镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-06 22:46:48 +00:00
Merge remote-tracking branch 'origin/boyin_summary'
这个提交包含在:
@@ -21,7 +21,7 @@ def get_crazy_functions():
|
||||
from crazy_functions.询问多个大语言模型 import 同时问询
|
||||
from crazy_functions.SourceCode_Analyse import 解析一个Lua项目
|
||||
from crazy_functions.SourceCode_Analyse import 解析一个CSharp项目
|
||||
from crazy_functions.总结word文档 import 总结word文档
|
||||
from crazy_functions.总结文档 import 总结文件
|
||||
from crazy_functions.解析JupyterNotebook import 解析ipynb文件
|
||||
from crazy_functions.Conversation_To_File import 载入对话历史存档
|
||||
from crazy_functions.Conversation_To_File import 对话历史存档
|
||||
@@ -110,12 +110,13 @@ def get_crazy_functions():
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后,Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||
},
|
||||
"批量总结Word文档": {
|
||||
"批量总结文档": {
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"Info": "批量总结word文档 | 输入参数为路径",
|
||||
"Function": HotReload(总结word文档),
|
||||
"Function": HotReload(总结文件),
|
||||
},
|
||||
"解析整个Matlab项目": {
|
||||
"Group": "编程",
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
import os
|
||||
from llama_index.core import SimpleDirectoryReader
|
||||
|
||||
supports_format = ['.csv', '.docx','.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
|
||||
'.pptm', '.pptx','.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml' ,'.m']
|
||||
|
||||
def read_docx_doc(file_path):
|
||||
if file_path.split(".")[-1] == "docx":
|
||||
from docx import Document
|
||||
doc = Document(file_path)
|
||||
file_content = "\n".join([para.text for para in doc.paragraphs])
|
||||
else:
|
||||
try:
|
||||
import win32com.client
|
||||
word = win32com.client.Dispatch("Word.Application")
|
||||
word.visible = False
|
||||
# 打开文件
|
||||
doc = word.Documents.Open(os.getcwd() + '/' + file_path)
|
||||
# file_content = doc.Content.Text
|
||||
doc = word.ActiveDocument
|
||||
file_content = doc.Range().Text
|
||||
doc.Close()
|
||||
word.Quit()
|
||||
except:
|
||||
raise RuntimeError('请先将.doc文档转换为.docx文档。')
|
||||
return file_content
|
||||
|
||||
# 修改后的 extract_text 函数,结合 SimpleDirectoryReader 和自定义解析逻辑
|
||||
import os
|
||||
|
||||
def extract_text(file_path):
|
||||
_, ext = os.path.splitext(file_path.lower())
|
||||
|
||||
# 使用 SimpleDirectoryReader 处理它支持的文件格式
|
||||
if ext in ['.docx', '.doc']:
|
||||
return read_docx_doc(file_path)
|
||||
try:
|
||||
reader = SimpleDirectoryReader(input_files=[file_path])
|
||||
documents = reader.load_data()
|
||||
if len(documents) > 0:
|
||||
return documents[0].text
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
return None
|
||||
@@ -2,34 +2,22 @@ from toolbox import update_ui
|
||||
from toolbox import CatchException, report_exception
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
|
||||
fast_debug = False
|
||||
|
||||
|
||||
def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
def 文档总结(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
import time, os
|
||||
from crazy_functions.rag_fns.rag_file_support import extract_text, supports_format
|
||||
# pip install python-docx 用于docx格式,跨平台
|
||||
# pip install pywin32 用于doc格式,仅支持Win平台
|
||||
for index, fp in enumerate(file_manifest):
|
||||
if fp.split(".")[-1] == "docx":
|
||||
from docx import Document
|
||||
doc = Document(fp)
|
||||
file_content = "\n".join([para.text for para in doc.paragraphs])
|
||||
else:
|
||||
try:
|
||||
import win32com.client
|
||||
word = win32com.client.Dispatch("Word.Application")
|
||||
word.visible = False
|
||||
# 打开文件
|
||||
doc = word.Documents.Open(os.getcwd() + '/' + fp)
|
||||
# file_content = doc.Content.Text
|
||||
doc = word.ActiveDocument
|
||||
file_content = doc.Range().Text
|
||||
doc.Close()
|
||||
word.Quit()
|
||||
except:
|
||||
raise RuntimeError('请先将.doc文档转换为.docx文档。')
|
||||
|
||||
file_content = extract_text(fp)
|
||||
# private_upload里面的文件名在解压zip后容易出现乱码(rar和7z格式正常),故可以只分析文章内容,不输入文件名
|
||||
if file_content==None:
|
||||
chatbot.append(
|
||||
[f"上传文件: {os.path.basename(fp)}", f"此文件解析失败,无法提取文本内容。失败原因可能为:1.文档格式过于复杂;2. 不支持的文件格式,支持的文件格式后缀有:" + ", ".join(supports_format)+ "等其他文本格式类型文件。"])
|
||||
continue
|
||||
from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
|
||||
from request_llms.bridge_all import model_info
|
||||
max_token = model_info[llm_kwargs['llm_model']]['max_token']
|
||||
@@ -37,8 +25,8 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
|
||||
this_paper_history = []
|
||||
for i, paper_frag in enumerate(paper_fragments):
|
||||
i_say = f'请对下面的文章片段用中文做概述,文件名是{os.path.relpath(fp, project_folder)},文章内容是 ```{paper_frag}```'
|
||||
i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
|
||||
i_say = f'请对下面的内容用中文做概述,文件名是{os.path.relpath(fp, project_folder)},做概述时请优先满足以下要求:{plugin_kwargs['advanced_arg']}:内容是 ```{paper_frag}```'
|
||||
i_say_show_user = f'请对下面的内容片段做概述,做概述时请优先满足以下要求:{plugin_kwargs['advanced_arg']}: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say_show_user,
|
||||
@@ -54,14 +42,14 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
|
||||
# 已经对该文章的所有片段总结完毕,如果文章被切分了,
|
||||
if len(paper_fragments) > 1:
|
||||
i_say = f"根据以上的对话,总结文章{os.path.abspath(fp)}的主要内容。"
|
||||
i_say = f"根据以上的对话,总结时请注意以下要求:{plugin_kwargs['advanced_arg']},总结文件{os.path.abspath(fp)}的主要内容。"
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say,
|
||||
inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history=this_paper_history,
|
||||
sys_prompt="总结文章。"
|
||||
sys_prompt="总结文件内容。"
|
||||
)
|
||||
|
||||
history.extend([i_say,gpt_say])
|
||||
@@ -69,35 +57,24 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
|
||||
|
||||
res = write_history_to_file(history)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot.append(("完成了吗?", res))
|
||||
chatbot.append((f"路径{fp}文件解读完成了吗?", "解读完成,存储路径为"+res))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
res = write_history_to_file(history)
|
||||
promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot.append(("所有文件都总结完成了吗?", res))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
@CatchException
|
||||
def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
def 总结文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
import glob, os
|
||||
|
||||
# 基本信息:功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能?",
|
||||
"批量总结Word文档。函数插件贡献者: JasonGuo1。注意, 如果是.doc文件, 请先转化为.docx格式。"])
|
||||
f"批量总结各类文件。函数插件贡献者: JasonGuo1 and BoyinLiu。支持的文件类型包括:{', '.join(supports_format)}。"
|
||||
])
|
||||
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:
|
||||
from docx import Document
|
||||
except:
|
||||
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 python-docx pywin32```。")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 清空历史,以免输入溢出
|
||||
history = []
|
||||
|
||||
@@ -111,17 +88,14 @@ def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pr
|
||||
return
|
||||
|
||||
# 搜索需要处理的文件清单
|
||||
if txt.endswith('.docx') or txt.endswith('.doc'):
|
||||
file_manifest = [txt]
|
||||
else:
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.docx', recursive=True)] + \
|
||||
[f for f in glob.glob(f'{project_folder}/**/*.doc', recursive=True)]
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**', recursive=True) if os.path.isfile(f)]
|
||||
|
||||
# 如果没找到任何文件
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.docx或doc文件: {txt}")
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何支持的文件类型: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始正式执行任务
|
||||
yield from 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
yield from 文档总结(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
在新工单中引用
屏蔽一个用户