Streaming mit semantischen Events

Arbeiten mit der OpenAI Responses API

James Chapman

AI Curriculum Manager, DataCamp

Warum streamen?

Streaming aus

Warum streamen?

Streaming an

Semantische Events

Strukturierte Updates, die beschreiben, was passiert

Semantische Events

Strukturierte Updates, die beschreiben, was passiert

Eventtyp	Beschreibung
`response.created`	Modell hat mit der Ausgabe begonnen
`response.output_text.delta`	Teil-Text-Update
`response.output_text.done`	Textblock fertig
`response.function_call.arguments.delta`	Streaming von Tool-Argumenten
`response.completed`	Antwort vollständig

Beispiel: Einfaches Text-Streaming

prompt = "Explain the seasons of the year concisely to a child."


with client.responses.create(model="gpt-5.4-mini", input=prompt, stream=True) as stream:

    current_text = ""


    for event in stream:
        if event.type == "response.output_text.delta":

            current_text += event.delta
            print(current_text)

Beispiel: Einfaches Text-Streaming

Text-Streaming

Beispiel: Mehrere Events verarbeiten

prompt = "Explain how a neural network learns concisely for a child."

with client.responses.create(model="gpt-5.4-mini", input=prompt, stream=True) as stream:

    for event in stream:
        if event.type == "response.created":

            print("Response started...\n")


        elif event.type == "response.output_text.done":

            print("\n\n--- Text block finished ---\n")


        elif event.type == "response.completed":

            print(f"\nFull response:\n{current_text}")

Beispiel: Mehrere Events verarbeiten

Mehrere Events

Beispiel: Tool-Events streamen

convert_currency() -> str:

date_time: str
from_timezone: str
to_timezone: str

tools = [
    {
        "type": "function",
        "name": "convert_currency",
        ...
     }
]

Frankfurter

Beispiel: Tool-Events streamen

prompt = "How much is 120 euros in British pounds using the current exchange rate?"


with client.responses.create(model="gpt-5.4-mini", input=prompt, tools=tools, stream=True) as stream:

    current_args = ""

    for event in stream:
        if event.type == "response.function_call_arguments.delta":

            current_args += event.delta
            print("Streaming args:", current_args)

        elif event.type == "response.function_call_arguments.done":

            print("\nFinal arguments:", event.arguments)

        elif event.type == "response.completed":

            print("\n--- Completed ---")

Beispiel: Tool-Events streamen

Tool-Events-Streaming

Zusammenfassung

Semantische Events in ChatGPT

¹ Semantische Events in ChatGPT

Lass uns üben!

Arbeiten mit der OpenAI Responses API