Skip to main content

Complete chat in OpenAI

Complete chat in OpenAI.

Application

  • OpenAI

Inputs (what you have)

NameDescriptionData TypeRequired?Example
Connected AccountThe connected account to use for the requestConnected AccountYes
ModelThe model which will generate the completionText (Short)No
Message Role 1Predefined Choice ListNo
Message Content 1Text (Long)No
Message Role 2Predefined Choice ListNo
Message Content 2Text (Short)No
Message Role 3Predefined Choice ListNo
Message Content 3Text (Long)No
Simplify?Whether to return a simplified version of the response instead of the raw dataTrue/FalseNo
Frequency penaltyPositive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatimNumber with decimalsNo
Maximum number of tokensThe maximum number of tokens to generate in the completion. Most models have a context length of 2048 tokens (except for the newest models, which support 32,768)NumberNo
Number of completionsHow many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stopNumberNo
Presence penaltyPositive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topicsNumber with decimalsNo
Sampling temperatureControls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitiveNumber with decimalsNo
Top pControls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered. We generally recommend altering this or temperature but not bothNumber with decimalsNo

Outputs (what you get)

NameDescriptionData TypeRequired?Example
JSON OutputJSON output returned by the APIText (Long)No

Outcomes

NameDescription
SuccessThis status is selected if the job has successfully completed.
UnsuccessfulThis status is selected if the job has completed unsuccessfully.

Requirements

  • N/A