zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

12.14 bug修复

Browse Source
This commit is contained in:
zy123 2024-12-14 12:12:06 +08:00
parent 605e404d11
commit 42a4473606
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
flask_app/货物标/技术参数要求提取.py
View File

@ -363,8 +363,12 @@ def generate_prompt(judge_res, full_text=None):
def get_technical_requirements(invalid_path,processed_filepath): def get_technical_requirements(invalid_path,processed_filepath):
file_id = "" file_id = ""
model_type = 1 # 默认使用豆包 model_type = 1 # 默认使用豆包
first_query_template="该文件是否说明了采购需求,即需要采购哪些货物?如果有,请回答'是',否则,回答'否'" #防止截取失败 first_query_template="""该文件是否说明了采购需求,即需要采购哪些内容（包括货物、设备、系统、功能模块等）?如果有,请回答'是',否则,回答'否'
文件内容：
{full_text}
"""
judge_query = generate_full_user_query(processed_filepath, first_query_template) judge_query = generate_full_user_query(processed_filepath, first_query_template)
print(judge_query)
judge_res = doubao_model(judge_query) judge_res = doubao_model(judge_query)
if '否' in judge_res: if '否' in judge_res:
model_type = 0 # 使用qianwen-long+invalid_path model_type = 0 # 使用qianwen-long+invalid_path
@ -523,7 +527,7 @@ def test_all_files_in_folder(input_folder, output_folder):
print(f"结果已保存到: {output_file_path}") print(f"结果已保存到: {output_file_path}")
except Exception as e: except Exception as e:
print(f"处理文件 {file_path} 时出错: {e}") print(f"处理文件 {file_path} 时出错: {e}")
# 如果采购需求为空 考虑再调用一次大模型 qianwen-stream
if __name__ == "__main__": if __name__ == "__main__":
start_time=time.time() start_time=time.time()
# truncate_file="C:\\Users\\Administrator\\Desktop\\fsdownload\\469d2aee-9024-4993-896e-2ac7322d41b7\\ztbfile_procurement.docx" # truncate_file="C:\\Users\\Administrator\\Desktop\\fsdownload\\469d2aee-9024-4993-896e-2ac7322d41b7\\ztbfile_procurement.docx"
@ -533,11 +537,11 @@ if __name__ == "__main__":
# truncate_file="D:\\flask_project\\flask_app\\static\\output\\output1\\e7dda5cb-10ba-47a8-b989-d2993d34bb89\\ztbfile_procurement.docx" # truncate_file="D:\\flask_project\\flask_app\\static\\output\\output1\\e7dda5cb-10ba-47a8-b989-d2993d34bb89\\ztbfile_procurement.docx"
# output_folder="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\tmp" # output_folder="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\tmp"
# file_id = upload_file(truncate_file) # file_id = upload_file(truncate_file)
invalid_path=r"C:\Users\Administrator\Desktop\fsdownload\a110ed59-00e8-47ec-873a-bd4579a6e628\ztbfile.pdf" invalid_path=r"C:\Users\Administrator\Desktop\fsdownload\8c63f0c9-d642-4f0c-918c-33db5efd6cd0\extract1.txt"
# file_id=upload_file(truncate_file) # file_id=upload_file(truncate_file)
processed_filepath = pdf2txt(truncate_file) # processed_filepath = pdf2txt(truncate_file)
# processed_filepath=r"C:\Users\Administrator\Desktop\fsdownload\e702f1e6-095d-443d-bb7d-ef2e42037cb1\金水河沿线排涝泵站提档升级项目.txt" processed_filepath=r"C:\Users\Administrator\Desktop\fsdownload\8c63f0c9-d642-4f0c-918c-33db5efd6cd0\extract1.txt"
res=get_technical_requirements(truncate_docfile,invalid_path,processed_filepath) res=get_technical_requirements(invalid_path,processed_filepath)
json_string = json.dumps(res, ensure_ascii=False, indent=4) json_string = json.dumps(res, ensure_ascii=False, indent=4)
print(json_string) print(json_string)
# # input_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\output1" # # input_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\output1"