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

增扩框架的参数IO

Browse Source
This commit is contained in:
qingxu fu
2023-04-09 20:42:23 +08:00
parent ea031ab05b
commit 0666fec86e
18 changed files with 239 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
crazy_functions/批量总结PDF文档pdfminer.py
View File

@@ -62,7 +62,7 @@ def readPdf(pdfPath):
return outTextList
def 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
import time, glob, os
from bs4 import BeautifulSoup
print('begin analysis on:', file_manifest)
@@ -78,39 +78,39 @@ def 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, hist
i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if not fast_debug:
msg = '正常'
# ** gpt request **
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[]) # 带超时倒计时
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, llm_kwargs, plugin_kwargs, history=[]) # 带超时倒计时
chatbot[-1] = (i_say_show_user, gpt_say)
history.append(i_say_show_user); history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg)
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) # 刷新界面
if not fast_debug: time.sleep(2)
all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
chatbot.append((i_say, "[Local Message] waiting gpt response."))
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
if not fast_debug:
msg = '正常'
# ** gpt request **
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, top_p, temperature, history=history) # 带超时倒计时
gpt_say = yield from predict_no_ui_but_counting_down(i_say, i_say, chatbot, llm_kwargs, plugin_kwargs, history=history) # 带超时倒计时
chatbot[-1] = (i_say, gpt_say)
history.append(i_say); history.append(gpt_say)
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg)
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) # 刷新界面
res = write_results_to_file(history)
chatbot.append(("完成了吗？", res))
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg)
yield from update_ui(chatbot=chatbot, history=chatbot, msg=msg) # 刷新界面
@CatchException
def 批量总结PDF文档pdfminer(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史，以免输入溢出
import glob, os
@@ -118,7 +118,7 @@ def 批量总结PDF文档pdfminer(txt, top_p, temperature, chatbot, history, sys
chatbot.append([
"函数插件功能？",
"批量总结PDF文档，此版本使用pdfminer插件，带token约简功能。函数插件贡献者: Euclid-Jie。"])
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 尝试导入依赖，如果缺少依赖，则给出安装建议
try:
@@ -127,14 +127,14 @@ def 批量总结PDF文档pdfminer(txt, top_p, temperature, chatbot, history, sys
report_execption(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 pdfminer beautifulsoup4```。")
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
if os.path.exists(txt):
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}")
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
[f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
@@ -142,7 +142,7 @@ def 批量总结PDF文档pdfminer(txt, top_p, temperature, chatbot, history, sys
# [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
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}")
yield from update_ui(chatbot=chatbot, history=history)
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)
yield from 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)