镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-07 23:16:48 +00:00
logging -> loguru: final stage
这个提交包含在:
@@ -1,4 +1,5 @@
|
||||
from crazy_functions.ipc_fns.mp import run_in_subprocess_with_timeout
|
||||
from loguru import logger
|
||||
|
||||
def force_breakdown(txt, limit, get_token_fn):
|
||||
""" 当无法用标点、空行分割时,我们用最暴力的方法切割
|
||||
@@ -76,7 +77,7 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
|
||||
remain_txt_to_cut = post
|
||||
remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
|
||||
process = fin_len/total_len
|
||||
print(f'正在文本切分 {int(process*100)}%')
|
||||
logger.info(f'正在文本切分 {int(process*100)}%')
|
||||
if len(remain_txt_to_cut.strip()) == 0:
|
||||
break
|
||||
return res
|
||||
@@ -119,7 +120,7 @@ if __name__ == '__main__':
|
||||
for i in range(5):
|
||||
file_content += file_content
|
||||
|
||||
print(len(file_content))
|
||||
logger.info(len(file_content))
|
||||
TOKEN_LIMIT_PER_FRAGMENT = 2500
|
||||
res = breakdown_text_to_satisfy_token_limit(file_content, TOKEN_LIMIT_PER_FRAGMENT)
|
||||
|
||||
|
||||
@@ -5,6 +5,7 @@ from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_
|
||||
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
||||
from shared_utils.colorful import *
|
||||
from loguru import logger
|
||||
import os
|
||||
|
||||
def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
@@ -93,7 +94,7 @@ def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwa
|
||||
generated_html_files.append(ch.save_file(create_report_file_name))
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
print('writing html result failed:', trimmed_format_exc())
|
||||
logger.error('writing html result failed:', trimmed_format_exc())
|
||||
|
||||
# 准备文件的下载
|
||||
for pdf_path in generated_conclusion_files:
|
||||
|
||||
在新工单中引用
屏蔽一个用户