mulu_ner/generate_mulu_only.py

import time

from tqdm import tqdm
import random
import requests
import json
import threading
from threading import Thread
import redis

lock = threading.RLock()

pool = redis.ConnectionPool(host='104.244.90.248', port=63179, max_connections=50, db=10, password='Zhicheng123*')
redis_ = redis.Redis(connection_pool=pool, decode_responses=True)


with open("api_key.txt", "r",) as f:
    a = f.read()
    a = a.split("\n")

redis_key_name_openaikey_list = "openaikey_list"
redis_zirenwu = "redis_zirenwu"

api_key_list = []
for i in a:
    api_key_list.append(str(i.split("----")[-1]))

for i in api_key_list:
    redis_.rpush(redis_key_name_openaikey_list, i)

lock = threading.RLock()

prompt_dict = {
    "mulu_prompt": "为论文题目《{}》生成目录，要求只有一级标题和二级标题，一级标题使用中文数字 例如一、xxx；二级标题使用阿拉伯数字 例如1.1 xxx；一级标题不少于7个；每个一级标题至少包含3个二级标题",
}

with open("./data/题目4_new.txt", encoding="utf-8") as f:
    text = f.read()

text_list = text.split("\n")

title_list = []
for i in text_list:
    title_list.append(i.split("@@@@@")[0])

random.shuffle(title_list)

print(len(title_list))

zirenwu_list = []

for title in title_list:
    for prompt in prompt_dict:
        zirenwu_list.append((prompt, str(prompt_dict[prompt]).format(title)))

for i in zirenwu_list:
    redis_.rpush(redis_zirenwu, str(i))


def request_api_chatgpt(api_key, task_type, prompt):
    t1 = time.time()
    global api_key_list
    global zirenwu_list
    try:
        OPENAI_API_KEY = api_key
        url = "https://api.openai.com/v1/chat/completions"
        headers = {
            "Content-Type": "application/json",
            "Authorization": f"Bearer {OPENAI_API_KEY}"
        }
        data = {
            "model": "gpt-3.5-turbo",
            "messages": [
                {"role": "user", "content": prompt},
            ],
            "temperature": 0.5
        }
        response = requests.post(url,
                                 headers=headers,
                                 data=json.dumps(data),
                                 timeout=1200)

        res = response.json()
        text = res["choices"][0]["message"]["content"]

        # api_key_list.append(api_key)
        t2 = time.time()
        t_n = t2 - t1
        lock.acquire()
        with open("/home/majiahui/mulu_ner/data/paper_prompt_title_4/title_{}_data.txt".format(task_type), mode="a") as f:
            f.write(prompt)
            f.write("**************")
            f.write(text)
            f.write("\n")
            f.write("=================================================================================================")
        lock.release()

        if t_n > 20:
            redis_.rpush(redis_key_name_openaikey_list, api_key)
        else:
            time.sleep(20 - t_n)
            redis_.rpush(redis_key_name_openaikey_list, api_key)

    except:
        print("task_type_bad", task_type)
        print("api_key_bad", api_key)
        time.sleep(20)
        lock.acquire()
        redis_.rpush(redis_key_name_openaikey_list, api_key)
        redis_.rpush(redis_zirenwu, str((task_type, prompt)))
        lock.release()


if __name__ == '__main__':
    while True:
        if redis_.llen(redis_zirenwu) == 0:
            time.sleep(1)
            continue
        elif redis_.llen(redis_zirenwu) != 0 and redis_.llen(redis_key_name_openaikey_list) != 0:
            lock.acquire()
            api_key = redis_.lpop(redis_key_name_openaikey_list)
            api_key = api_key.decode('UTF-8')
            dan_zirenwu = redis_.lpop(redis_zirenwu)
            dan_zirenwu = dan_zirenwu.decode('UTF-8')
            lock.release()
            # dan_zirenwu = zirenwu_list.pop(0)
            dan_zirenwu = eval(dan_zirenwu)
            task_type, prompt = dan_zirenwu[0], dan_zirenwu[1]
            t = Thread(target=request_api_chatgpt, args=(api_key, task_type, prompt))
            t.start()
        elif redis_.llen(redis_key_name_openaikey_list) == 0:
            time.sleep(1)
            continue
        else:
            time.sleep(1)
            continue