CommencerCommencer gratuitement

Streaming Semantic Events

You're building a weather assistant that provides real-time forecasts. The OpenAI client has been initialized and configured to work with the Responses API. You'll stream semantic events to track when the response starts, when text blocks finish, and when the full response is complete. This creates a more engaging user experience by showing progress as the model generates the forecast.

Cet exercice fait partie du cours

Working with the OpenAI Responses API

Afficher le cours

Instructions

  • Handle the "response.created" event by printing a start message.
  • Handle the "response.output_text.done" event by printing a completion message.
  • Handle the "response.completed" event by printing the full response text stored in current_text.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

prompt = "Explain how to read a weather forecast in one sentence for a beginner hiker."

with client.responses.create(model="gpt-5-mini", input=prompt, stream=True) as stream:
    for event in stream:
        # Find response created events
        if event.type == "____":
            print("Forecast generation started...\n")

        # Find output text completed events
        elif event.type == "____":
            print("\n--- Forecast complete ---\n")

        # Find response completed events
        elif event.type == "____":
            print(f"\nFull forecast:\n{current_text}")
Modifier et exécuter le code