修复Latex矫错和本地Latex论文翻译的问题

This commit is contained in:
qingxu fu 2023-06-29 11:30:42 +08:00
parent d684b4cdb3
commit eb4c07997e
4 changed files with 41 additions and 27 deletions

View File

@ -348,11 +348,11 @@ def get_crazy_functions():
try:
from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
function_plugins.update({
"[功能尚不稳定] Latex英文纠错+LatexDiff高亮修正位置": {
"Latex英文纠错+高亮修正位置 [需Latex]": {
"Color": "stop",
"AsButton": False,
# "AdvancedArgs": True,
# "ArgsReminder": "",
"AdvancedArgs": True,
"ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令(使用英文)。",
"Function": HotReload(Latex英文纠错加PDF对比)
}
})
@ -368,17 +368,17 @@ def get_crazy_functions():
"Function": HotReload(Latex翻译中文并重新编译PDF)
}
})
# function_plugins.update({
# "本地论文翻译上传Latex压缩包 [需Latex]": {
# "Color": "stop",
# "AsButton": False,
# "AdvancedArgs": True,
# "ArgsReminder":
# "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+
# "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
# "Function": HotReload(Latex翻译中文并重新编译PDF)
# }
# })
function_plugins.update({
"本地论文翻译上传Latex压缩包[需Latex]": {
"Color": "stop",
"AsButton": False,
"AdvancedArgs": True,
"ArgsReminder":
"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+
"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
"Function": HotReload(Latex翻译中文并重新编译PDF)
}
})
except:
print('Load function plugin failed')

View File

@ -19,9 +19,9 @@ def switch_prompt(pfg, mode, more_requirement):
- sys_prompt_array: A list of strings containing prompts for system prompts.
"""
n_split = len(pfg.sp_file_contents)
if mode == 'proofread':
if mode == 'proofread_en':
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
r"Answer me only with the revised text:" +
f"\n\n{frag}" for frag in pfg.sp_file_contents]
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
@ -70,6 +70,12 @@ def move_project(project_folder, arxiv_id=None):
shutil.rmtree(new_workfolder)
except:
pass
# align subfolder if there is a folder wrapper
items = glob.glob(pj(project_folder,'*'))
if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
if os.path.isdir(items[0]): project_folder = items[0]
shutil.copytree(src=project_folder, dst=new_workfolder)
return new_workfolder
@ -142,6 +148,10 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
"对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4其他模型转化效果未知。目前对机器学习类文献转化效果最好其他类型文献转化效果未知。仅在Windows系统进行了测试其他操作系统表现未知。"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# <-------------- more requirements ------------->
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
more_req = plugin_kwargs.get("advanced_arg", "")
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
# <-------------- check deps ------------->
try:
@ -180,13 +190,13 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
if not os.path.exists(project_folder + '/merge_proofread.tex'):
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
chatbot, history, system_prompt, mode='proofread_latex', switch_prompt=switch_prompt)
chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
# <-------------- compile PDF ------------->
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread',
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en',
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
@ -195,6 +205,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
@ -278,6 +289,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
if success:
chatbot.append((f"成功啦", '请查收结果(压缩包)...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
else:
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果(压缩包), 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面

View File

@ -190,10 +190,10 @@ def test_Latex():
# txt = r"C:\Users\x\arxiv_cache\2211.16068\workfolder" # ACE
# txt = r"https://arxiv.org/abs/2002.09253"
# txt = r"https://arxiv.org/abs/2306.07831"
txt = r"https://arxiv.org/abs/2212.10156"
# txt = r"https://arxiv.org/abs/2212.10156"
# txt = r"https://arxiv.org/abs/2211.11559"
# txt = r"https://arxiv.org/abs/2303.08774"
# txt = r"https://arxiv.org/abs/2303.12712"
txt = r"https://arxiv.org/abs/2303.12712"
# txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"

View File

@ -430,7 +430,7 @@ class LatexPaperSplit():
"""
def __init__(self) -> None:
self.nodes = None
self.msg = "{\\scriptsize\\textbf{警告该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成" + \
self.msg = "*{\\scriptsize\\textbf{警告该PDF由GPT-Academic开源项目调用大语言模型+\Latex 翻译插件一键生成," + \
"版权归原文作者所有。翻译内容可靠性无保障,请仔细鉴别并以原文为准。" + \
"项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
# 请您不要删除或修改这行警告除非您是论文的原作者如果您是论文原作者欢迎加REAME中的QQ联系开发者
@ -741,13 +741,15 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
yield from update_ui_lastest_msg(f'{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
if diff_pdf_success:
result_pdf = pj(work_folder_modified, f'merge_diff.pdf') # get pdf path
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
if modified_pdf_success:
yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 即将退出 ...', chatbot, history) # 刷新Gradio前端界面
os.chdir(current_dir)
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
if os.path.exists(pj(work_folder, '..', 'translation')):
shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
return True # 成功啦
else:
if n_fix>=max_try: break