chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
mrhblfx 2023-04-18 23:40:51 +08:00
commit 20bec70160
5 changed files with 15 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -68,11 +68,13 @@ huggingface免科学上网[在线体验](https://huggingface.co/spaces/qingxu98/
<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" > <img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
</div> </div>
- 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） - 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）
<div align="center"> <div align="center">
<img src="https://user-images.githubusercontent.com/96192199/231222778-34776885-a7f0-4f2c-b5f4-7cc2ef3ecb58.png" width="700" > <img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
</div> </div>
v3.1的[huggingface测试版](https://huggingface.co/spaces/qingxu98/academic-chatgpt-beta)（huggingface版不支持chatglm）
## 直接运行 (Windows, Linux or MacOS) ## 直接运行 (Windows, Linux or MacOS)

7
crazy_functions/crazy_utils.py
View File

@ -444,6 +444,7 @@ def read_and_clean_pdf_text(fp):
pf = 998 pf = 998
for l in t['lines']: for l in t['lines']:
txt_line = "".join([wtf['text'] for wtf in l['spans']]) txt_line = "".join([wtf['text'] for wtf in l['spans']])
if len(txt_line) == 0: continue
pf = primary_ffsize(l) pf = primary_ffsize(l)
meta_line.append([txt_line, pf, l['bbox'], l]) meta_line.append([txt_line, pf, l['bbox'], l])
for wtf in l['spans']: # for l in t['lines']: for wtf in l['spans']: # for l in t['lines']:
@ -554,8 +555,8 @@ def read_and_clean_pdf_text(fp):
meta_txt = meta_txt.replace('\n', '\n\n') meta_txt = meta_txt.replace('\n', '\n\n')
############################## <第 5 步，展示分割效果> ################################## ############################## <第 5 步，展示分割效果> ##################################
for f in finals: # for f in finals:
print亮黄(f) # print亮黄(f)
print亮绿('***************************') # print亮绿('***************************')
return meta_txt, page_one_meta return meta_txt, page_one_meta

8
crazy_functions/批量翻译PDF文档_多线程.py
View File

@ -13,7 +13,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
# 基本信息：功能、贡献者 # 基本信息：功能、贡献者
chatbot.append([ chatbot.append([
"函数插件功能？", "函数插件功能？",
"批量总结PDF文档。函数插件贡献者: Binary-Husky"]) "批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 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 # 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_
def 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 os
import tiktoken import tiktoken
TOKEN_LIMIT_PER_FRAGMENT = 1600 TOKEN_LIMIT_PER_FRAGMENT = 1280
generated_conclusion_files = [] generated_conclusion_files = []
for index, fp in enumerate(file_manifest): for index, fp in enumerate(file_manifest):
@ -91,13 +91,13 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
# 多线，翻译 # 多线，翻译
gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency( gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
inputs_array=[ inputs_array=[
f"以下是你需要翻译的论文片段：\n{frag}" for frag in paper_fragments], f"你需要翻译以下内容：\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], 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, llm_kwargs=llm_kwargs,
chatbot=chatbot, chatbot=chatbot,
history_array=[[paper_meta] for _ in paper_fragments], history_array=[[paper_meta] for _ in paper_fragments],
sys_prompt_array=[ 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], "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],
# max_workers=5 # OpenAI所允许的最大并行过载 # max_workers=5 # OpenAI所允许的最大并行过载
) )

2
toolbox.py
View File

@ -456,7 +456,7 @@ def on_file_uploaded(files, chatbot, txt):
chatbot.append(['我上传了文件，请查收', chatbot.append(['我上传了文件，请查收',
f'[Local Message] 收到以下文件: \n\n{moved_files_str}' + f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
f'\n\n调用路径参数已自动修正到: \n\n{txt}' + f'\n\n调用路径参数已自动修正到: \n\n{txt}' +
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]) 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])
return chatbot, txt return chatbot, txt

4
version
View File

@ -1,5 +1,5 @@
{ {
"version": 2.68, "version": 2.7,
"show_feature": true, "show_feature": true,
"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" "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"
} }