mrhblfx commited on
Commit
20bec70
2 Parent(s): 9b5f088 faffc59

Merge branch 'master' of github.com:mrhblfx/chatgpt_academic

Browse files
README.md CHANGED
@@ -68,11 +68,13 @@ huggingface免科学上网[在线体验](https://huggingface.co/spaces/qingxu98/
68
  <img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
69
  </div>
70
 
71
- - 多种大语言模型混合调用([v3.1分支](https://github.com/binary-husky/chatgpt_academic/tree/v3.1)测试中)
72
  <div align="center">
73
- <img src="https://user-images.githubusercontent.com/96192199/231222778-34776885-a7f0-4f2c-b5f4-7cc2ef3ecb58.png" width="700" >
74
  </div>
75
 
 
 
76
 
77
 
78
  ## 直接运行 (Windows, Linux or MacOS)
 
68
  <img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
69
  </div>
70
 
71
+ - 多种大语言模型混合调用(ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4, [v3.1分支](https://github.com/binary-husky/chatgpt_academic/tree/v3.1)测试中)
72
  <div align="center">
73
+ <img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
74
  </div>
75
 
76
+ v3.1的[huggingface测试版](https://huggingface.co/spaces/qingxu98/academic-chatgpt-beta)(huggingface版不支持chatglm)
77
+
78
 
79
 
80
  ## 直接运行 (Windows, Linux or MacOS)
crazy_functions/crazy_utils.py CHANGED
@@ -444,6 +444,7 @@ def read_and_clean_pdf_text(fp):
444
  pf = 998
445
  for l in t['lines']:
446
  txt_line = "".join([wtf['text'] for wtf in l['spans']])
 
447
  pf = primary_ffsize(l)
448
  meta_line.append([txt_line, pf, l['bbox'], l])
449
  for wtf in l['spans']: # for l in t['lines']:
@@ -554,8 +555,8 @@ def read_and_clean_pdf_text(fp):
554
  meta_txt = meta_txt.replace('\n', '\n\n')
555
 
556
  ############################## <第 5 步,展示分割效果> ##################################
557
- for f in finals:
558
- print亮黄(f)
559
- print亮绿('***************************')
560
 
561
  return meta_txt, page_one_meta
 
444
  pf = 998
445
  for l in t['lines']:
446
  txt_line = "".join([wtf['text'] for wtf in l['spans']])
447
+ if len(txt_line) == 0: continue
448
  pf = primary_ffsize(l)
449
  meta_line.append([txt_line, pf, l['bbox'], l])
450
  for wtf in l['spans']: # for l in t['lines']:
 
555
  meta_txt = meta_txt.replace('\n', '\n\n')
556
 
557
  ############################## <第 5 步,展示分割效果> ##################################
558
+ # for f in finals:
559
+ # print亮黄(f)
560
+ # print亮绿('***************************')
561
 
562
  return meta_txt, page_one_meta
crazy_functions/批量翻译PDF文档_多线程.py CHANGED
@@ -13,7 +13,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
13
  # 基本信息:功能、贡献者
14
  chatbot.append([
15
  "函数插件功能?",
16
- "批量总结PDF文档。函数插件贡献者: Binary-Husky"])
17
  yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
18
 
19
  # 尝试导入依赖,如果缺少依赖,则给出安装建议
@@ -59,7 +59,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
59
  def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
60
  import os
61
  import tiktoken
62
- TOKEN_LIMIT_PER_FRAGMENT = 1600
63
  generated_conclusion_files = []
64
  for index, fp in enumerate(file_manifest):
65
 
@@ -91,13 +91,13 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
91
  # 多线,翻译
92
  gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
93
  inputs_array=[
94
- f"以下是你需要翻译的论文片段:\n{frag}" for frag in paper_fragments],
95
  inputs_show_user_array=[f"\n---\n 原文: \n\n {frag.replace('#', '')} \n---\n 翻译:\n " for frag in paper_fragments],
96
  llm_kwargs=llm_kwargs,
97
  chatbot=chatbot,
98
  history_array=[[paper_meta] for _ in paper_fragments],
99
  sys_prompt_array=[
100
- "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],
101
  # max_workers=5 # OpenAI所允许的最大并行过载
102
  )
103
 
 
13
  # 基本信息:功能、贡献者
14
  chatbot.append([
15
  "函数插件功能?",
16
+ "批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
17
  yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
18
 
19
  # 尝试导入依赖,如果缺少依赖,则给出安装建议
 
59
  def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
60
  import os
61
  import tiktoken
62
+ TOKEN_LIMIT_PER_FRAGMENT = 1280
63
  generated_conclusion_files = []
64
  for index, fp in enumerate(file_manifest):
65
 
 
91
  # 多线,翻译
92
  gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
93
  inputs_array=[
94
+ f"你需要翻译以下内容:\n{frag}" for frag in paper_fragments],
95
  inputs_show_user_array=[f"\n---\n 原文: \n\n {frag.replace('#', '')} \n---\n 翻译:\n " for frag in paper_fragments],
96
  llm_kwargs=llm_kwargs,
97
  chatbot=chatbot,
98
  history_array=[[paper_meta] for _ in paper_fragments],
99
  sys_prompt_array=[
100
+ "请你作为一个学术翻译,负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
101
  # max_workers=5 # OpenAI所允许的最大并行过载
102
  )
103
 
toolbox.py CHANGED
@@ -456,7 +456,7 @@ def on_file_uploaded(files, chatbot, txt):
456
  chatbot.append(['我上传了文件,请查收',
457
  f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
458
  f'\n\n调用路径参数已自动修正到: \n\n{txt}' +
459
- f'\n\n现在您点击任意实验功能时,以上文件将被作为输入参数'+err_msg])
460
  return chatbot, txt
461
 
462
 
 
456
  chatbot.append(['我上传了文件,请查收',
457
  f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
458
  f'\n\n调用路径参数已自动修正到: \n\n{txt}' +
459
+ f'\n\n现在您点击任意“红颜色”标识的函数插件时,以上文件将被作为输入参数'+err_msg])
460
  return chatbot, txt
461
 
462
 
version CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": 2.68,
3
  "show_feature": true,
4
- "new_feature": "改善理解pdf(chatpdf)功能 <-> 修复读取罕见字符的BUG <-> 如果一键更新失败,可前往github手动更新"
5
  }
 
1
  {
2
+ "version": 2.7,
3
  "show_feature": true,
4
+ "new_feature": "修复BUG <-> 改善理解pdf(chatpdf)功能 <-> 如果一键更新失败,可前往github手动更新"
5
  }