多语言翻译与本地化

import os
from openai import OpenAI

client = OpenAI(base_url="https://open.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"])

GLOSSARY = {"土土金 API": "Tutujin API", "分组": "group", "用量明细": "Usage"}
SYSTEM = (
    "Translate Simplified Chinese into natural English for a software product. "
    "Keep Markdown, numbers, code, URLs and placeholders such as %s unchanged. "
    "Always use these term translations:\n"
    + "\n".join(k + " => " + v for k, v in GLOSSARY.items())
)


def chunks(text, limit=1500):
    """Split on blank lines so every request stays small and paragraphs stay whole."""
    part = ""
    for para in text.split("\n\n"):
        if part and len(part) + len(para) > limit:
            yield part
            part = ""
        part = part + "\n\n" + para if part else para
    if part:
        yield part


def translate(text):
    out = []
    for piece in chunks(text):
        resp = client.chat.completions.create(
            model="deepseek-v4.1-flash",
            messages=[
                {"role": "system", "content": SYSTEM},  # identical prefix on every call
                {"role": "user", "content": piece},
            ],
            temperature=0.2,
        )
        out.append(resp.choices[0].message.content)
    return "\n\n".join(out)


with open("article.zh.md", encoding="utf-8") as f:
    print(translate(f.read()))
# Important pages: send source and translation to claude-sonnet-5-5 and ask it to flag omissions and wrong terms.