class

OpenAI::CreateChatCompletionStreamResponse

Inherits JSON::Serializable < Reference < Object

Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. Learn more.

Constructors

new(pull : JSON::PullParser)
Source
new(id : String = "", choices : Array(CreateChatCompletionStreamResponseChoicesItem) = [] of CreateChatCompletionStreamResponseChoicesItem, created : Int64 = 0, model : String = "", service_tier : ServiceTier | Nil = nil, system_fingerprint : String | Nil = nil, object : CreateChatCompletionStreamResponseObject = CreateChatCompletionStreamResponseObject::ChatCompletionChunk, usage : CompletionUsage | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

choices

A list of chat completion choices. Can contain more than one elements if n is greater than 1. Can also be empty for the last chunk if you set stream_options: {"include_usage": true}.

Source
choices=(choices : Array(CreateChatCompletionStreamResponseChoicesItem))

A list of chat completion choices. Can contain more than one elements if n is greater than 1. Can also be empty for the last chunk if you set stream_options: {"include_usage": true}.

Source
created

The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.

Source
created=(created : Int64)

The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.

Source
id

A unique identifier for the chat completion. Each chunk has the same ID.

Source
id=(id : String)

A unique identifier for the chat completion. Each chunk has the same ID.

Source
model

The model to generate the completion.

Source
model=(model : String)

The model to generate the completion.

Source
object

The object type, which is always chat.completion.chunk.

Source
object=(object : CreateChatCompletionStreamResponseObject)

The object type, which is always chat.completion.chunk.

Source
service_tier
Source
service_tier=(service_tier : ServiceTier | Nil)
Source
system_fingerprint

This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

Source
system_fingerprint=(system_fingerprint : String | Nil)

This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

Source
usage

An optional field that will only be present when you set stream_options: {"include_usage": true} in your request. When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.

NOTE: If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request.

Source
usage=(usage : CompletionUsage | Nil)

An optional field that will only be present when you set stream_options: {"include_usage": true} in your request. When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.

NOTE: If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request.

Source