데이터 준비 & 업로드

from openai import OpenAI
import json

client = OpenAI()

def validate_openai_data(filepath: str) -> int:
    """Returns number of valid examples; raises on hard errors."""
    with open(filepath) as f:
        data = [json.loads(line) for line in f]
    print(f"Number of examples: {len(data)}")
    if len(data) < 10:
        raise ValueError(f"Too few examples: {len(data)} < 10")

    for i, ex in enumerate(data):
        msgs = ex.get("messages", [])
        if not msgs:
            raise ValueError(f"Example {i}: missing 'messages'")
        if msgs[-1]["role"] != "assistant":
            raise ValueError(f"Example {i}: last message must be assistant")
        for j, m in enumerate(msgs):
            if not (m.get("content") or "").strip():
                raise ValueError(f"Example {i} msg {j}: empty content")

    chars = sum(len(json.dumps(ex)) for ex in data)
    tokens = chars // 4
    print(f"Estimated tokens: ~{tokens:,}")
    print(f"Estimated training cost on gpt-4.1-mini @ 3 epochs: "
          f"~${tokens * 3 / 1_000_000 * 0.80:.2f}")
    return len(data)

validate_openai_data("training_data.jsonl")

# Upload after local validation passes
training_file = client.files.create(
    file=open("training_data.jsonl", "rb"),
    purpose="fine-tune",
)
print(f"File ID: {training_file.id}")

# Optional but recommended: validation file for monitoring
validation_file = client.files.create(
    file=open("validation_data.jsonl", "rb"),
    purpose="fine-tune",
)
print(f"Validation File ID: {validation_file.id}")