chat_completion_chunk

Classes:

Name	Description
`ChatCompletionChunk`
`Choice`
`ChoiceDelta`
`ChoiceDeltaFunctionCall`
`ChoiceDeltaToolCall`
`ChoiceDeltaToolCallFunction`
`ChoiceLogprobs`

ChatCompletionChunk

Attributes:

Name	Type	Description
`choices`	`List[Choice]`	A list of chat completion choices.
`created`	`int`	The Unix timestamp (in seconds) of when the chat completion was created.
`id`	`str`	A unique identifier for the chat completion. Each chunk has the same ID.
`model`	`str`	The model to generate the completion.
`object`	`Literal['chat.completion.chunk']`	The object type, which is always `chat.completion.chunk`.
`system_fingerprint`	`Optional[str]`	This fingerprint represents the backend configuration that the model runs with.

choices `instance-attribute`

choices: List[Choice]

A list of chat completion choices.

Can be more than one if n is greater than 1.

created `instance-attribute`

created: int

The Unix timestamp (in seconds) of when the chat completion was created.

Each chunk has the same timestamp.

id `instance-attribute`

id: str

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

model `instance-attribute`

model: str

The model to generate the completion.

object `instance-attribute`

object: Literal['chat.completion.chunk']

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

system_fingerprint `class-attribute` `instance-attribute`

system_fingerprint: Optional[str] = None

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.

Choice

Attributes:

Name	Type	Description
`delta`	`ChoiceDelta`	A chat completion delta generated by streamed model responses.
`finish_reason`	`Optional[Literal['stop', 'length', 'tool_calls', 'content_filter', 'function_call']]`	The reason the model stopped generating tokens.
`index`	`int`	The index of the choice in the list of choices.
`logprobs`	`Optional[ChoiceLogprobs]`	Log probability information for the choice.

delta `instance-attribute`

delta: ChoiceDelta

A chat completion delta generated by streamed model responses.

finish_reason `class-attribute` `instance-attribute`

finish_reason: Optional[
    Literal[
        "stop",
        "length",
        "tool_calls",
        "content_filter",
        "function_call",
    ]
] = None

The reason the model stopped generating tokens.

This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.

index `instance-attribute`

index: int

The index of the choice in the list of choices.

logprobs `class-attribute` `instance-attribute`

logprobs: Optional[ChoiceLogprobs] = None

Log probability information for the choice.

ChoiceDelta

Attributes:

Name	Type	Description
`content`	`Optional[str]`	The contents of the chunk message.
`function_call`	`Optional[ChoiceDeltaFunctionCall]`	Deprecated and replaced by `tool_calls`.
`role`	`Optional[Literal['system', 'user', 'assistant', 'tool']]`	The role of the author of this message.
`tool_calls`	`Optional[List[ChoiceDeltaToolCall]]`

content `class-attribute` `instance-attribute`

content: Optional[str] = None

The contents of the chunk message.

function_call `class-attribute` `instance-attribute`

function_call: Optional[ChoiceDeltaFunctionCall] = None

Deprecated and replaced by tool_calls.

The name and arguments of a function that should be called, as generated by the model.

role `class-attribute` `instance-attribute`

role: Optional[
    Literal["system", "user", "assistant", "tool"]
] = None

The role of the author of this message.

tool_calls `class-attribute` `instance-attribute`

tool_calls: Optional[List[ChoiceDeltaToolCall]] = None

ChoiceDeltaFunctionCall

Attributes:

Name	Type	Description
`arguments`	`Optional[str]`	The arguments to call the function with, as generated by the model in JSON
`name`	`Optional[str]`	The name of the function to call.

arguments `class-attribute` `instance-attribute`

arguments: Optional[str] = None

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name `class-attribute` `instance-attribute`

name: Optional[str] = None

The name of the function to call.

ChoiceDeltaToolCall

Attributes:

Name	Type	Description
`function`	`Optional[ChoiceDeltaToolCallFunction]`
`id`	`Optional[str]`	The ID of the tool call.
`index`	`int`
`type`	`Optional[Literal['function']]`	The type of the tool. Currently, only `function` is supported.

function `class-attribute` `instance-attribute`

function: Optional[ChoiceDeltaToolCallFunction] = None

id `class-attribute` `instance-attribute`

id: Optional[str] = None

The ID of the tool call.

index `instance-attribute`

index: int

type `class-attribute` `instance-attribute`

type: Optional[Literal['function']] = None

The type of the tool. Currently, only function is supported.

ChoiceDeltaToolCallFunction

Attributes:

Name	Type	Description
`arguments`	`Optional[str]`	The arguments to call the function with, as generated by the model in JSON
`name`	`Optional[str]`	The name of the function to call.

arguments `class-attribute` `instance-attribute`

arguments: Optional[str] = None

The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.

name `class-attribute` `instance-attribute`

name: Optional[str] = None

The name of the function to call.

ChoiceLogprobs

Attributes:

Name	Type	Description
`content`	`Optional[List[ChatCompletionTokenLogprob]]`	A list of message content tokens with log probability information.

content `class-attribute` `instance-attribute`

content: Optional[List[ChatCompletionTokenLogprob]] = None

A list of message content tokens with log probability information.

chat_completion_chunk