科研与高校

import json
import os
import time

from openai import OpenAI

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

MODELS = ["gpt-5.5", "deepseek-v4-pro"]
# Record exactly what you send. Reasoning models may reject temperature or max_tokens,
# so add sampling parameters per model only where they are supported.
PARAMS = {"seed": 42}


def run(questions, out_path="results.jsonl"):
    with open(out_path, "a", encoding="utf-8") as f:
        for model in MODELS:
            for q in questions:
                started = time.time()
                resp = client.chat.completions.create(
                    model=model,
                    messages=[{"role": "user", "content": q["prompt"]}],
                    **PARAMS,
                )
                f.write(json.dumps({
                    "question_id": q["id"],
                    "model": model,
                    "returned_model": resp.model,
                    "params": PARAMS,
                    "answer": resp.choices[0].message.content,
                    "usage": resp.usage.model_dump() if resp.usage else None,
                    "latency_s": round(time.time() - started, 2),
                    "called_at": time.strftime("%Y-%m-%dT%H:%M:%S%z"),
                }, ensure_ascii=False) + "\n")


run([{"id": "q1", "prompt": "State the main finding of the abstract below in one sentence: ..."}])
# Literature search: embed abstracts with text-embedding-3-large and store the vectors with their DOIs.