Jump to content

Connect Leeroopedia MCP: Equip your AI agents to search best practices, build plans, verify code, diagnose failures, and look up hyperparameter defaults.

Implementation:Openai Openai python Realtime Conversation Item Create

From Leeroopedia
Knowledge Sources
Domains Realtime_Communication, Conversation
Last Updated 2026-02-15 00:00 GMT

Overview

Concrete tool for sending conversation items and triggering responses over a Realtime WebSocket connection provided by the OpenAI Python SDK.

Description

The RealtimeConversationItemResource.create() method adds items (user messages, function call outputs) to the conversation. The RealtimeResponseResource.create() method triggers the model to generate a response based on the current conversation state. Both send typed events over the WebSocket connection.

Usage

Use connection.conversation.item.create() to add user text or function results. Use connection.response.create() to trigger generation.

Code Reference

Source Location

  • Repository: openai-python
  • File: src/openai/resources/beta/realtime/realtime.py
  • Lines: L724-814 (sync ConversationItemResource), L976-1066 (async), L622-665 (ResponseResource)

Signature

class AsyncRealtimeConversationItemResource:
    async def create(
        self,
        *,
        item: ConversationItemParam,
        event_id: str | NotGiven = NOT_GIVEN,
        previous_item_id: str | NotGiven = NOT_GIVEN,
    ) -> None:
        """
        Adds a conversation item.

        Args:
            item: Conversation item (message with role and content).
            event_id: Optional custom event ID.
            previous_item_id: Insert after this item ID.
        """
class AsyncRealtimeResponseResource:
    async def create(
        self,
        *,
        event_id: str | NotGiven = NOT_GIVEN,
        response: response_create_event_param.Response | NotGiven = NOT_GIVEN,
    ) -> None:
        """
        Triggers model response generation.

        Args:
            event_id: Optional custom event ID.
            response: Optional response config overrides (modalities, instructions).
        """

Import

from openai import AsyncOpenAI
# Access via connection.conversation.item.create() and connection.response.create()

I/O Contract

Inputs

Name Type Required Description
item ConversationItemParam Yes Message with type, role, and content array
previous_item_id str No Insert after this specific item
response ResponseParam No Override modalities/instructions for this response

Outputs

Name Type Description
(WebSocket events) None Server responds with conversation.item.created, then response.created/response.done

Usage Examples

Send Text Message and Get Response

async with client.beta.realtime.connect(model="gpt-4o-realtime-preview") as connection:
    await connection.session.update(session={"modalities": ["text"]})

    # Add user message
    await connection.conversation.item.create(item={
        "type": "message",
        "role": "user",
        "content": [{"type": "input_text", "text": "What is Python?"}],
    })

    # Trigger response
    await connection.response.create()

    # Receive response events
    async for event in connection:
        if event.type == "response.text.delta":
            print(event.delta, end="", flush=True)
        elif event.type == "response.done":
            break

Send Function Call Output

await connection.conversation.item.create(item={
    "type": "function_call_output",
    "call_id": "call_abc123",
    "output": '{"temperature": 22, "condition": "sunny"}',
})
await connection.response.create()

Related Pages

Implements Principle

Requires Environment

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment