Implementation:Openai Openai python Response Output Text Annotation Added

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Responses_API
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete type for representing an event emitted when an annotation is added to output text content during a streaming response, provided by the openai-python SDK.

Description

ResponseOutputTextAnnotationAddedEvent is a Pydantic model that represents the response.output_text.annotation.added streaming event. It is emitted when an annotation (such as a citation or file path) is appended to a text output content part. The event carries the annotation object itself, positional indices (annotation_index, content_index, output_index), the item_id of the parent output item, and a sequence_number for ordering within the event stream.

Usage

Import this type when you need to handle or type-check annotation-added events during streaming responses, for example when processing citations that appear in real time.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/response_output_text_annotation_added_event.py

Signature

class ResponseOutputTextAnnotationAddedEvent(BaseModel):
    """Emitted when an annotation is added to output text content."""

    annotation: object
    annotation_index: int
    content_index: int
    item_id: str
    output_index: int
    sequence_number: int
    type: Literal["response.output_text.annotation.added"]

Import

from openai.types.responses import ResponseOutputTextAnnotationAddedEvent

I/O Contract

Fields

Name	Type	Required	Description
annotation	object	Yes	The annotation object being added (see annotation schema for details).
annotation_index	int	Yes	The index of the annotation within the content part.
content_index	int	Yes	The index of the content part within the output item.
item_id	str	Yes	The unique identifier of the item to which the annotation is being added.
output_index	int	Yes	The index of the output item in the response's output array.
sequence_number	int	Yes	The sequence number of this event.
type	Literal["response.output_text.annotation.added"]	Yes	The type of the event. Always 'response.output_text.annotation.added'.

Usage Examples

import openai

client = openai.OpenAI()

stream = client.responses.create(
    model="gpt-4o",
    input="Summarize recent AI news with citations.",
    tools=[{"type": "web_search_preview"}],
    stream=True,
)

for event in stream:
    if event.type == "response.output_text.annotation.added":
        print(f"Annotation added at index {event.annotation_index}: {event.annotation}")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus