CC/gpt_academic
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

version 3.6

Browse Source
This commit is contained in:
binary-husky
2023-11-20 01:17:59 +08:00
parent 971ac206f3
commit 17d0a32f36
120 changed files with 12092 additions and 626 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
crazy_functions/批量总结PDF文档.py
View File

@@ -1,5 +1,5 @@
from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
from toolbox import CatchException, report_execption
from toolbox import CatchException, report_exception
from toolbox import write_history_to_file, promote_file_to_downloadzone
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from .crazy_utils import read_and_clean_pdf_text
@@ -21,7 +21,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
TOKEN_LIMIT_PER_FRAGMENT = 2500
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
from request_llm.bridge_all import model_info
from request_llms.bridge_all import model_info
enc = model_info["gpt-3.5-turbo"]['tokenizer']
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
@@ -119,7 +119,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
try:
import fitz
except:
report_execption(chatbot, history,
report_exception(chatbot, history,
a = f"解析项目: {txt}",
b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -133,7 +133,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
project_folder = txt
else:
if txt == "": txt = '空空如也的输入栏'
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
@@ -142,7 +142,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
# 如果没找到任何文件
if len(file_manifest) == 0:
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return