Nắm Vững Structured Output Với LLMs (JSON Mode)

from openai import OpenAI
 
client = OpenAI()
 
response = client.chat.completions.create(
    model="gpt-4o",
    response_format={"type": "json_object"},
    messages=[
        {
            "role": "system",
            "content": "You extract product information and return it as JSON with fields: name, price, category, description."
        },
        {
            "role": "user",
            "content": "The new AirPods Pro 3 cost $249 and feature hearing health capabilities with improved noise cancellation."
        }
    ]
)
 
data = json.loads(response.choices[0].message.content)
print(data)
# {"name": "AirPods Pro 3", "price": 249, "category": "audio", "description": "..."}

from openai import OpenAI
from pydantic import BaseModel
 
class ProductInfo(BaseModel):
    name: str
    price: float
    currency: str
    category: str
    features: list[str]
    in_stock: bool
 
client = OpenAI()
 
response = client.beta.chat.completions.parse(
    model="gpt-4o",
    response_format=ProductInfo,
    messages=[
        {
            "role": "system",
            "content": "Extract product information from the user's text."
        },
        {
            "role": "user",
            "content": "The Sony WH-1000XM6 headphones ($348) feature 40-hour battery life, multipoint connection, and improved ANC. Currently available."
        }
    ]
)
 
product = response.choices[0].message.parsed
print(product.name)       # "Sony WH-1000XM6"
print(product.features)   # ["40-hour battery life", "multipoint connection", "improved ANC"]

import anthropic
 
client = anthropic.Anthropic()
 
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    tools=[
        {
            "name": "extract_product",
            "description": "Extract structured product information",
            "input_schema": {
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "price": {"type": "number"},
                    "currency": {"type": "string"},
                    "category": {"type": "string"},
                    "features": {
                        "type": "array",
                        "items": {"type": "string"}
                    },
                    "in_stock": {"type": "boolean"}
                },
                "required": ["name", "price", "currency", "category", "features", "in_stock"]
            }
        }
    ],
    tool_choice={"type": "tool", "name": "extract_product"},
    messages=[
        {
            "role": "user",
            "content": "Extract product info: The Sony WH-1000XM6 headphones ($348) feature 40-hour battery life, multipoint connection, and improved ANC. Currently available."
        }
    ]
)
 
# Dữ liệu có cấu trúc nằm trong tool use block
tool_use_block = next(
    block for block in response.content if block.type == "tool_use"
)
product_data = tool_use_block.input
print(product_data["name"])      # "Sony WH-1000XM6"
print(product_data["features"])  # ["40-hour battery life", ...]

# OpenAI với Pydantic model lồng nhau
class Address(BaseModel):
    street: str
    city: str
    country: str
    postal_code: str
 
class ContactInfo(BaseModel):
    email: str
    phone: str | None
    address: Address
 
class CompanyProfile(BaseModel):
    name: str
    industry: str
    founded_year: int
    contacts: list[ContactInfo]
    annual_revenue_usd: float | None

# Claude với JSON schema lồng nhau
nested_schema = {
    "type": "object",
    "properties": {
        "name": {"type": "string"},
        "industry": {"type": "string"},
        "founded_year": {"type": "integer"},
        "contacts": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "email": {"type": "string"},
                    "phone": {"type": ["string", "null"]},
                    "address": {
                        "type": "object",
                        "properties": {
                            "street": {"type": "string"},
                            "city": {"type": "string"},
                            "country": {"type": "string"},
                            "postal_code": {"type": "string"}
                        },
                        "required": ["street", "city", "country", "postal_code"]
                    }
                },
                "required": ["email", "address"]
            }
        }
    },
    "required": ["name", "industry", "founded_year", "contacts"]
}

import json
from openai import OpenAI
 
client = OpenAI()
 
def extract_with_fallback(text: str) -> dict:
    try:
        response = client.beta.chat.completions.parse(
            model="gpt-4o",
            response_format=ProductInfo,
            messages=[
                {"role": "system", "content": "Extract product information."},
                {"role": "user", "content": text}
            ]
        )
 
        # Kiểm tra trường hợp model từ chối
        if response.choices[0].message.refusal:
            return {"error": "Model refused", "reason": response.choices[0].message.refusal}
 
        return response.choices[0].message.parsed.model_dump()
 
    except Exception as e:
        return {"error": "Extraction failed", "reason": str(e)}