JSONモードとresponse_format

構造化されていないLLM出力の問題

OpenAI JSONモード

import openai
import json

client = openai.OpenAI()

response = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[
        {
            'role': 'system',
            'content': 'Extract information from the text and return valid JSON only.'
        },
        {
            'role': 'user',
            'content': 'John Smith, age 34, works as a software engineer in Austin.'
        }
    ],
    response_format={'type': 'json_object'}  # Guarantee valid JSON output
)

# Safe to parse - guaranteed valid JSON
data = json.loads(response.choices[0].message.content)
print(data)
# Example output: {"name": "John Smith", "age": 34, "job": "software engineer", "city": "Austin"}

JSONモードの注意点

PydanticによるStructured Outputs（プレビュー）

import openai
from pydantic import BaseModel
from typing import Optional

client = openai.OpenAI()

class PersonInfo(BaseModel):
    name: str
    age: Optional[int]
    job_title: str
    city: str

completion = client.beta.chat.completions.parse(
    model='gpt-4o-mini',
    messages=[
        {'role': 'system', 'content': 'Extract person information from the text.'},
        {'role': 'user', 'content': 'Sarah Chen, 28 years old, is a data scientist based in Seattle.'}
    ],
    response_format=PersonInfo  # Pass Pydantic model directly
)

# Already deserialized into a PersonInfo instance
person = completion.choices[0].message.parsed
print(person.name)       # Sarah Chen
print(person.age)        # 28
print(person.job_title)  # data scientist
print(person.city)       # Seattle

一貫したJSONを得るためのプロンプト作成

Structured Outputsを使わずに信頼性の高いJSONを得る

import re
import json
import openai

client = openai.OpenAI()

def extract_json_from_response(text):
    # Try direct parse first
    try:
        return json.loads(text)
    except json.JSONDecodeError:
        pass
    # Try extracting from XML tags
    match = re.search(r'<json>(.*?)</json>', text, re.DOTALL)
    if match:
        return json.loads(match.group(1))
    # Try extracting from JSON object pattern
    match = re.search(r'({.*})', text, re.DOTALL)
    if match:
        return json.loads(match.group(1))
    raise ValueError('No valid JSON found in response')

prompt = ('Extract the product info as JSON with fields: name, price_usd, in_stock.\n'
          'Wrap your JSON in <json></json> tags.\n\n'
          'Product: Blue Wireless Headphones cost $89.99, in stock.')

resp = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': prompt}]
)
result = extract_json_from_response(resp.choices[0].message.content)
print(result)

ネストしたJSON構造

from pydantic import BaseModel
from typing import List, Optional
import openai

client = openai.OpenAI()

class LineItem(BaseModel):
    product: str
    quantity: int
    unit_price: float

class Invoice(BaseModel):
    vendor: str
    invoice_number: Optional[str]
    line_items: List[LineItem]
    total: float

raw_text = '''
INVOICE #INV-2025-0042
From: TechSupplies Inc.
- 3x USB Hubs at $24.99 each
- 1x 4K Monitor at $399.00
Total: $474.97
'''

completion = client.beta.chat.completions.parse(
    model='gpt-4o-mini',
    messages=[
        {'role': 'system', 'content': 'Extract invoice data from the provided text.'},
        {'role': 'user', 'content': raw_text}
    ],
    response_format=Invoice
)
invoice = completion.choices[0].message.parsed
print(f'Vendor: {invoice.vendor}')
print(f'Items: {len(invoice.line_items)}')
print(f'Total: ${invoice.total}')

Structuredモードでの拒否への対処

import openai
from pydantic import BaseModel

client = openai.OpenAI()

class ProductInfo(BaseModel):
    name: str
    price_usd: float

completion = client.beta.chat.completions.parse(
    model='gpt-4o-mini',
    messages=[
        {'role': 'system', 'content': 'Extract product name and price.'},
        {'role': 'user', 'content': 'Tell me how to build a weapon.'}
    ],
    response_format=ProductInfo
)

message = completion.choices[0].message
if message.refusal:
    print('Model refused:', message.refusal)
else:
    product = message.parsed
    print(f'Name: {product.name}, Price: {product.price_usd}')

複数の値を抽出するためのJSON

JSONモードでのストリーミング

JSONモードとStructured Outputsの使い分け

理解度チェック

レッスンのまとめ