2024-10-24 14:34:37 +08:00
|
|
|
|
import json
|
|
|
|
|
|
from flask_app.general.json_utils import clean_json_string
|
|
|
|
|
|
from flask_app.general.多线程提问 import multi_threading,read_questions_from_file
|
2024-10-24 10:56:33 +08:00
|
|
|
|
from flask_app.general.通义千问long import upload_file,qianwen_long
|
2024-10-24 11:29:31 +08:00
|
|
|
|
|
2024-10-24 14:34:37 +08:00
|
|
|
|
# 从json文件中读取数据
|
|
|
|
|
|
with open('test.json', 'r', encoding='utf-8') as f:
|
|
|
|
|
|
data_dict = json.load(f)
|
|
|
|
|
|
|
|
|
|
|
|
# 定义目标名称列表
|
|
|
|
|
|
target_names = [
|
|
|
|
|
|
"营业执照",
|
|
|
|
|
|
"开户信息",
|
|
|
|
|
|
"法定代表人身份证",
|
|
|
|
|
|
"法定代表人授权人身份证",
|
|
|
|
|
|
# "人员证书",
|
|
|
|
|
|
# "人员社保资料",
|
|
|
|
|
|
# "劳动合同",
|
|
|
|
|
|
# "企业证书",
|
|
|
|
|
|
# "企业业绩",
|
|
|
|
|
|
# "财务信息（财务审计报告）",
|
|
|
|
|
|
# "财务信息（缴纳税收证明）",
|
|
|
|
|
|
# "财务信息（缴纳社保证明）"
|
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
# 定义user_query模板
|
|
|
|
|
|
def generate_user_query(target, chapters, keywords):
|
|
|
|
|
|
template = f"""该文件为投标文件格式要求的部分，请你根据该招标文件回答：{target}应该附在该文件哪个地方？你可能需要查找以下章节（若有）：{', '.join([f"'{chapter}'" for chapter in chapters])}；或者查找以下关键字出现的地方：{', '.join([f"'{kw}'" for kw in keywords])}，你需要确定相关信息所在章节。
|
|
|
|
|
|
我需要将{target}贴在该章节的最后面，但是在下一章（别的内容）之前，目前我需要定位到插入的位置，请你返回给我插入位置的上下文，其中下文应该是下一章的章节名或开头内容，字数限制在30字以内，以json格式返回，键名分别是'上文','下文'，上下文格式内容应完全与原文保持一致，不得擅自删减总结，示例输出如下：
|
|
|
|
|
|
{{
|
|
|
|
|
|
"上文":"投标人： （盖单位章）
|
|
|
|
|
|
年 月 日",
|
|
|
|
|
|
"下文":"四、投标保证金
|
|
|
|
|
|
（招标人名称）："
|
|
|
|
|
|
}}
|
|
|
|
|
|
"""
|
|
|
|
|
|
return template
|
|
|
|
|
|
|
|
|
|
|
|
# 生成user_query_list
|
|
|
|
|
|
user_query_list = []
|
|
|
|
|
|
|
|
|
|
|
|
for target in target_names:
|
|
|
|
|
|
if target in data_dict:
|
|
|
|
|
|
chapters = data_dict[target]["章节"]
|
|
|
|
|
|
keywords = data_dict[target]["关键字"]
|
|
|
|
|
|
user_query = generate_user_query(target, chapters, keywords)
|
|
|
|
|
|
user_query_list.append({
|
|
|
|
|
|
"target": target,
|
|
|
|
|
|
"query": user_query
|
|
|
|
|
|
})
|
|
|
|
|
|
else:
|
|
|
|
|
|
print(f"警告：'{target}'未在数据字典中找到相关信息。")
|
|
|
|
|
|
|
|
|
|
|
|
# 将生成的查询添加到queries列表
|
|
|
|
|
|
queries = [item['query'] for item in user_query_list]
|
|
|
|
|
|
truncate_file="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest19\\zbtest19_214-320.pdf"
|
|
|
|
|
|
# 上传文件并获取file_id
|
|
|
|
|
|
file_id = upload_file(truncate_file)
|
|
|
|
|
|
# 使用multi_threading并行处理查询
|
|
|
|
|
|
results = multi_threading(queries, "", file_id, 2)
|
|
|
|
|
|
# 清理返回结果并输出
|
|
|
|
|
|
baseinfo_list = [clean_json_string(res) for _, res in results] if results else []
|
|
|
|
|
|
for i in baseinfo_list:
|
|
|
|
|
|
print(json.dumps(i, ensure_ascii=False, indent=4))
|
