Skip to content

mirascope.core.openai.call_response_chunk

This module contains the OpenAICallResponseChunk class.

Usage Documentation

Streams

OpenAICallResponseChunk

Bases: BaseCallResponseChunk[ChatCompletionChunk, FinishReason]

A convenience wrapper around the OpenAI ChatCompletionChunk streamed chunks.

When calling the OpenAI API using a function decorated with openai_call and stream set to True, the stream will contain OpenAIResponseChunk instances with properties that allow for more convenient access to commonly used attributes.

Example:

from mirascope.core import prompt_template
from mirascope.core.openai import openai_call


@openai_call("gpt-4o-mini", stream=True)
def recommend_book(genre: str) -> str:
    return f"Recommend a {genre} book"


stream = recommend_book("fantasy")  # response is an `OpenAIStream`
for chunk, _ in stream:
    print(chunk.content, end="", flush=True)

content property 

content: str

Returns the content for the 0th choice delta.

finish_reasons property 

finish_reasons: list[FinishReason]

Returns the finish reasons of the response.

model property 

model: str

Returns the name of the response model.

id property 

id: str

Returns the id of the response.

usage property 

usage: CompletionUsage | None

Returns the usage of the chat completion.

input_tokens property 

input_tokens: int | None

Returns the number of input tokens.

output_tokens property 

output_tokens: int | None

Returns the number of output tokens.

audio property 

audio: bytes | None

Returns the audio data of the response.

audio_transcript property 

audio_transcript: str | None

Returns the transcript of the audio content.