비용: 임베딩 budget 과 호출 패턴

import hashlib, json
from pathlib import Path

CACHE = Path('embedding_cache.jsonl')

def cached_embed(texts: list[str]) -> list[list[float]]:
    cache: dict[str, list[float]] = {}
    if CACHE.exists():
        for line in CACHE.read_text().splitlines():
            row = json.loads(line)
            cache[row['hash']] = row['vec']

    results, misses, miss_hashes = [], [], []
    for t in texts:
        h = hashlib.sha256(t.encode()).hexdigest()
        if h in cache:
            results.append(cache[h])
        else:
            results.append(None)
            misses.append(t)
            miss_hashes.append(h)

    if misses:
        new_vecs = model.encode(misses, normalize_embeddings=True).tolist()
        with CACHE.open('a') as f:
            for h, v in zip(miss_hashes, new_vecs):
                f.write(json.dumps({'hash': h, 'vec': v}) + '\n')
        miss_iter = iter(new_vecs)
        results = [r if r is not None else next(miss_iter) for r in results]
    return results

from openai import OpenAI
from itertools import islice

client = OpenAI()

def batched(it, n):
    it = iter(it)
    while batch := list(islice(it, n)):
        yield batch

def embed_corpus(texts, batch_size=64):
    out = []
    for batch in batched(texts, batch_size):
        resp = client.embeddings.create(model='text-embedding-3-large', input=batch)
        out.extend([d.embedding for d in resp.data])
    return out