update
This commit is contained in:
kaixindelele
13
README.md
13
README.md
@ -91,7 +91,7 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
|
||||
|
||||
1. 下载项目
|
||||
```sh
|
||||
git clone https://github.com/binary-husky/.git
|
||||
git clone https://github.com/binary-husky/gpt_academic.git
|
||||
cd gpt_academic
|
||||
```
|
||||
|
||||
@ -186,16 +186,19 @@ docker-compose up
|
||||
2. 使用docker-compose运行。
|
||||
请阅读docker-compose.yml后，按照其中的提示操作即可
|
||||
|
||||
3. 如何使用反代URL/微软云AzureAPI。
|
||||
3. 如何使用反代URL
|
||||
按照`config.py`中的说明配置API_URL_REDIRECT即可。
|
||||
|
||||
4. 远程云服务器部署（需要云服务器知识与经验）。
|
||||
4. 微软云AzureAPI
|
||||
按照`config.py`中的说明配置即可（AZURE_ENDPOINT等四个配置）
|
||||
|
||||
5. 远程云服务器部署（需要云服务器知识与经验）。
|
||||
请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
|
||||
|
||||
5. 使用WSL2（Windows Subsystem for Linux 子系统）。
|
||||
6. 使用WSL2（Windows Subsystem for Linux 子系统）。
|
||||
请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
|
||||
|
||||
6. 如何在二级网址（如`http://localhost/subpath`）下运行。
|
||||
7. 如何在二级网址（如`http://localhost/subpath`）下运行。
|
||||
请访问[FastAPI运行说明](docs/WithFastapi.md)
|
||||
|
||||
---
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
# [step 1]>> 例如： API_KEY = "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" （此key无效）
|
||||
API_KEY = "sk-此处填API密钥" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
|
||||
|
||||
|
||||
# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改
|
||||
USE_PROXY = False
|
||||
if USE_PROXY:
|
||||
@ -81,3 +82,10 @@ your bing cookies here
|
||||
# 如果需要使用Slack Claude，使用教程详情见 request_llm/README.md
|
||||
SLACK_CLAUDE_BOT_ID = ''
|
||||
SLACK_CLAUDE_USER_TOKEN = ''
|
||||
|
||||
|
||||
# 如果需要使用AZURE 详情请见额外文档 docs\use_azure.md
|
||||
AZURE_ENDPOINT = "https://你的api名称.openai.azure.com/"
|
||||
AZURE_API_KEY = "填入azure openai api的密钥"
|
||||
AZURE_API_VERSION = "填入api版本"
|
||||
AZURE_ENGINE = "填入ENGINE"
|
||||
|
||||
@ -40,57 +40,57 @@ def get_crazy_functions():
|
||||
"AsButton":False,
|
||||
"Function": HotReload(删除所有本地对话历史记录)
|
||||
},
|
||||
# "[测试功能] 解析Jupyter Notebook文件": {
|
||||
# "Color": "stop",
|
||||
# "AsButton":False,
|
||||
# "Function": HotReload(解析ipynb文件),
|
||||
# "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
# "ArgsReminder": "若输入0，则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
|
||||
# },
|
||||
"[测试功能] 解析Jupyter Notebook文件": {
|
||||
"Color": "stop",
|
||||
"AsButton":False,
|
||||
"Function": HotReload(解析ipynb文件),
|
||||
"AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
"ArgsReminder": "若输入0，则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
|
||||
},
|
||||
"批量总结Word文档": {
|
||||
"Color": "stop",
|
||||
"Function": HotReload(总结word文档)
|
||||
},
|
||||
# "解析整个C++项目头文件": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个C项目的头文件)
|
||||
# },
|
||||
# "解析整个C++项目（.cpp/.hpp/.c/.h）": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个C项目)
|
||||
# },
|
||||
# "解析整个Go项目": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个Golang项目)
|
||||
# },
|
||||
# "解析整个Rust项目": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个Rust项目)
|
||||
# },
|
||||
# "解析整个Java项目": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个Java项目)
|
||||
# },
|
||||
# "解析整个前端项目（js,ts,css等）": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个前端项目)
|
||||
# },
|
||||
# "解析整个Lua项目": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个Lua项目)
|
||||
# },
|
||||
# "解析整个CSharp项目": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析一个CSharp项目)
|
||||
# },
|
||||
"解析整个C++项目头文件": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个C项目的头文件)
|
||||
},
|
||||
"解析整个C++项目（.cpp/.hpp/.c/.h）": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个C项目)
|
||||
},
|
||||
"解析整个Go项目": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个Golang项目)
|
||||
},
|
||||
"解析整个Rust项目": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个Rust项目)
|
||||
},
|
||||
"解析整个Java项目": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个Java项目)
|
||||
},
|
||||
"解析整个前端项目（js,ts,css等）": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个前端项目)
|
||||
},
|
||||
"解析整个Lua项目": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个Lua项目)
|
||||
},
|
||||
"解析整个CSharp项目": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析一个CSharp项目)
|
||||
},
|
||||
"读Tex论文写摘要": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"Function": HotReload(读文章写摘要)
|
||||
@ -108,19 +108,19 @@ def get_crazy_functions():
|
||||
"保存当前的对话": {
|
||||
"Function": HotReload(对话历史存档)
|
||||
},
|
||||
# "[多线程Demo] 解析此项目本身（源码自译解）": {
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(解析项目本身)
|
||||
# },
|
||||
"[多线程Demo] 解析此项目本身（源码自译解）": {
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析项目本身)
|
||||
},
|
||||
# "[老旧的Demo] 把本项目源代码切换成全英文": {
|
||||
# # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Function": HotReload(全项目切换英文)
|
||||
# },
|
||||
# "[插件demo] 历史上的今天": {
|
||||
# # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
|
||||
# "Function": HotReload(高阶功能模板函数)
|
||||
# },
|
||||
"[插件demo] 历史上的今天": {
|
||||
# HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
|
||||
"Function": HotReload(高阶功能模板函数)
|
||||
},
|
||||
|
||||
}
|
||||
###################### 第二组插件 ###########################
|
||||
@ -135,35 +135,17 @@ def get_crazy_functions():
|
||||
from crazy_functions.Latex全文翻译 import Latex中译英
|
||||
from crazy_functions.Latex全文翻译 import Latex英译中
|
||||
from crazy_functions.批量Markdown翻译 import Markdown中译英
|
||||
# from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
|
||||
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
|
||||
|
||||
function_plugins.update({
|
||||
"翻译任意PDF文档2MD": {
|
||||
"批量翻译PDF文档（多线程）": {
|
||||
"Color": "stop",
|
||||
"AsButton": True, # 加入下拉菜单中
|
||||
"Function": HotReload(批量翻译PDF文档)
|
||||
},
|
||||
# "[功能尚不稳定] Latex英文纠错+LatexDiff高亮修正位置": {
|
||||
# "Color": "stop",
|
||||
# "AsButton": True,
|
||||
# # "AdvancedArgs": True,
|
||||
# # "ArgsReminder": "",
|
||||
# "Function": HotReload(Latex英文纠错加PDF对比)
|
||||
# },
|
||||
"[功能尚不稳定] Latex翻译/Arixv翻译+重构PDF": {
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
# "AdvancedArgs": True,
|
||||
# "ArgsReminder": "",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF)
|
||||
"询问多个GPT模型": {
|
||||
"Color": "stop", # 按钮颜色
|
||||
"Function": HotReload(同时问询)
|
||||
},
|
||||
|
||||
|
||||
# "询问多个GPT模型": {
|
||||
# "Color": "stop", # 按钮颜色
|
||||
# "Function": HotReload(同时问询)
|
||||
# },
|
||||
"[测试功能] 批量总结PDF文档": {
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
@ -253,33 +235,33 @@ def get_crazy_functions():
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
# try:
|
||||
# from crazy_functions.解析项目源代码 import 解析任意code项目
|
||||
# function_plugins.update({
|
||||
# "解析项目源代码（手动指定和筛选源代码文件类型）": {
|
||||
# "Color": "stop",
|
||||
# "AsButton": False,
|
||||
# "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
# "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
|
||||
# "Function": HotReload(解析任意code项目)
|
||||
# },
|
||||
# })
|
||||
# except:
|
||||
# print('Load function plugin failed')
|
||||
try:
|
||||
from crazy_functions.解析项目源代码 import 解析任意code项目
|
||||
function_plugins.update({
|
||||
"解析项目源代码（手动指定和筛选源代码文件类型）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
"ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
|
||||
"Function": HotReload(解析任意code项目)
|
||||
},
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
# try:
|
||||
# from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
|
||||
# function_plugins.update({
|
||||
# "询问多个GPT模型（手动指定询问哪些模型）": {
|
||||
# "Color": "stop",
|
||||
# "AsButton": False,
|
||||
# "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
# "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
|
||||
# "Function": HotReload(同时问询_指定模型)
|
||||
# },
|
||||
# })
|
||||
# except:
|
||||
# print('Load function plugin failed')
|
||||
try:
|
||||
from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
|
||||
function_plugins.update({
|
||||
"询问多个GPT模型（手动指定询问哪些模型）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
|
||||
"ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
|
||||
"Function": HotReload(同时问询_指定模型)
|
||||
},
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.图片生成 import 图片生成
|
||||
@ -364,17 +346,54 @@ def get_crazy_functions():
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.虚空终端 import 终端
|
||||
from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
|
||||
function_plugins.update({
|
||||
"超级终端": {
|
||||
"[功能尚不稳定] Latex英文纠错+LatexDiff高亮修正位置": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
# "AdvancedArgs": True,
|
||||
# "ArgsReminder": "",
|
||||
"Function": HotReload(终端)
|
||||
"Function": HotReload(Latex英文纠错加PDF对比)
|
||||
}
|
||||
})
|
||||
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
|
||||
function_plugins.update({
|
||||
"Arixv翻译（输入arxivID） [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')
|
||||
|
||||
# try:
|
||||
# from crazy_functions.虚空终端 import 终端
|
||||
# function_plugins.update({
|
||||
# "超级终端": {
|
||||
# "Color": "stop",
|
||||
# "AsButton": False,
|
||||
# # "AdvancedArgs": True,
|
||||
# # "ArgsReminder": "",
|
||||
# "Function": HotReload(终端)
|
||||
# }
|
||||
# })
|
||||
# except:
|
||||
# print('Load function plugin failed')
|
||||
|
||||
return function_plugins
|
||||
|
||||
@ -1,13 +1,13 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, objdump, objload, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_execption, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time
|
||||
pj = os.path.join
|
||||
# ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
# ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
ARXIV_CACHE_DIR = os.getenv("Arxiv_Cache")
|
||||
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
|
||||
# =================================== 工具函数 ===============================================
|
||||
专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode):
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
@ -26,7 +26,7 @@ def switch_prompt(pfg, mode):
|
||||
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)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + 专业词汇声明 +
|
||||
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
@ -80,7 +80,7 @@ def arxiv_download(chatbot, history, txt):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file)
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
def is_float(s):
|
||||
@ -89,8 +89,10 @@ def arxiv_download(chatbot, history, txt):
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt):
|
||||
txt = 'https://arxiv.org/abs/' + txt
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None
|
||||
|
||||
@ -106,6 +108,7 @@ def arxiv_download(chatbot, history, txt):
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf: return cached_translation_pdf, arxiv_id
|
||||
|
||||
@ -178,7 +181,8 @@ 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'):
|
||||
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)
|
||||
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)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
@ -187,13 +191,14 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_result(project_folder)
|
||||
zip_res = zip_result(project_folder)
|
||||
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
|
||||
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
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
@ -209,6 +214,10 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。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。"])
|
||||
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:
|
||||
@ -256,21 +265,23 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='translate_zh', switch_prompt=switch_prompt)
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh',
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_result(project_folder)
|
||||
zip_res = zip_result(project_folder)
|
||||
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
|
||||
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
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
|
||||
@ -189,6 +189,7 @@ def test_Latex():
|
||||
# txt = r"https://arxiv.org/abs/2211.16068" # ACE
|
||||
# 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"
|
||||
for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
cli_printer.print(cb) # print(cb)
|
||||
|
||||
@ -217,6 +218,7 @@ def test_Latex():
|
||||
# test_数学动画生成manim()
|
||||
# test_Langchain知识库()
|
||||
# test_Langchain知识库读取()
|
||||
test_Latex()
|
||||
input("程序完成，回车退出。")
|
||||
print("退出。")
|
||||
if __name__ == "__main__":
|
||||
test_Latex()
|
||||
input("程序完成，回车退出。")
|
||||
print("退出。")
|
||||
@ -698,3 +698,51 @@ def try_install_deps(deps):
|
||||
for dep in deps:
|
||||
import subprocess, sys
|
||||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '--user', dep])
|
||||
|
||||
|
||||
class construct_html():
|
||||
def __init__(self) -> None:
|
||||
self.css = """
|
||||
.row {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.column {
|
||||
flex: 1;
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.table-header {
|
||||
font-weight: bold;
|
||||
border-bottom: 1px solid black;
|
||||
}
|
||||
|
||||
.table-row {
|
||||
border-bottom: 1px solid lightgray;
|
||||
}
|
||||
|
||||
.table-cell {
|
||||
padding: 5px;
|
||||
}
|
||||
"""
|
||||
self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
|
||||
|
||||
|
||||
def add_row(self, a, b):
|
||||
tmp = """
|
||||
<div class="row table-row">
|
||||
<div class="column table-cell">REPLACE_A</div>
|
||||
<div class="column table-cell">REPLACE_B</div>
|
||||
</div>
|
||||
"""
|
||||
from toolbox import markdown_convertion
|
||||
tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
|
||||
tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
|
||||
self.html_string += tmp
|
||||
|
||||
|
||||
def save_file(self, file_name):
|
||||
with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
|
||||
f.write(self.html_string.encode('utf-8', 'ignore').decode())
|
||||
|
||||
|
||||
@ -175,9 +175,8 @@ def merge_tex_files(project_foler, main_file, mode):
|
||||
main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
|
||||
# fontset=windows
|
||||
import platform
|
||||
if platform.system() != 'Windows':
|
||||
main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows]{\2}",main_file)
|
||||
main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows]{\1}",main_file)
|
||||
main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
|
||||
main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
|
||||
# find paper abstract
|
||||
pattern = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
match = pattern.search(main_file)
|
||||
@ -213,6 +212,8 @@ def fix_content(final_tex, node_string):
|
||||
final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
|
||||
final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
|
||||
|
||||
if "Traceback" in final_tex and "[Local Message]" in final_tex:
|
||||
final_tex = node_string # 出问题了，还原原文
|
||||
if node_string.count('\\begin') != final_tex.count('\\begin'):
|
||||
final_tex = node_string # 出问题了，还原原文
|
||||
if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
|
||||
@ -404,7 +405,7 @@ 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，" + \
|
||||
"版权归原文作者所有。翻译内容可靠性无任何保障，请仔细鉴别并以原文为准。" + \
|
||||
"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）
|
||||
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
|
||||
@ -498,7 +499,32 @@ class LatexPaperFileGroup():
|
||||
f.write(res)
|
||||
return manifest
|
||||
|
||||
def write_html(sp_file_contents, sp_file_result, chatbot):
|
||||
|
||||
# write html
|
||||
try:
|
||||
import copy
|
||||
from .crazy_utils import construct_html
|
||||
from toolbox import gen_time_str
|
||||
ch = construct_html()
|
||||
orig = ""
|
||||
trans = ""
|
||||
final = []
|
||||
for c,r in zip(sp_file_contents, sp_file_result):
|
||||
final.append(c)
|
||||
final.append(r)
|
||||
for i, k in enumerate(final):
|
||||
if i%2==0:
|
||||
orig = k
|
||||
if i%2==1:
|
||||
trans = k
|
||||
ch.add_row(a=orig, b=trans)
|
||||
create_report_file_name = f"{gen_time_str()}.trans.html"
|
||||
ch.save_file(create_report_file_name)
|
||||
promote_file_to_downloadzone(file=f'./gpt_log/{create_report_file_name}', chatbot=chatbot)
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
print('writing html result failed:', trimmed_format_exc())
|
||||
|
||||
def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
|
||||
import time, os, re
|
||||
@ -575,6 +601,7 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
pfg.get_token_num = None
|
||||
objdump(pfg, file=pj(project_folder,'temp.pkl'))
|
||||
|
||||
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot)
|
||||
|
||||
# <-------- 写出文件 ---------->
|
||||
msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
|
||||
@ -624,7 +651,7 @@ def compile_latex_with_timeout(command, timeout=60):
|
||||
return False
|
||||
return True
|
||||
|
||||
def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder):
|
||||
def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
|
||||
import os, time
|
||||
current_dir = os.getcwd()
|
||||
n_fix = 1
|
||||
@ -635,6 +662,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
|
||||
while True:
|
||||
import os
|
||||
|
||||
# https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
|
||||
@ -656,6 +684,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
|
||||
|
||||
if mode!='translate_zh':
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
print( f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
|
||||
ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
|
||||
@ -685,9 +714,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
|
||||
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, chatbot=chatbot)
|
||||
# 我重新指定了参数传入。
|
||||
# promote_file_to_downloadzone(file=result_pdf, rename_file=None, chatbot=chatbot)
|
||||
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)
|
||||
return True # 成功啦
|
||||
else:
|
||||
if n_fix>=max_try: break
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from toolbox import CatchException, update_ui, promote_file_to_downloadzone
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
import re
|
||||
|
||||
@ -29,9 +29,8 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
|
||||
for h in history:
|
||||
f.write("\n>>>" + h)
|
||||
f.write('</code>')
|
||||
res = '对话历史写入：' + os.path.abspath(f'./gpt_log/{file_name}')
|
||||
print(res)
|
||||
return res
|
||||
promote_file_to_downloadzone(f'./gpt_log/{file_name}', rename_file=file_name, chatbot=chatbot)
|
||||
return '对话历史写入：' + os.path.abspath(f'./gpt_log/{file_name}')
|
||||
|
||||
def gen_file_preview(file_name):
|
||||
try:
|
||||
|
||||
25
docs/GithubAction+NoLocal+Latex
Normal file
25
docs/GithubAction+NoLocal+Latex
Normal file
@ -0,0 +1,25 @@
|
||||
# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
|
||||
# - 1 修改 `config.py`
|
||||
# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/Dockerfile+NoLocal+Latex .
|
||||
# - 3 运行 docker run -v /home/fuqingxu/arxiv_cache:/root/arxiv_cache --rm -it --net=host gpt-academic-nolocal-latex
|
||||
|
||||
FROM fuqingxu/python311_texlive_ctex:latest
|
||||
|
||||
# 指定路径
|
||||
WORKDIR /gpt
|
||||
|
||||
RUN pip3 install gradio openai numpy arxiv rich
|
||||
RUN pip3 install colorama Markdown pygments pymupdf
|
||||
|
||||
# 装载项目文件
|
||||
COPY . .
|
||||
|
||||
|
||||
# 安装依赖
|
||||
RUN pip3 install -r requirements.txt
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
# 启动
|
||||
CMD ["python3", "-u", "main.py"]
|
||||
143
docs/use_azure.md
Normal file
143
docs/use_azure.md
Normal file
@ -0,0 +1,143 @@
|
||||
# 通过微软Azure云服务申请 Openai API
|
||||
|
||||
由于Openai和微软的关系，现在是可以通过微软的Azure云计算服务直接访问openai的api，免去了注册和网络的问题。
|
||||
|
||||
快速入门的官方文档的链接是：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
|
||||
|
||||
# 申请API
|
||||
|
||||
按文档中的“先决条件”的介绍，出了编程的环境以外，还需要以下三个条件：
|
||||
|
||||
1. Azure账号并创建订阅
|
||||
|
||||
2. 为订阅添加Azure OpenAI 服务
|
||||
|
||||
3. 部署模型
|
||||
|
||||
## Azure账号并创建订阅
|
||||
|
||||
### Azure账号
|
||||
|
||||
创建Azure的账号时最好是有微软的账号，这样似乎更容易获得免费额度（第一个月的200美元，实测了一下，如果用一个刚注册的微软账号登录Azure的话，并没有这一个月的免费额度）。
|
||||
|
||||
创建Azure账号的网址是：[立即创建 Azure 免费帐户 | Microsoft Azure](https://azure.microsoft.com/zh-cn/free/)
|
||||
|
||||
|
||||
|
||||
打开网页后，点击 “免费开始使用” 会跳转到登录或注册页面，如果有微软的账户，直接登录即可，如果没有微软账户，那就需要到微软的网页再另行注册一个。
|
||||
|
||||
注意，Azure的页面和政策时不时会变化，已实际最新显示的为准就好。
|
||||
|
||||
### 创建订阅
|
||||
|
||||
注册好Azure后便可进入主页：
|
||||
|
||||
|
||||
|
||||
首先需要在订阅里进行添加操作，点开后即可进入订阅的页面：
|
||||
|
||||
|
||||
|
||||
第一次进来应该是空的，点添加即可创建新的订阅（可以是“免费”或者“即付即用”的订阅），其中订阅ID是后面申请Azure OpenAI需要使用的。
|
||||
|
||||
## 为订阅添加Azure OpenAI服务
|
||||
|
||||
之后回到首页，点Azure OpenAI即可进入OpenAI服务的页面（如果不显示的话，则在首页上方的搜索栏里搜索“openai”即可）。
|
||||
|
||||
|
||||
|
||||
不过现在这个服务还不能用。在使用前，还需要在这个网址申请一下：
|
||||
|
||||
[Request Access to Azure OpenAI Service (microsoft.com)](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOFA5Qk1UWDRBMjg0WFhPMkIzTzhKQ1dWNyQlQCN0PWcu)
|
||||
|
||||
这里有二十来个问题，按照要求和自己的实际情况填写即可。
|
||||
|
||||
其中需要注意的是
|
||||
|
||||
1. 千万记得填对"订阅ID"
|
||||
|
||||
2. 需要填一个公司邮箱（可以不是注册用的邮箱）和公司网址
|
||||
|
||||
之后，在回到上面那个页面，点创建，就会进入创建页面了：
|
||||
|
||||
|
||||
|
||||
需要填入“资源组”和“名称”，按照自己的需要填入即可。
|
||||
|
||||
完成后，在主页的“资源”里就可以看到刚才创建的“资源”了，点击进入后，就可以进行最后的部署了。
|
||||
|
||||
|
||||
|
||||
## 部署模型
|
||||
|
||||
进入资源页面后，在部署模型前，可以先点击“开发”，把密钥和终结点记下来。
|
||||
|
||||
|
||||
|
||||
之后，就可以去部署模型了，点击“部署”即可，会跳转到 Azure OpenAI Stuido 进行下面的操作：
|
||||
|
||||
|
||||
|
||||
进入 Azure OpenAi Studio 后，点击新建部署，会弹出如下对话框：
|
||||
|
||||
|
||||
|
||||
在这里选 gpt-35-turbo 或需要的模型并按需要填入“部署名”即可完成模型的部署。
|
||||
|
||||
|
||||
|
||||
这个部署名需要记下来。
|
||||
|
||||
到现在为止，申请操作就完成了，需要记下来的有下面几个东西：
|
||||
|
||||
● 密钥（1或2都可以）
|
||||
|
||||
● 终结点
|
||||
|
||||
● 部署名（不是模型名）
|
||||
|
||||
# API的使用
|
||||
|
||||
接下来就是具体怎么使用API了，还是可以参考官方文档：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
|
||||
|
||||
和openai自己的api调用有点类似，都需要安装openai库，不同的是调用方式
|
||||
|
||||
```
|
||||
import openai
|
||||
openai.api_type = "azure" #固定格式，无需修改
|
||||
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") #这里填入“终结点”
|
||||
openai.api_version = "2023-05-15" #固定格式，无需修改
|
||||
openai.api_key = os.getenv("AZURE_OPENAI_KEY") #这里填入“密钥1”或“密钥2”
|
||||
|
||||
response = openai.ChatCompletion.create(
|
||||
engine="gpt-35-turbo", #这里填入的不是模型名，是部署名
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
|
||||
{"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
|
||||
{"role": "user", "content": "Do other Azure Cognitive Services support this too?"}
|
||||
]
|
||||
)
|
||||
|
||||
print(response)
|
||||
print(response['choices'][0]['message']['content'])
|
||||
|
||||
```
|
||||
|
||||
需要注意的是：
|
||||
|
||||
1. engine那里填入的是部署名，不是模型名
|
||||
|
||||
2. 通过openai库获得的这个 response 和通过 request 库访问 url 获得的 response 不同，不需要 decode，已经是解析好的 json 了，直接根据键值读取即可。
|
||||
|
||||
更细节的使用方法，详见官方API文档。
|
||||
|
||||
# 关于费用
|
||||
|
||||
Azure OpenAI API 还是需要一些费用的（免费订阅只有1个月有效期），费用如下：
|
||||
|
||||
|
||||
|
||||
具体可以可以看这个网址 ：[Azure OpenAI 服务 - 定价| Microsoft Azure](https://azure.microsoft.com/zh-cn/pricing/details/cognitive-services/openai-service/?cdn=disable)
|
||||
|
||||
并非网上说的什么“一年白嫖”，但注册方法以及网络问题都比直接使用openai的api要简单一些。
|
||||
@ -16,6 +16,9 @@ from toolbox import get_conf, trimmed_format_exc
|
||||
from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
|
||||
from .bridge_chatgpt import predict as chatgpt_ui
|
||||
|
||||
from .bridge_azure_test import predict_no_ui_long_connection as azure_noui
|
||||
from .bridge_azure_test import predict as azure_ui
|
||||
|
||||
from .bridge_chatglm import predict_no_ui_long_connection as chatglm_noui
|
||||
from .bridge_chatglm import predict as chatglm_ui
|
||||
|
||||
@ -102,6 +105,16 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
# azure openai
|
||||
"azure-gpt35":{
|
||||
"fn_with_ui": azure_ui,
|
||||
"fn_without_ui": azure_noui,
|
||||
"endpoint": get_conf("AZURE_ENDPOINT"),
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
# api_2d
|
||||
"api2d-gpt-3.5-turbo": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
|
||||
241
request_llm/bridge_azure_test.py
Normal file
241
request_llm/bridge_azure_test.py
Normal file
@ -0,0 +1,241 @@
|
||||
"""
|
||||
该文件中主要包含三个函数
|
||||
|
||||
不具备多线程能力的函数：
|
||||
1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
|
||||
|
||||
具备多线程调用能力的函数
|
||||
2. predict_no_ui：高级实验性功能模块调用，不会实时显示在界面上，参数简单，可以多线程并行，方便实现复杂的功能逻辑
|
||||
3. predict_no_ui_long_connection：在实验过程中发现调用predict_no_ui处理长文档时，和openai的连接容易断掉，这个函数用stream的方式解决这个问题，同样支持多线程
|
||||
"""
|
||||
|
||||
import logging
|
||||
import traceback
|
||||
import importlib
|
||||
import openai
|
||||
import time
|
||||
|
||||
|
||||
# 读取config.py文件中关于AZURE OPENAI API的信息
|
||||
from toolbox import get_conf, update_ui, clip_history, trimmed_format_exc
|
||||
TIMEOUT_SECONDS, MAX_RETRY, AZURE_ENGINE, AZURE_ENDPOINT, AZURE_API_VERSION, AZURE_API_KEY = \
|
||||
get_conf('TIMEOUT_SECONDS', 'MAX_RETRY',"AZURE_ENGINE","AZURE_ENDPOINT", "AZURE_API_VERSION", "AZURE_API_KEY")
|
||||
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
获取完整的从Openai返回的报错
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
chunk += next(stream_response)
|
||||
except:
|
||||
break
|
||||
return chunk
|
||||
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
发送至azure openai api，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
print(llm_kwargs["llm_model"])
|
||||
|
||||
if additional_fn is not None:
|
||||
import core_functional
|
||||
importlib.reload(core_functional) # 热更新prompt
|
||||
core_functional = core_functional.get_core_functions()
|
||||
if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs) # 获取预处理函数（如果有的话）
|
||||
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
|
||||
|
||||
raw_input = inputs
|
||||
logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
|
||||
payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
|
||||
openai.api_type = "azure"
|
||||
openai.api_version = AZURE_API_VERSION
|
||||
openai.api_base = AZURE_ENDPOINT
|
||||
openai.api_key = AZURE_API_KEY
|
||||
response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
|
||||
|
||||
except:
|
||||
retry += 1
|
||||
chatbot[-1] = ((chatbot[-1][0], "获取response失败，重试中。。。"))
|
||||
retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
is_head_of_the_stream = True
|
||||
if stream:
|
||||
|
||||
stream_response = response
|
||||
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
|
||||
except StopIteration:
|
||||
from toolbox import regular_txt_to_markdown; tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 远程返回错误: \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk)}")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk) # 刷新界面
|
||||
return
|
||||
|
||||
if is_head_of_the_stream and (r'"object":"error"' not in chunk):
|
||||
# 数据流的第一帧不携带content
|
||||
is_head_of_the_stream = False; continue
|
||||
|
||||
if chunk:
|
||||
#print(chunk)
|
||||
try:
|
||||
if "delta" in chunk["choices"][0]:
|
||||
if chunk["choices"][0]["finish_reason"] == "stop":
|
||||
logging.info(f'[response] {gpt_replying_buffer}')
|
||||
break
|
||||
status_text = f"finish_reason: {chunk['choices'][0]['finish_reason']}"
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunk["choices"][0]["delta"]["content"]
|
||||
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
||||
|
||||
except Exception as e:
|
||||
traceback.print_exc()
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
|
||||
error_msg = chunk
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至AZURE OPENAI API，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
系统静默prompt
|
||||
llm_kwargs：
|
||||
chatGPT的内部调优参数
|
||||
history：
|
||||
是之前的对话列表
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
|
||||
retry = 0
|
||||
while True:
|
||||
|
||||
try:
|
||||
openai.api_type = "azure"
|
||||
openai.api_version = AZURE_API_VERSION
|
||||
openai.api_base = AZURE_ENDPOINT
|
||||
openai.api_key = AZURE_API_KEY
|
||||
response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
|
||||
|
||||
except:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
|
||||
stream_response = response
|
||||
result = ''
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
|
||||
if len(chunk)==0: continue
|
||||
if not chunk.startswith('data:'):
|
||||
error_msg = get_full_error(chunk, stream_response)
|
||||
if "reduce the length" in error_msg:
|
||||
raise ConnectionAbortedError("AZURE OPENAI API拒绝了请求:" + error_msg)
|
||||
else:
|
||||
raise RuntimeError("AZURE OPENAI API拒绝了请求：" + error_msg)
|
||||
if ('data: [DONE]' in chunk): break
|
||||
|
||||
delta = chunk["delta"]
|
||||
if len(delta) == 0: break
|
||||
if "role" in delta: continue
|
||||
if "content" in delta:
|
||||
result += delta["content"]
|
||||
if not console_slience: print(delta["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1: observe_window[0] += delta["content"]
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
else: raise RuntimeError("意外Json结构："+delta)
|
||||
if chunk['finish_reason'] == 'length':
|
||||
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
||||
return result
|
||||
|
||||
|
||||
def generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成 azure openai api请求，为发送请求做准备
|
||||
"""
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
|
||||
payload = {
|
||||
"model": llm_kwargs['llm_model'],
|
||||
"messages": messages,
|
||||
"temperature": llm_kwargs['temperature'], # 1.0,
|
||||
"top_p": llm_kwargs['top_p'], # 1.0,
|
||||
"n": 1,
|
||||
"stream": stream,
|
||||
"presence_penalty": 0,
|
||||
"frequency_penalty": 0,
|
||||
"engine": AZURE_ENGINE
|
||||
}
|
||||
try:
|
||||
print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
|
||||
except:
|
||||
print('输入中可能存在乱码。')
|
||||
return payload
|
||||
|
||||
|
||||
14
toolbox.py
14
toolbox.py
@ -6,6 +6,7 @@ import re
|
||||
import os
|
||||
from latex2mathml.converter import convert as tex2mathml
|
||||
from functools import wraps, lru_cache
|
||||
pj = os.path.join
|
||||
|
||||
"""
|
||||
========================================================================
|
||||
@ -399,7 +400,7 @@ def extract_archive(file_path, dest_dir):
|
||||
print("Successfully extracted rar archive to {}".format(dest_dir))
|
||||
except:
|
||||
print("Rar format requires additional dependencies to install")
|
||||
return '\n\n需要安装pip install rarfile来解压rar文件'
|
||||
return '\n\n解压失败! 需要安装pip install rarfile来解压rar文件'
|
||||
|
||||
# 第三方库，需要预先pip install py7zr
|
||||
elif file_extension == '.7z':
|
||||
@ -410,7 +411,7 @@ def extract_archive(file_path, dest_dir):
|
||||
print("Successfully extracted 7z archive to {}".format(dest_dir))
|
||||
except:
|
||||
print("7z format requires additional dependencies to install")
|
||||
return '\n\n需要安装pip install py7zr来解压7z文件'
|
||||
return '\n\n解压失败! 需要安装pip install py7zr来解压7z文件'
|
||||
else:
|
||||
return ''
|
||||
return ''
|
||||
@ -444,10 +445,12 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
|
||||
import shutil
|
||||
if rename_file is None: rename_file = f'{gen_time_str()}-{os.path.basename(file)}'
|
||||
new_path = os.path.join(f'./gpt_log/', rename_file)
|
||||
if os.path.exists(new_path): os.remove(new_path)
|
||||
shutil.copyfile(file, new_path)
|
||||
if os.path.exists(new_path) and not os.path.samefile(new_path, file): os.remove(new_path)
|
||||
if not os.path.exists(new_path): shutil.copyfile(file, new_path)
|
||||
if chatbot:
|
||||
chatbot._cookies.update({'file_to_promote': [new_path]})
|
||||
if 'file_to_promote' in chatbot._cookies: current = chatbot._cookies['file_to_promote']
|
||||
else: current = []
|
||||
chatbot._cookies.update({'file_to_promote': [new_path] + current})
|
||||
|
||||
def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
|
||||
"""
|
||||
@ -802,6 +805,7 @@ def zip_result(folder):
|
||||
import time
|
||||
t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
|
||||
zip_folder(folder, './gpt_log/', f'{t}-result.zip')
|
||||
return pj('./gpt_log/', f'{t}-result.zip')
|
||||
|
||||
def gen_time_str():
|
||||
import time
|
||||
|
||||
Reference in New Issue
Block a user