Choice interface
The representation of a single prompt completion as part of an overall completions request.
Generally, n
choices are generated per provided prompt with a default value of 1.
Token limits and other settings may limit the number of choices generated.
Properties
content |
Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. |
finish |
Reason for finishing |
index | The ordered index associated with this completions choice. |
logprobs | The log probabilities model for tokens associated with this completions choice. |
text | The generated text for a given completions prompt. |
Property Details
contentFilterResults
Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not.
contentFilterResults?: ContentFilterResultsForChoice
Property Value
finishReason
Reason for finishing
finishReason: null | string
Property Value
null | string
index
The ordered index associated with this completions choice.
index: number
Property Value
number
logprobs
The log probabilities model for tokens associated with this completions choice.
logprobs: null | CompletionsLogProbabilityModel
Property Value
text
The generated text for a given completions prompt.
text: string
Property Value
string
Azure SDK for JavaScript