합성 데이터 & 데이터 Flywheel

import json, itertools
from openai import OpenAI

client = OpenAI()

def generate_pair(topic: str, difficulty: str) -> dict:
    r = client.chat.completions.create(
        model="gpt-4o",
        messages=[{
            "role": "system",
            "content": (
                "Generate a training example for a Python coding assistant. "
                "Output JSON: {\"question\": \"...\", \"answer\": \"...\"}. "
                "Answer should include code AND a one-paragraph explanation. "
                f"Difficulty: {difficulty}."
            ),
        }, {
            "role": "user",
            "content": f"Topic: {topic}",
        }],
        response_format={"type": "json_object"},
        temperature=0.8,
    )
    return json.loads(r.choices[0].message.content)

TOPICS = ["list comprehensions", "decorators", "async/await",
          "file handling", "error handling", "classes", "generators"]
DIFFICULTIES = ["beginner", "intermediate", "advanced"]

examples = []
for topic, diff in itertools.product(TOPICS, DIFFICULTIES):
    for _ in range(10):  # 10 per cell
        pair = generate_pair(topic, diff)
        examples.append({"messages": [
            {"role": "system", "content": "You are a Python expert."},
            {"role": "user",   "content": pair["question"]},
            {"role": "assistant", "content": pair["answer"]},
        ]})

print(f"Generated {len(examples)} examples")
# 7 topics × 3 difficulties × 10 = 210 examples