> ## Documentation Index
> Fetch the complete documentation index at: https://wb-21fd5541-docs-hivemind-launch.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Activer la sortie structurée

> Comment configurer la sortie structurée dans les réponses de Serverless Inference

La sortie structurée est similaire au [mode JSON](/fr/inference/response-settings/json-mode), mais elle offre l’avantage supplémentaire de garantir que la réponse du modèle respecte le schéma que vous spécifiez. Nous vous recommandons d’utiliser la sortie structurée plutôt que le mode JSON lorsque c’est possible.

Pour activer la sortie structurée, spécifiez `json_schema` comme type de `response_format` dans la requête :

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    import json
    import openai

    client = openai.OpenAI(
        base_url='https://api.inference.wandb.ai/v1',
        api_key="<your-api-key>",  # Créez une clé API sur https://wandb.ai/settings
    )

    response = client.chat.completions.create(
        model="openai/gpt-oss-20b",
        messages=[
            {"role": "system", "content": "Extract the event information."},
            {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
        ],
        response_format={
            "type": "json_schema",
            "json_schema": {
                "name": "CalendarEventResponse",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "name": {"type": "string"},
                        "date": {"type": "string"},
                        "participants": {"type": "array", "items": {"type": "string"}},
                    },
                    "required": ["name", "date", "participants"],
                    "additionalProperties": False,
                },
            },
        },
    )

    content = response.choices[0].message.content
    parsed = json.loads(content)
    print(parsed)
    ```
  </Tab>

  <Tab title="Bash">
    ```bash theme={null}
    curl https://api.inference.wandb.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer <your-api-key>" \
      -d '{
        "model": "openai/gpt-oss-20b",
        "messages": [
            {"role": "system", "content": "Extract the event information."},
            {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."},
        ],
        "response_format": {
            "type": "json_schema",
            "json_schema": {
                "name": "CalendarEventResponse",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "name": {"type": "string"},
                        "date": {"type": "string"},
                        "participants": {"type": "array", "items": {"type": "string"}},
                    },
                    "required": ["name", "date", "participants"],
                    "additionalProperties": False,
                },
            },
        },
      }'
    ```
  </Tab>
</Tabs>