Function Calling & Structured Outputs

ModelMart fully supports Function Calling (Tools) and JSON Schema Structured Outputs.

---

1. Tool Calling Example (Python)

from openai import OpenAI
import json

client = OpenAI(
    api_key="mm_live_xxxxxxxxxxxx",
    base_url="https://api.modelmart.io.vn/v1"
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get real-time weather for a given city.",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        }
    }
]

messages = [{"role": "user", "content": "What's the weather in Tokyo?"}]

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=messages,
    tools=tools
)

tool_call = response.choices[0].message.tool_calls[0]
print(f"Tool called: {tool_call.function.name} with args: {tool_call.function.arguments}")

---

2. Structured JSON Outputs

Enforce strict output compliance with JSON Schema:

response = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[
        {"role": "user", "content": "Extract: Alice, 30, Software Engineer in London."}
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "person",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "age": {"type": "integer"},
                    "occupation": {"type": "string"},
                    "city": {"type": "string"}
                },
                "required": ["name", "age", "occupation", "city"],
                "additionalProperties": False
            }
        }
    }
)

print(response.choices[0].message.content)