamResponse if set to true
. If set to
false
or not specified, returns CreateChatCompletionResponse
Optional
temperatureWhat sampling temperature to use, between 0 and 2.
Higher values like 0.8 will make the output more random, while lower values
like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p
but not both.
Optional
top_An alternative to sampling with temperature, called nucleus
sampling, where the model considers the results of the tokens with top_p
probability mass. So 0.1 means only the tokens comprising the top 10%
probability mass are considered.
We generally recommend altering this or temperature
but not both.
Generated using TypeDoc
ChatCompletionCreateRequest class. Can be used as an interface, but also instantiates the class handling stream default behavior with stream default being disabled if not explicitly set to on.