Spaces:
Sleeping
Sleeping
File size: 6,513 Bytes
e8cf757 ea031ab e8cf757 8ac9b45 fc33168 0b3f7b8 dcaa7a1 0666fec dcaa7a1 49a6ff6 0666fec dcaa7a1 0b3f7b8 dcaa7a1 079916f 0666fec dcaa7a1 0666fec dcaa7a1 0666fec dcaa7a1 0666fec dcaa7a1 0666fec dcaa7a1 85d85d8 e8cf757 dcaa7a1 fc33168 85d85d8 fc33168 85d85d8 dcaa7a1 e6cf553 2472185 dd648bd 0b3f7b8 85d85d8 fc33168 85d85d8 0b3f7b8 0666fec 85d85d8 fc33168 85d85d8 0b3f7b8 fc33168 0666fec 85d85d8 0b3f7b8 fc33168 b2fba01 85d85d8 fc33168 d32a52c e8cf757 fc33168 49a6ff6 0b3f7b8 929c0af 85d85d8 e8cf757 0b3f7b8 e8cf757 929c0af |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
from toolbox import CatchException, report_execption, write_results_to_file
from toolbox import update_ui
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
from .crazy_utils import read_and_clean_pdf_text
from colorful import *
@CatchException
def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt, web_port):
import glob
import os
# 基本信息:功能、贡献者
chatbot.append([
"函数插件功能?",
"批量总结PDF文档。函数插件贡献者: Binary-Husky"])
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:
import fitz
import tiktoken
except:
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 pymupdf tiktoken```。")
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
return
# 清空历史,以免输入溢出
history = []
# 检测输入参数,如没有给定输入参数,直接退出
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) # 刷新界面
return
# 搜索需要处理的文件清单
file_manifest = [f for f in glob.glob(
f'{project_folder}/**/*.pdf', recursive=True)]
# 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}")
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PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt)
def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
import os
import tiktoken
TOKEN_LIMIT_PER_FRAGMENT = 1600
generated_conclusion_files = []
for index, fp in enumerate(file_manifest):
# 读取PDF文件
file_content, page_one = read_and_clean_pdf_text(fp)
# 递归地切割PDF文件
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
from toolbox import get_conf
enc = tiktoken.encoding_for_model("gpt-3.5-turbo")
def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
txt=file_content, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
# 为了更好的效果,我们剥离Introduction之后的部分(如果有)
paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
# 单线,获取文章meta信息
paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
inputs=f"以下是一篇学术论文的基础信息,请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出,最后用中文翻译摘要部分。请提取:{paper_meta}",
inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
llm_kwargs=llm_kwargs,
chatbot=chatbot, history=[],
sys_prompt="Your job is to collect information from materials。",
)
# 多线,翻译
gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array=[
f"以下是你需要翻译的论文片段:\n{frag}" for frag in paper_fragments],
inputs_show_user_array=[f"\n---\n 原文: \n\n {frag.replace('#', '')} \n---\n 翻译:\n " for frag in paper_fragments],
llm_kwargs=llm_kwargs,
chatbot=chatbot,
history_array=[[paper_meta] for _ in paper_fragments],
sys_prompt_array=[
"请你作为一个学术翻译,负责把学术论文的片段准确翻译成中文。" for _ in paper_fragments],
# max_workers=5 # OpenAI所允许的最大并行过载
)
# 整理报告的格式
for i,k in enumerate(gpt_response_collection):
if i%2==0:
gpt_response_collection[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection)//2}]: \n\n {paper_fragments[i//2].replace('#', '')} \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection)//2}]:\n "
else:
gpt_response_collection[i] = gpt_response_collection[i]
final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
final.extend(gpt_response_collection)
create_report_file_name = f"{os.path.basename(fp)}.trans.md"
res = write_results_to_file(final, file_name=create_report_file_name)
# 更新UI
generated_conclusion_files.append(f'./gpt_log/{create_report_file_name}')
chatbot.append((f"{fp}完成了吗?", res))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
# 准备文件的下载
import shutil
for pdf_path in generated_conclusion_files:
# 重命名文件
rename_file = f'./gpt_log/总结论文-{os.path.basename(pdf_path)}'
if os.path.exists(rename_file):
os.remove(rename_file)
shutil.copyfile(pdf_path, rename_file)
if os.path.exists(pdf_path):
os.remove(pdf_path)
chatbot.append(("给出输出文件清单", str(generated_conclusion_files)))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|