Structured Output

Learn how to use structured output in Private AI

​

Structured Output in Private AI

Private AI supports structured output, enabling you to receive responses in specific formats such as JSON structures. This is particularly useful for applications that require data to be processed or integrated into other systems.

​

Example of Structured Output

Replace <API_KEY> with your actual API key in the examples below.

import requests

response = requests.post(
    "https://inference.phala.com/v1/chat/completions",
    headers={
        "Authorization": "Bearer <API_KEY>",
        "Content-Type": "application/json",
    },
    json={
        "model": "z-ai/glm-5.3",
        "messages": [
            {"role": "user", "content": "What is the weather like in Los Angeles?"},
        ],
        "response_format": {
            "type": "json_schema",
            "json_schema": {
                "name": "weather",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "City or location name",
                        },
                        "temperature": {
                            "type": "number",
                            "description": "Temperature in Celsius",
                        },
                        "conditions": {
                            "type": "string",
                            "description": "Weather conditions description",
                        },
                    },
                    "required": ["location", "temperature", "conditions"],
                    "additionalProperties": False,
                },
            },
        },
    },
)

data = response.json()
info = data["choices"][0]["message"]["content"]
print(info)

Sample output of structured output

{
   "location":"Los Angeles",
   "temperature":75,
   "conditions":"Sunny with a few clouds"
}

​

Find Compatible Models

curl -s https://inference.phala.com/v1/models \
  | jq -r '.data[] | select((.supported_features // []) | index("structured_outputs")) | .id'