Compare commits
24 Commits
threejs-ap
...
CodeInterp
| Author | SHA1 | Date | |
|---|---|---|---|
| fb22f716ff | |||
| a8093b9dd8 | |||
| 4f55dfdc0e | |||
| 505b10965f | |||
| a393edfaa4 | |||
| dd7a01cda5 | |||
| 00a3b91f95 | |||
| 61ba544282 | |||
| b5b8c123e4 | |||
| d9ceba959f | |||
| 6b5b040701 | |||
| 4f4c09a5f3 | |||
| 067bc97cce | |||
| 7368580cd6 | |||
| df90db210c | |||
| 0927ed20a2 | |||
| 73b22f85be | |||
| b8d77557b0 | |||
| 99b8fce8f3 | |||
| 16364f1b2d | |||
| 3b88e00cfb | |||
| 0c8c539e9b | |||
| fd549fb986 | |||
| babb775cfb |
1
.gitignore
vendored
1
.gitignore
vendored
@ -151,3 +151,4 @@ multi-language
|
||||
request_llm/moss
|
||||
media
|
||||
flagged
|
||||
objdump.tmp
|
||||
|
||||
@ -44,7 +44,7 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
|
||||
Latex论文一键校对 | [函数插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
|
||||
[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
|
||||
互联网信息聚合+GPT | [函数插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
|
||||
⭐Arxiv论文精细翻译 | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
|
||||
⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
|
||||
⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [函数插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
|
||||
公式/图片/表格显示 | 可以同时显示公式的[tex形式和渲染形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)，支持公式、代码高亮
|
||||
多线程函数插件支持 | 支持多线调用chatgpt，一键处理[海量文本](https://www.bilibili.com/video/BV1FT411H7c5/)或程序
|
||||
|
||||
12
config.py
12
config.py
@ -32,9 +32,9 @@ else:
|
||||
|
||||
# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
|
||||
|
||||
# 重新URL重新定向，实现更换API_URL的作用（常规情况下，不要修改!! 高危设置！通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
|
||||
# 格式 API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
|
||||
# 例如 API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions":"https://reverse-proxy-url/v1/chat/completions"}
|
||||
# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
|
||||
# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
|
||||
# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
|
||||
API_URL_REDIRECT = {}
|
||||
|
||||
|
||||
@ -71,7 +71,7 @@ MAX_RETRY = 2
|
||||
# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
|
||||
LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "stack-claude"]
|
||||
# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "claude-1-100k", "claude-2", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
||||
# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "claude-1-100k", "claude-2", "internlm", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
||||
|
||||
|
||||
# ChatGLM(2) Finetune Model Path （如果使用ChatGLM2微调模型，需要把"chatglmft"加入AVAIL_LLM_MODELS中）
|
||||
@ -137,3 +137,7 @@ ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK
|
||||
|
||||
# Claude API KEY
|
||||
ANTHROPIC_API_KEY = ""
|
||||
|
||||
|
||||
# 自定义API KEY格式
|
||||
CUSTOM_API_KEY_PATTERN = ""
|
||||
@ -432,18 +432,18 @@ def get_crazy_functions():
|
||||
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')
|
||||
try:
|
||||
from crazy_functions.虚空终端CodeInterpreter import 虚空终端CodeInterpreter
|
||||
function_plugins.update({
|
||||
"虚空终端CodeInterpreter": {
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
# "AdvancedArgs": True,
|
||||
# "ArgsReminder": "",
|
||||
"Function": HotReload(虚空终端CodeInterpreter)
|
||||
}
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
return function_plugins
|
||||
|
||||
@ -157,7 +157,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_utils import Latex精细分解与转化, 编译Latex
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
@ -234,7 +234,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_utils import Latex精细分解与转化, 编译Latex
|
||||
from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
|
||||
@ -195,9 +195,12 @@ def test_Latex():
|
||||
# txt = r"https://arxiv.org/abs/2303.08774"
|
||||
# txt = r"https://arxiv.org/abs/2303.12712"
|
||||
# txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
|
||||
txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
|
||||
|
||||
|
||||
# txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
|
||||
# txt = "https://arxiv.org/abs/2205.14135"
|
||||
# txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
|
||||
# txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
|
||||
txt = r"2210.03629"
|
||||
txt = r"2307.04964"
|
||||
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)
|
||||
|
||||
@ -225,6 +228,22 @@ def test_chatglm_finetune():
|
||||
for cookies, cb, hist, msg in (启动微调)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
cli_printer.print(cb)
|
||||
|
||||
def test_虚空终端CodeInterpreter():
|
||||
from crazy_functions.虚空终端CodeInterpreter import 虚空终端CodeInterpreter
|
||||
txt = 'Convert this dataset to excel.'
|
||||
plugin_kwargs = {"recently_uploaded_files":"build/assets/iris.csv"}
|
||||
|
||||
for cookies, cb, hist, msg in (虚空终端CodeInterpreter)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
cli_printer.print(cb)
|
||||
|
||||
|
||||
def test_解析项目源代码炫酷版():
|
||||
from crazy_functions.解析项目源代码炫酷版 import 解析一个Python项目炫酷版
|
||||
txt = './'
|
||||
|
||||
for cookies, cb, hist, msg in (解析一个Python项目炫酷版)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
cli_printer.print(cb)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# test_解析一个Python项目()
|
||||
@ -241,6 +260,8 @@ if __name__ == "__main__":
|
||||
# test_Langchain知识库()
|
||||
# test_Langchain知识库读取()
|
||||
# test_Latex()
|
||||
test_chatglm_finetune()
|
||||
# test_chatglm_finetune()
|
||||
# test_虚空终端CodeInterpreter()
|
||||
test_解析项目源代码炫酷版()
|
||||
input("程序完成，回车退出。")
|
||||
print("退出。")
|
||||
@ -141,7 +141,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
chatbot, history_array, sys_prompt_array,
|
||||
refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
|
||||
handle_token_exceed=True, show_user_at_complete=False,
|
||||
retry_times_at_unknown_error=2,
|
||||
retry_times_at_unknown_error=2, callback_fn=None
|
||||
):
|
||||
"""
|
||||
Request GPT model using multiple threads with UI and high efficiency
|
||||
@ -166,6 +166,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
handle_token_exceed：是否自动处理token溢出的情况，如果选择自动处理，则会在溢出时暴力截断，默认开启
|
||||
show_user_at_complete (bool, optional): (在结束时，把完整输入-输出结果显示在聊天框)
|
||||
retry_times_at_unknown_error：子任务失败时的重试次数
|
||||
callback_fn: 当信息更新时，在主进程调用的回调函数
|
||||
|
||||
输出 Returns:
|
||||
list: List of GPT model responses （每个子任务的输出汇总，如果某个子任务出错，response中会携带traceback报错信息，方便调试和定位问题。）
|
||||
@ -283,6 +284,9 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
# 在前端打印些好玩的东西
|
||||
chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
|
||||
yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
|
||||
# 回调函数
|
||||
if callback_fn is not None: callback_fn([mutable[thread_index][0] for thread_index in range(len(futures))])
|
||||
# 结束了吗？
|
||||
if all(worker_done):
|
||||
executor.shutdown()
|
||||
break
|
||||
|
||||
@ -1,320 +1,16 @@
|
||||
from toolbox import update_ui, update_ui_lastest_msg # 刷新Gradio前端界面
|
||||
from toolbox import zip_folder, objdump, objload, promote_file_to_downloadzone
|
||||
from .latex_toolbox import PRESERVE, TRANSFORM
|
||||
from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
|
||||
from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
|
||||
from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
|
||||
|
||||
import os, shutil
|
||||
import re
|
||||
import numpy as np
|
||||
|
||||
pj = os.path.join
|
||||
|
||||
"""
|
||||
========================================================================
|
||||
Part One
|
||||
Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
|
||||
========================================================================
|
||||
"""
|
||||
PRESERVE = 0
|
||||
TRANSFORM = 1
|
||||
|
||||
def set_forbidden_text(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper
|
||||
e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
|
||||
you can mask out (mask = PRESERVE so that text become untouchable for GPT)
|
||||
everything between "\begin{equation}" and "\end{equation}"
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
mask[res.span()[0]:res.span()[1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\begin{abstract} blablablablablabla. \end{abstract}
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
if not forbid_wrapper:
|
||||
mask[res.span()[0]:res.span()[1]] = TRANSFORM
|
||||
else:
|
||||
mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE # '\\begin{abstract}'
|
||||
mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM # abstract
|
||||
mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE # abstract
|
||||
return text, mask
|
||||
|
||||
def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper (text become untouchable for GPT).
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
brace_level = -1
|
||||
p = begin = end = res.regs[0][0]
|
||||
for _ in range(1024*16):
|
||||
if text[p] == '}' and brace_level == 0: break
|
||||
elif text[p] == '}': brace_level -= 1
|
||||
elif text[p] == '{': brace_level += 1
|
||||
p += 1
|
||||
end = p+1
|
||||
mask[begin:end] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
brace_level = 0
|
||||
p = begin = end = res.regs[1][0]
|
||||
for _ in range(1024*16):
|
||||
if text[p] == '}' and brace_level == 0: break
|
||||
elif text[p] == '}': brace_level -= 1
|
||||
elif text[p] == '{': brace_level += 1
|
||||
p += 1
|
||||
end = p
|
||||
mask[begin:end] = TRANSFORM
|
||||
if forbid_wrapper:
|
||||
mask[res.regs[0][0]:begin] = PRESERVE
|
||||
mask[end:res.regs[0][1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
|
||||
"""
|
||||
Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
|
||||
Add it to preserve area
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
def search_with_line_limit(text, mask):
|
||||
for res in pattern_compile.finditer(text):
|
||||
cmd = res.group(1) # begin{what}
|
||||
this = res.group(2) # content between begin and end
|
||||
this_mask = mask[res.regs[2][0]:res.regs[2][1]]
|
||||
white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof',
|
||||
'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
|
||||
if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
|
||||
this, this_mask = search_with_line_limit(this, this_mask)
|
||||
mask[res.regs[2][0]:res.regs[2][1]] = this_mask
|
||||
else:
|
||||
mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
|
||||
return text, mask
|
||||
return search_with_line_limit(text, mask)
|
||||
|
||||
class LinkedListNode():
|
||||
"""
|
||||
Linked List Node
|
||||
"""
|
||||
def __init__(self, string, preserve=True) -> None:
|
||||
self.string = string
|
||||
self.preserve = preserve
|
||||
self.next = None
|
||||
# self.begin_line = 0
|
||||
# self.begin_char = 0
|
||||
|
||||
def convert_to_linklist(text, mask):
|
||||
root = LinkedListNode("", preserve=True)
|
||||
current_node = root
|
||||
for c, m, i in zip(text, mask, range(len(text))):
|
||||
if (m==PRESERVE and current_node.preserve) \
|
||||
or (m==TRANSFORM and not current_node.preserve):
|
||||
# add
|
||||
current_node.string += c
|
||||
else:
|
||||
current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
|
||||
current_node = current_node.next
|
||||
return root
|
||||
"""
|
||||
========================================================================
|
||||
Latex Merge File
|
||||
========================================================================
|
||||
"""
|
||||
|
||||
def 寻找Latex主文件(file_manifest, mode):
|
||||
"""
|
||||
在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
|
||||
P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
|
||||
"""
|
||||
canidates = []
|
||||
for texf in file_manifest:
|
||||
if os.path.basename(texf).startswith('merge'):
|
||||
continue
|
||||
with open(texf, 'r', encoding='utf8', errors='ignore') as f:
|
||||
file_content = f.read()
|
||||
if r'\documentclass' in file_content:
|
||||
canidates.append(texf)
|
||||
else:
|
||||
continue
|
||||
|
||||
if len(canidates) == 0:
|
||||
raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
|
||||
elif len(canidates) == 1:
|
||||
return canidates[0]
|
||||
else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
|
||||
canidates_score = []
|
||||
# 给出一些判定模板文档的词作为扣分项
|
||||
unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
|
||||
expected_words = ['\input', '\ref', '\cite']
|
||||
for texf in canidates:
|
||||
canidates_score.append(0)
|
||||
with open(texf, 'r', encoding='utf8', errors='ignore') as f:
|
||||
file_content = f.read()
|
||||
for uw in unexpected_words:
|
||||
if uw in file_content:
|
||||
canidates_score[-1] -= 1
|
||||
for uw in expected_words:
|
||||
if uw in file_content:
|
||||
canidates_score[-1] += 1
|
||||
select = np.argmax(canidates_score) # 取评分最高者返回
|
||||
return canidates[select]
|
||||
|
||||
def rm_comments(main_file):
|
||||
new_file_remove_comment_lines = []
|
||||
for l in main_file.splitlines():
|
||||
# 删除整行的空注释
|
||||
if l.lstrip().startswith("%"):
|
||||
pass
|
||||
else:
|
||||
new_file_remove_comment_lines.append(l)
|
||||
main_file = '\n'.join(new_file_remove_comment_lines)
|
||||
# main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file) # 将 \include 命令转换为 \input 命令
|
||||
main_file = re.sub(r'(?<!\\)%.*', '', main_file) # 使用正则表达式查找半行注释, 并替换为空字符串
|
||||
return main_file
|
||||
|
||||
def find_tex_file_ignore_case(fp):
|
||||
dir_name = os.path.dirname(fp)
|
||||
base_name = os.path.basename(fp)
|
||||
if not base_name.endswith('.tex'): base_name+='.tex'
|
||||
if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
|
||||
# go case in-sensitive
|
||||
import glob
|
||||
for f in glob.glob(dir_name+'/*.tex'):
|
||||
base_name_s = os.path.basename(fp)
|
||||
if base_name_s.lower() == base_name.lower(): return f
|
||||
return None
|
||||
|
||||
def merge_tex_files_(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recrusively
|
||||
"""
|
||||
main_file = rm_comments(main_file)
|
||||
for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
|
||||
f = s.group(1)
|
||||
fp = os.path.join(project_foler, f)
|
||||
fp = find_tex_file_ignore_case(fp)
|
||||
if fp:
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
|
||||
else:
|
||||
raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
|
||||
c = merge_tex_files_(project_foler, c, mode)
|
||||
main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
|
||||
return main_file
|
||||
|
||||
def merge_tex_files(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recrusively
|
||||
P.S. 顺便把CTEX塞进去以支持中文
|
||||
P.S. 顺便把Latex的注释去除
|
||||
"""
|
||||
main_file = merge_tex_files_(project_foler, main_file, mode)
|
||||
main_file = rm_comments(main_file)
|
||||
|
||||
if mode == 'translate_zh':
|
||||
# find paper documentclass
|
||||
pattern = re.compile(r'\\documentclass.*\n')
|
||||
match = pattern.search(main_file)
|
||||
assert match is not None, "Cannot find documentclass statement!"
|
||||
position = match.end()
|
||||
add_ctex = '\\usepackage{ctex}\n'
|
||||
add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
|
||||
main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
|
||||
# fontset=windows
|
||||
import platform
|
||||
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_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
|
||||
match_opt1 = pattern_opt1.search(main_file)
|
||||
match_opt2 = pattern_opt2.search(main_file)
|
||||
assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
|
||||
return main_file
|
||||
|
||||
|
||||
|
||||
"""
|
||||
========================================================================
|
||||
Post process
|
||||
========================================================================
|
||||
"""
|
||||
def mod_inbraket(match):
|
||||
"""
|
||||
为啥chatgpt会把cite里面的逗号换成中文逗号呀
|
||||
"""
|
||||
# get the matched string
|
||||
cmd = match.group(1)
|
||||
str_to_modify = match.group(2)
|
||||
# modify the matched string
|
||||
str_to_modify = str_to_modify.replace('：', ':') # 前面是中文冒号，后面是英文冒号
|
||||
str_to_modify = str_to_modify.replace('，', ',') # 前面是中文逗号，后面是英文逗号
|
||||
# str_to_modify = 'BOOM'
|
||||
return "\\" + cmd + "{" + str_to_modify + "}"
|
||||
|
||||
def fix_content(final_tex, node_string):
|
||||
"""
|
||||
Fix common GPT errors to increase success rate
|
||||
"""
|
||||
final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
|
||||
final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
|
||||
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('\_'):
|
||||
# walk and replace any _ without \
|
||||
final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
|
||||
|
||||
def compute_brace_level(string):
|
||||
# this function count the number of { and }
|
||||
brace_level = 0
|
||||
for c in string:
|
||||
if c == "{": brace_level += 1
|
||||
elif c == "}": brace_level -= 1
|
||||
return brace_level
|
||||
def join_most(tex_t, tex_o):
|
||||
# this function join translated string and original string when something goes wrong
|
||||
p_t = 0
|
||||
p_o = 0
|
||||
def find_next(string, chars, begin):
|
||||
p = begin
|
||||
while p < len(string):
|
||||
if string[p] in chars: return p, string[p]
|
||||
p += 1
|
||||
return None, None
|
||||
while True:
|
||||
res1, char = find_next(tex_o, ['{','}'], p_o)
|
||||
if res1 is None: break
|
||||
res2, char = find_next(tex_t, [char], p_t)
|
||||
if res2 is None: break
|
||||
p_o = res1 + 1
|
||||
p_t = res2 + 1
|
||||
return tex_t[:p_t] + tex_o[p_o:]
|
||||
|
||||
if compute_brace_level(final_tex) != compute_brace_level(node_string):
|
||||
# 出问题了，还原部分原文，保证括号正确
|
||||
final_tex = join_most(final_tex, node_string)
|
||||
return final_tex
|
||||
|
||||
def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
"""
|
||||
@ -356,77 +52,9 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
|
||||
root = convert_to_linklist(text, mask)
|
||||
|
||||
# 修复括号
|
||||
node = root
|
||||
while True:
|
||||
string = node.string
|
||||
if node.preserve:
|
||||
node = node.next
|
||||
if node is None: break
|
||||
continue
|
||||
def break_check(string):
|
||||
str_stack = [""] # (lv, index)
|
||||
for i, c in enumerate(string):
|
||||
if c == '{':
|
||||
str_stack.append('{')
|
||||
elif c == '}':
|
||||
if len(str_stack) == 1:
|
||||
print('stack fix')
|
||||
return i
|
||||
str_stack.pop(-1)
|
||||
else:
|
||||
str_stack[-1] += c
|
||||
return -1
|
||||
bp = break_check(string)
|
||||
# 最后一步处理，增强稳健性
|
||||
root = post_process(root)
|
||||
|
||||
if bp == -1:
|
||||
pass
|
||||
elif bp == 0:
|
||||
node.string = string[:1]
|
||||
q = LinkedListNode(string[1:], False)
|
||||
q.next = node.next
|
||||
node.next = q
|
||||
else:
|
||||
node.string = string[:bp]
|
||||
q = LinkedListNode(string[bp:], False)
|
||||
q.next = node.next
|
||||
node.next = q
|
||||
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 屏蔽空行和太短的句子
|
||||
node = root
|
||||
while True:
|
||||
if len(node.string.strip('\n').strip(''))==0: node.preserve = True
|
||||
if len(node.string.strip('\n').strip(''))<42: node.preserve = True
|
||||
node = node.next
|
||||
if node is None: break
|
||||
node = root
|
||||
while True:
|
||||
if node.next and node.preserve and node.next.preserve:
|
||||
node.string += node.next.string
|
||||
node.next = node.next.next
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 将前后断行符脱离
|
||||
node = root
|
||||
prev_node = None
|
||||
while True:
|
||||
if not node.preserve:
|
||||
lstriped_ = node.string.lstrip().lstrip('\n')
|
||||
if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
|
||||
prev_node.string += node.string[:-len(lstriped_)]
|
||||
node.string = lstriped_
|
||||
rstriped_ = node.string.rstrip().rstrip('\n')
|
||||
if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
|
||||
node.next.string = node.string[len(rstriped_):] + node.next.string
|
||||
node.string = rstriped_
|
||||
# =====
|
||||
prev_node = node
|
||||
node = node.next
|
||||
if node is None: break
|
||||
# 输出html调试文件，用红色标注处保留区（PRESERVE），用黑色标注转换区（TRANSFORM）
|
||||
with open(pj(project_folder, 'debug_log.html'), 'w', encoding='utf8') as f:
|
||||
segment_parts_for_gpt = []
|
||||
@ -437,7 +65,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
show_html = node.string.replace('\n','<br/>')
|
||||
if not node.preserve:
|
||||
segment_parts_for_gpt.append(node.string)
|
||||
f.write(f'<p style="color:black;">#{show_html}#</p>')
|
||||
f.write(f'<p style="color:black;">#{node.range}{show_html}#</p>')
|
||||
else:
|
||||
f.write(f'<p style="color:red;">{show_html}</p>')
|
||||
node = node.next
|
||||
@ -448,8 +76,6 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
|
||||
return return_dict
|
||||
|
||||
|
||||
|
||||
class LatexPaperSplit():
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
@ -464,18 +90,32 @@ class LatexPaperSplit():
|
||||
# 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。}}\\\\"
|
||||
|
||||
def merge_result(self, arr, mode, msg):
|
||||
|
||||
def merge_result(self, arr, mode, msg, buggy_lines=[], buggy_line_surgery_n_lines=10):
|
||||
"""
|
||||
Merge the result after the GPT process completed
|
||||
"""
|
||||
result_string = ""
|
||||
p = 0
|
||||
node_cnt = 0
|
||||
line_cnt = 0
|
||||
|
||||
for node in self.nodes:
|
||||
if node.preserve:
|
||||
line_cnt += node.string.count('\n')
|
||||
result_string += node.string
|
||||
else:
|
||||
result_string += fix_content(arr[p], node.string)
|
||||
p += 1
|
||||
translated_txt = fix_content(arr[node_cnt], node.string)
|
||||
begin_line = line_cnt
|
||||
end_line = line_cnt + translated_txt.count('\n')
|
||||
|
||||
# reverse translation if any error
|
||||
if any([begin_line-buggy_line_surgery_n_lines <= b_line <= end_line+buggy_line_surgery_n_lines for b_line in buggy_lines]):
|
||||
translated_txt = node.string
|
||||
|
||||
result_string += translated_txt
|
||||
node_cnt += 1
|
||||
line_cnt += translated_txt.count('\n')
|
||||
|
||||
if mode == 'translate_zh':
|
||||
pattern = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
match = pattern.search(result_string)
|
||||
@ -490,6 +130,7 @@ class LatexPaperSplit():
|
||||
result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
|
||||
return result_string
|
||||
|
||||
|
||||
def split(self, txt, project_folder, opts):
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
@ -511,7 +152,6 @@ class LatexPaperSplit():
|
||||
return self.sp
|
||||
|
||||
|
||||
|
||||
class LatexPaperFileGroup():
|
||||
"""
|
||||
use tokenizer to break down text according to max_token_limit
|
||||
@ -539,7 +179,7 @@ class LatexPaperFileGroup():
|
||||
self.sp_file_index.append(index)
|
||||
self.sp_file_tag.append(self.file_paths[index])
|
||||
else:
|
||||
from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
from ..crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
|
||||
segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
|
||||
for j, segment in enumerate(segments):
|
||||
self.sp_file_contents.append(segment)
|
||||
@ -560,41 +200,14 @@ class LatexPaperFileGroup():
|
||||
f.write(res)
|
||||
return manifest
|
||||
|
||||
def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
|
||||
|
||||
# write html
|
||||
try:
|
||||
import shutil
|
||||
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)
|
||||
shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, 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
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .latex_utils import LatexPaperFileGroup, merge_tex_files, LatexPaperSplit, 寻找Latex主文件
|
||||
from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
|
||||
|
||||
# <-------- 寻找主tex文件 ---------->
|
||||
maintex = 寻找Latex主文件(file_manifest, mode)
|
||||
maintex = find_main_tex_file(file_manifest, mode)
|
||||
chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
time.sleep(3)
|
||||
@ -668,54 +281,51 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
# <-------- 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']}。"
|
||||
final_tex = lps.merge_result(pfg.file_result, mode, msg)
|
||||
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
|
||||
|
||||
with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
|
||||
if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
|
||||
|
||||
|
||||
# <-------- 整理结果, 退出 ---------->
|
||||
chatbot.append((f"完成了吗？", 'GPT结果已输出, 正在编译PDF'))
|
||||
chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------- 返回 ---------->
|
||||
return project_folder + f'/merge_{mode}.tex'
|
||||
|
||||
|
||||
|
||||
def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified):
|
||||
def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified, fixed_line=[]):
|
||||
try:
|
||||
with open(log_path, 'r', encoding='utf-8', errors='replace') as f:
|
||||
log = f.read()
|
||||
with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_lines = f.readlines()
|
||||
import re
|
||||
buggy_lines = re.findall(tex_name+':([0-9]{1,5}):', log)
|
||||
buggy_lines = [int(l) for l in buggy_lines]
|
||||
buggy_lines = sorted(buggy_lines)
|
||||
print("removing lines that has errors", buggy_lines)
|
||||
file_lines.pop(buggy_lines[0]-1)
|
||||
buggy_line = buggy_lines[0]-1
|
||||
print("reversing tex line that has errors", buggy_line)
|
||||
|
||||
# 重组，逆转出错的段落
|
||||
if buggy_line not in fixed_line:
|
||||
fixed_line.append(buggy_line)
|
||||
|
||||
lps, file_result, mode, msg = objload(file=pj(work_folder_modified,'merge_result.pkl'))
|
||||
final_tex = lps.merge_result(file_result, mode, msg, buggy_lines=fixed_line, buggy_line_surgery_n_lines=5*n_fix)
|
||||
|
||||
with open(pj(work_folder_modified, f"{tex_name_pure}_fix_{n_fix}.tex"), 'w', encoding='utf-8', errors='replace') as f:
|
||||
f.writelines(file_lines)
|
||||
f.write(final_tex)
|
||||
|
||||
return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
|
||||
except:
|
||||
print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
|
||||
return False, -1, [-1]
|
||||
|
||||
def compile_latex_with_timeout(command, cwd, timeout=60):
|
||||
import subprocess
|
||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
|
||||
try:
|
||||
stdout, stderr = process.communicate(timeout=timeout)
|
||||
except subprocess.TimeoutExpired:
|
||||
process.kill()
|
||||
stdout, stderr = process.communicate()
|
||||
print("Process timed out!")
|
||||
return False
|
||||
return True
|
||||
|
||||
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
|
||||
fixed_line = []
|
||||
max_try = 32
|
||||
chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
|
||||
chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
|
||||
@ -723,6 +333,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
|
||||
while True:
|
||||
import os
|
||||
may_exist_bbl = pj(work_folder_modified, f'merge.bbl')
|
||||
target_bbl = pj(work_folder_modified, f'{main_file_modified}.bbl')
|
||||
if os.path.exists(may_exist_bbl) and not os.path.exists(target_bbl):
|
||||
shutil.copyfile(may_exist_bbl, target_bbl)
|
||||
|
||||
# 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
|
||||
@ -756,7 +370,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||
|
||||
|
||||
# <---------- 检查结果 ----------->
|
||||
results_ = ""
|
||||
original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
|
||||
@ -773,9 +386,19 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
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
|
||||
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
|
||||
origin_pdf = pj(work_folder_original, f'{main_file_original}.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 web UI
|
||||
# 将两个PDF拼接
|
||||
if original_pdf_success:
|
||||
try:
|
||||
from .latex_toolbox import merge_pdfs
|
||||
concat_pdf = pj(work_folder_modified, f'comparison.pdf')
|
||||
merge_pdfs(origin_pdf, result_pdf, concat_pdf)
|
||||
promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
|
||||
except Exception as e:
|
||||
pass
|
||||
return True # 成功啦
|
||||
else:
|
||||
if n_fix>=max_try: break
|
||||
@ -787,6 +410,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
tex_name_pure=f'{main_file_modified}',
|
||||
n_fix=n_fix,
|
||||
work_folder_modified=work_folder_modified,
|
||||
fixed_line=fixed_line
|
||||
)
|
||||
yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
if not can_retry: break
|
||||
@ -794,4 +418,29 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
return False # 失败啦
|
||||
|
||||
|
||||
|
||||
def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
|
||||
# write html
|
||||
try:
|
||||
import shutil
|
||||
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)
|
||||
shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, 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())
|
||||
456
crazy_functions/latex_fns/latex_toolbox.py
Normal file
456
crazy_functions/latex_fns/latex_toolbox.py
Normal file
@ -0,0 +1,456 @@
|
||||
import os, shutil
|
||||
import re
|
||||
import numpy as np
|
||||
PRESERVE = 0
|
||||
TRANSFORM = 1
|
||||
|
||||
pj = os.path.join
|
||||
|
||||
class LinkedListNode():
|
||||
"""
|
||||
Linked List Node
|
||||
"""
|
||||
def __init__(self, string, preserve=True) -> None:
|
||||
self.string = string
|
||||
self.preserve = preserve
|
||||
self.next = None
|
||||
self.range = None
|
||||
# self.begin_line = 0
|
||||
# self.begin_char = 0
|
||||
|
||||
def convert_to_linklist(text, mask):
|
||||
root = LinkedListNode("", preserve=True)
|
||||
current_node = root
|
||||
for c, m, i in zip(text, mask, range(len(text))):
|
||||
if (m==PRESERVE and current_node.preserve) \
|
||||
or (m==TRANSFORM and not current_node.preserve):
|
||||
# add
|
||||
current_node.string += c
|
||||
else:
|
||||
current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
|
||||
current_node = current_node.next
|
||||
return root
|
||||
|
||||
def post_process(root):
|
||||
# 修复括号
|
||||
node = root
|
||||
while True:
|
||||
string = node.string
|
||||
if node.preserve:
|
||||
node = node.next
|
||||
if node is None: break
|
||||
continue
|
||||
def break_check(string):
|
||||
str_stack = [""] # (lv, index)
|
||||
for i, c in enumerate(string):
|
||||
if c == '{':
|
||||
str_stack.append('{')
|
||||
elif c == '}':
|
||||
if len(str_stack) == 1:
|
||||
print('stack fix')
|
||||
return i
|
||||
str_stack.pop(-1)
|
||||
else:
|
||||
str_stack[-1] += c
|
||||
return -1
|
||||
bp = break_check(string)
|
||||
|
||||
if bp == -1:
|
||||
pass
|
||||
elif bp == 0:
|
||||
node.string = string[:1]
|
||||
q = LinkedListNode(string[1:], False)
|
||||
q.next = node.next
|
||||
node.next = q
|
||||
else:
|
||||
node.string = string[:bp]
|
||||
q = LinkedListNode(string[bp:], False)
|
||||
q.next = node.next
|
||||
node.next = q
|
||||
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 屏蔽空行和太短的句子
|
||||
node = root
|
||||
while True:
|
||||
if len(node.string.strip('\n').strip(''))==0: node.preserve = True
|
||||
if len(node.string.strip('\n').strip(''))<42: node.preserve = True
|
||||
node = node.next
|
||||
if node is None: break
|
||||
node = root
|
||||
while True:
|
||||
if node.next and node.preserve and node.next.preserve:
|
||||
node.string += node.next.string
|
||||
node.next = node.next.next
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 将前后断行符脱离
|
||||
node = root
|
||||
prev_node = None
|
||||
while True:
|
||||
if not node.preserve:
|
||||
lstriped_ = node.string.lstrip().lstrip('\n')
|
||||
if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
|
||||
prev_node.string += node.string[:-len(lstriped_)]
|
||||
node.string = lstriped_
|
||||
rstriped_ = node.string.rstrip().rstrip('\n')
|
||||
if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
|
||||
node.next.string = node.string[len(rstriped_):] + node.next.string
|
||||
node.string = rstriped_
|
||||
# =====
|
||||
prev_node = node
|
||||
node = node.next
|
||||
if node is None: break
|
||||
|
||||
# 标注节点的行数范围
|
||||
node = root
|
||||
n_line = 0
|
||||
expansion = 2
|
||||
while True:
|
||||
n_l = node.string.count('\n')
|
||||
node.range = [n_line-expansion, n_line+n_l+expansion] # 失败时，扭转的范围
|
||||
n_line = n_line+n_l
|
||||
node = node.next
|
||||
if node is None: break
|
||||
return root
|
||||
|
||||
|
||||
"""
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
"""
|
||||
|
||||
|
||||
def set_forbidden_text(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper
|
||||
e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
|
||||
you can mask out (mask = PRESERVE so that text become untouchable for GPT)
|
||||
everything between "\begin{equation}" and "\end{equation}"
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
mask[res.span()[0]:res.span()[1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\begin{abstract} blablablablablabla. \end{abstract}
|
||||
"""
|
||||
if isinstance(pattern, list): pattern = '|'.join(pattern)
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
if not forbid_wrapper:
|
||||
mask[res.span()[0]:res.span()[1]] = TRANSFORM
|
||||
else:
|
||||
mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE # '\\begin{abstract}'
|
||||
mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM # abstract
|
||||
mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE # abstract
|
||||
return text, mask
|
||||
|
||||
def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper (text become untouchable for GPT).
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
brace_level = -1
|
||||
p = begin = end = res.regs[0][0]
|
||||
for _ in range(1024*16):
|
||||
if text[p] == '}' and brace_level == 0: break
|
||||
elif text[p] == '}': brace_level -= 1
|
||||
elif text[p] == '{': brace_level += 1
|
||||
p += 1
|
||||
end = p+1
|
||||
mask[begin:end] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
for res in pattern_compile.finditer(text):
|
||||
brace_level = 0
|
||||
p = begin = end = res.regs[1][0]
|
||||
for _ in range(1024*16):
|
||||
if text[p] == '}' and brace_level == 0: break
|
||||
elif text[p] == '}': brace_level -= 1
|
||||
elif text[p] == '{': brace_level += 1
|
||||
p += 1
|
||||
end = p
|
||||
mask[begin:end] = TRANSFORM
|
||||
if forbid_wrapper:
|
||||
mask[res.regs[0][0]:begin] = PRESERVE
|
||||
mask[end:res.regs[0][1]] = PRESERVE
|
||||
return text, mask
|
||||
|
||||
def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
|
||||
"""
|
||||
Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
|
||||
Add it to preserve area
|
||||
"""
|
||||
pattern_compile = re.compile(pattern, flags)
|
||||
def search_with_line_limit(text, mask):
|
||||
for res in pattern_compile.finditer(text):
|
||||
cmd = res.group(1) # begin{what}
|
||||
this = res.group(2) # content between begin and end
|
||||
this_mask = mask[res.regs[2][0]:res.regs[2][1]]
|
||||
white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof',
|
||||
'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
|
||||
if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
|
||||
this, this_mask = search_with_line_limit(this, this_mask)
|
||||
mask[res.regs[2][0]:res.regs[2][1]] = this_mask
|
||||
else:
|
||||
mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
|
||||
return text, mask
|
||||
return search_with_line_limit(text, mask)
|
||||
|
||||
|
||||
|
||||
"""
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
Latex Merge File
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
"""
|
||||
|
||||
def find_main_tex_file(file_manifest, mode):
|
||||
"""
|
||||
在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
|
||||
P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
|
||||
"""
|
||||
canidates = []
|
||||
for texf in file_manifest:
|
||||
if os.path.basename(texf).startswith('merge'):
|
||||
continue
|
||||
with open(texf, 'r', encoding='utf8', errors='ignore') as f:
|
||||
file_content = f.read()
|
||||
if r'\documentclass' in file_content:
|
||||
canidates.append(texf)
|
||||
else:
|
||||
continue
|
||||
|
||||
if len(canidates) == 0:
|
||||
raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
|
||||
elif len(canidates) == 1:
|
||||
return canidates[0]
|
||||
else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
|
||||
canidates_score = []
|
||||
# 给出一些判定模板文档的词作为扣分项
|
||||
unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
|
||||
expected_words = ['\input', '\ref', '\cite']
|
||||
for texf in canidates:
|
||||
canidates_score.append(0)
|
||||
with open(texf, 'r', encoding='utf8', errors='ignore') as f:
|
||||
file_content = f.read()
|
||||
for uw in unexpected_words:
|
||||
if uw in file_content:
|
||||
canidates_score[-1] -= 1
|
||||
for uw in expected_words:
|
||||
if uw in file_content:
|
||||
canidates_score[-1] += 1
|
||||
select = np.argmax(canidates_score) # 取评分最高者返回
|
||||
return canidates[select]
|
||||
|
||||
def rm_comments(main_file):
|
||||
new_file_remove_comment_lines = []
|
||||
for l in main_file.splitlines():
|
||||
# 删除整行的空注释
|
||||
if l.lstrip().startswith("%"):
|
||||
pass
|
||||
else:
|
||||
new_file_remove_comment_lines.append(l)
|
||||
main_file = '\n'.join(new_file_remove_comment_lines)
|
||||
# main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file) # 将 \include 命令转换为 \input 命令
|
||||
main_file = re.sub(r'(?<!\\)%.*', '', main_file) # 使用正则表达式查找半行注释, 并替换为空字符串
|
||||
return main_file
|
||||
|
||||
def find_tex_file_ignore_case(fp):
|
||||
dir_name = os.path.dirname(fp)
|
||||
base_name = os.path.basename(fp)
|
||||
if not base_name.endswith('.tex'): base_name+='.tex'
|
||||
if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
|
||||
# go case in-sensitive
|
||||
import glob
|
||||
for f in glob.glob(dir_name+'/*.tex'):
|
||||
base_name_s = os.path.basename(fp)
|
||||
if base_name_s.lower() == base_name.lower(): return f
|
||||
return None
|
||||
|
||||
def merge_tex_files_(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recrusively
|
||||
"""
|
||||
main_file = rm_comments(main_file)
|
||||
for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
|
||||
f = s.group(1)
|
||||
fp = os.path.join(project_foler, f)
|
||||
fp = find_tex_file_ignore_case(fp)
|
||||
if fp:
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
|
||||
else:
|
||||
raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
|
||||
c = merge_tex_files_(project_foler, c, mode)
|
||||
main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
|
||||
return main_file
|
||||
|
||||
def merge_tex_files(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recrusively
|
||||
P.S. 顺便把CTEX塞进去以支持中文
|
||||
P.S. 顺便把Latex的注释去除
|
||||
"""
|
||||
main_file = merge_tex_files_(project_foler, main_file, mode)
|
||||
main_file = rm_comments(main_file)
|
||||
|
||||
if mode == 'translate_zh':
|
||||
# find paper documentclass
|
||||
pattern = re.compile(r'\\documentclass.*\n')
|
||||
match = pattern.search(main_file)
|
||||
assert match is not None, "Cannot find documentclass statement!"
|
||||
position = match.end()
|
||||
add_ctex = '\\usepackage{ctex}\n'
|
||||
add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
|
||||
main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
|
||||
# fontset=windows
|
||||
import platform
|
||||
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_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
|
||||
pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
|
||||
match_opt1 = pattern_opt1.search(main_file)
|
||||
match_opt2 = pattern_opt2.search(main_file)
|
||||
assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
|
||||
return main_file
|
||||
|
||||
|
||||
"""
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
Post process
|
||||
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
||||
"""
|
||||
def mod_inbraket(match):
|
||||
"""
|
||||
为啥chatgpt会把cite里面的逗号换成中文逗号呀
|
||||
"""
|
||||
# get the matched string
|
||||
cmd = match.group(1)
|
||||
str_to_modify = match.group(2)
|
||||
# modify the matched string
|
||||
str_to_modify = str_to_modify.replace('：', ':') # 前面是中文冒号，后面是英文冒号
|
||||
str_to_modify = str_to_modify.replace('，', ',') # 前面是中文逗号，后面是英文逗号
|
||||
# str_to_modify = 'BOOM'
|
||||
return "\\" + cmd + "{" + str_to_modify + "}"
|
||||
|
||||
def fix_content(final_tex, node_string):
|
||||
"""
|
||||
Fix common GPT errors to increase success rate
|
||||
"""
|
||||
final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
|
||||
final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
|
||||
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('\_'):
|
||||
# walk and replace any _ without \
|
||||
final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
|
||||
|
||||
def compute_brace_level(string):
|
||||
# this function count the number of { and }
|
||||
brace_level = 0
|
||||
for c in string:
|
||||
if c == "{": brace_level += 1
|
||||
elif c == "}": brace_level -= 1
|
||||
return brace_level
|
||||
def join_most(tex_t, tex_o):
|
||||
# this function join translated string and original string when something goes wrong
|
||||
p_t = 0
|
||||
p_o = 0
|
||||
def find_next(string, chars, begin):
|
||||
p = begin
|
||||
while p < len(string):
|
||||
if string[p] in chars: return p, string[p]
|
||||
p += 1
|
||||
return None, None
|
||||
while True:
|
||||
res1, char = find_next(tex_o, ['{','}'], p_o)
|
||||
if res1 is None: break
|
||||
res2, char = find_next(tex_t, [char], p_t)
|
||||
if res2 is None: break
|
||||
p_o = res1 + 1
|
||||
p_t = res2 + 1
|
||||
return tex_t[:p_t] + tex_o[p_o:]
|
||||
|
||||
if compute_brace_level(final_tex) != compute_brace_level(node_string):
|
||||
# 出问题了，还原部分原文，保证括号正确
|
||||
final_tex = join_most(final_tex, node_string)
|
||||
return final_tex
|
||||
|
||||
def compile_latex_with_timeout(command, cwd, timeout=60):
|
||||
import subprocess
|
||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
|
||||
try:
|
||||
stdout, stderr = process.communicate(timeout=timeout)
|
||||
except subprocess.TimeoutExpired:
|
||||
process.kill()
|
||||
stdout, stderr = process.communicate()
|
||||
print("Process timed out!")
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
|
||||
def merge_pdfs(pdf1_path, pdf2_path, output_path):
|
||||
import PyPDF2
|
||||
Percent = 0.8
|
||||
# Open the first PDF file
|
||||
with open(pdf1_path, 'rb') as pdf1_file:
|
||||
pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
|
||||
# Open the second PDF file
|
||||
with open(pdf2_path, 'rb') as pdf2_file:
|
||||
pdf2_reader = PyPDF2.PdfFileReader(pdf2_file)
|
||||
# Create a new PDF file to store the merged pages
|
||||
output_writer = PyPDF2.PdfFileWriter()
|
||||
# Determine the number of pages in each PDF file
|
||||
num_pages = max(pdf1_reader.numPages, pdf2_reader.numPages)
|
||||
# Merge the pages from the two PDF files
|
||||
for page_num in range(num_pages):
|
||||
# Add the page from the first PDF file
|
||||
if page_num < pdf1_reader.numPages:
|
||||
page1 = pdf1_reader.getPage(page_num)
|
||||
else:
|
||||
page1 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
|
||||
# Add the page from the second PDF file
|
||||
if page_num < pdf2_reader.numPages:
|
||||
page2 = pdf2_reader.getPage(page_num)
|
||||
else:
|
||||
page2 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
|
||||
# Create a new empty page with double width
|
||||
new_page = PyPDF2.PageObject.createBlankPage(
|
||||
width = int(int(page1.mediaBox.getWidth()) + int(page2.mediaBox.getWidth()) * Percent),
|
||||
height = max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight())
|
||||
)
|
||||
new_page.mergeTranslatedPage(page1, 0, 0)
|
||||
new_page.mergeTranslatedPage(page2, int(int(page1.mediaBox.getWidth())-int(page2.mediaBox.getWidth())* (1-Percent)), 0)
|
||||
output_writer.addPage(new_page)
|
||||
# Save the merged PDF file
|
||||
with open(output_path, 'wb') as output_file:
|
||||
output_writer.write(output_file)
|
||||
@ -1,87 +1,70 @@
|
||||
from toolbox import CatchException, update_ui, gen_time_str
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import input_clipping
|
||||
import copy, json
|
||||
|
||||
|
||||
prompt = """
|
||||
I have to achieve some functionalities by calling one of the functions below.
|
||||
Your job is to find the correct funtion to use to satisfy my requirement,
|
||||
and then write python code to call this function with correct parameters.
|
||||
|
||||
These are functions you are allowed to choose from:
|
||||
1.
|
||||
功能描述: 总结音视频内容
|
||||
调用函数: ConcludeAudioContent(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: 音频文件的路径
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
2.
|
||||
功能描述: 将每次对话记录写入Markdown格式的文件中
|
||||
调用函数: WriteMarkdown()
|
||||
3.
|
||||
功能描述: 将指定目录下的PDF文件从英文翻译成中文
|
||||
调用函数: BatchTranslatePDFDocuments_MultiThreaded(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: PDF文件所在的路径
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
4.
|
||||
功能描述: 根据文本使用GPT模型生成相应的图像
|
||||
调用函数: ImageGeneration(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: 图像生成所用到的提示文本
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
5.
|
||||
功能描述: 对输入的word文档进行摘要生成
|
||||
调用函数: SummarizingWordDocuments(input_path, output_path)
|
||||
参数说明:
|
||||
input_path: 待处理的word文档路径
|
||||
output_path: 摘要生成后的文档路径
|
||||
|
||||
|
||||
You should always anwser with following format:
|
||||
----------------
|
||||
Code:
|
||||
```
|
||||
class AutoAcademic(object):
|
||||
def __init__(self):
|
||||
self.selected_function = "FILL_CORRECT_FUNCTION_HERE" # e.g., "GenerateImage"
|
||||
self.txt = "FILL_MAIN_PARAMETER_HERE" # e.g., "荷叶上的蜻蜓"
|
||||
self.llm_kwargs = None
|
||||
```
|
||||
Explanation:
|
||||
只有GenerateImage和生成图像相关, 因此选择GenerateImage函数。
|
||||
----------------
|
||||
|
||||
Now, this is my requirement:
|
||||
|
||||
"""
|
||||
def get_fn_lib():
|
||||
return {
|
||||
"BatchTranslatePDFDocuments_MultiThreaded": ("crazy_functions.批量翻译PDF文档_多线程", "批量翻译PDF文档"),
|
||||
"SummarizingWordDocuments": ("crazy_functions.总结word文档", "总结word文档"),
|
||||
"ImageGeneration": ("crazy_functions.图片生成", "图片生成"),
|
||||
"TranslateMarkdownFromEnglishToChinese": ("crazy_functions.批量Markdown翻译", "Markdown中译英"),
|
||||
"SummaryAudioVideo": ("crazy_functions.总结音视频", "总结音视频"),
|
||||
"BatchTranslatePDFDocuments_MultiThreaded": {
|
||||
"module": "crazy_functions.批量翻译PDF文档_多线程",
|
||||
"function": "批量翻译PDF文档",
|
||||
"description": "Translate PDF Documents",
|
||||
"arg_1_description": "A path containing pdf files.",
|
||||
},
|
||||
"SummarizingWordDocuments": {
|
||||
"module": "crazy_functions.总结word文档",
|
||||
"function": "总结word文档",
|
||||
"description": "Summarize Word Documents",
|
||||
"arg_1_description": "A path containing Word files.",
|
||||
},
|
||||
"ImageGeneration": {
|
||||
"module": "crazy_functions.图片生成",
|
||||
"function": "图片生成",
|
||||
"description": "Generate a image that satisfies some description.",
|
||||
"arg_1_description": "Descriptions about the image to be generated.",
|
||||
},
|
||||
"TranslateMarkdownFromEnglishToChinese": {
|
||||
"module": "crazy_functions.批量Markdown翻译",
|
||||
"function": "Markdown中译英",
|
||||
"description": "Translate Markdown Documents from English to Chinese.",
|
||||
"arg_1_description": "A path containing Markdown files.",
|
||||
},
|
||||
"SummaryAudioVideo": {
|
||||
"module": "crazy_functions.总结音视频",
|
||||
"function": "总结音视频",
|
||||
"description": "Get text from a piece of audio and summarize this audio.",
|
||||
"arg_1_description": "A path containing audio files.",
|
||||
},
|
||||
}
|
||||
|
||||
functions = [
|
||||
{
|
||||
"name": k,
|
||||
"description": v['description'],
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"plugin_arg_1": {
|
||||
"type": "string",
|
||||
"description": v['arg_1_description'],
|
||||
},
|
||||
},
|
||||
"required": ["plugin_arg_1"],
|
||||
},
|
||||
} for k, v in get_fn_lib().items()
|
||||
]
|
||||
|
||||
def inspect_dependency(chatbot, history):
|
||||
return True
|
||||
|
||||
def eval_code(code, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
import subprocess, sys, os, shutil, importlib
|
||||
|
||||
with open('gpt_log/void_terminal_runtime.py', 'w', encoding='utf8') as f:
|
||||
f.write(code)
|
||||
|
||||
import importlib
|
||||
try:
|
||||
AutoAcademic = getattr(importlib.import_module('gpt_log.void_terminal_runtime', 'AutoAcademic'), 'AutoAcademic')
|
||||
# importlib.reload(AutoAcademic)
|
||||
auto_dict = AutoAcademic()
|
||||
selected_function = auto_dict.selected_function
|
||||
txt = auto_dict.txt
|
||||
fp, fn = get_fn_lib()[selected_function]
|
||||
tmp = get_fn_lib()[code['name']]
|
||||
fp, fn = tmp['module'], tmp['function']
|
||||
fn_plugin = getattr(importlib.import_module(fp, fn), fn)
|
||||
yield from fn_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
arg = json.loads(code['arguments'])['plugin_arg_1']
|
||||
yield from fn_plugin(arg, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
chatbot.append(["执行错误", f"\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
@ -110,22 +93,27 @@ def 终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_
|
||||
history = []
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append(["函数插件功能？", "根据自然语言执行插件命令, 作者: binary-husky, 插件初始化中 ..."])
|
||||
chatbot.append(["虚空终端插件的功能？", "根据自然语言的描述, 执行任意插件的命令."])
|
||||
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
|
||||
# dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
|
||||
# if not dep_ok: return
|
||||
|
||||
# 输入
|
||||
i_say = prompt + txt
|
||||
i_say = txt
|
||||
# 开始
|
||||
llm_kwargs_function_call = copy.deepcopy(llm_kwargs)
|
||||
llm_kwargs_function_call['llm_model'] = 'gpt-call-fn' # 修改调用函数
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=txt,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
|
||||
sys_prompt=""
|
||||
llm_kwargs=llm_kwargs_function_call, chatbot=chatbot, history=[],
|
||||
sys_prompt=functions
|
||||
)
|
||||
|
||||
# 将代码转为动画
|
||||
code = get_code_block(gpt_say)
|
||||
yield from eval_code(code, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
res = json.loads(gpt_say)['choices'][0]
|
||||
if res['finish_reason'] == 'function_call':
|
||||
code = json.loads(gpt_say)['choices'][0]
|
||||
yield from eval_code(code['message']['function_call'], llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
else:
|
||||
chatbot.append(["无法调用相关功能", res])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
|
||||
213
crazy_functions/虚空终端CodeInterpreter.py
Normal file
213
crazy_functions/虚空终端CodeInterpreter.py
Normal file
@ -0,0 +1,213 @@
|
||||
from collections.abc import Callable, Iterable, Mapping
|
||||
from typing import Any
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, promote_file_to_downloadzone, clear_file_downloadzone
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from .crazy_utils import input_clipping, try_install_deps
|
||||
from multiprocessing import Process, Pipe
|
||||
import os
|
||||
|
||||
templete = """
|
||||
```python
|
||||
import ... # Put dependencies here, e.g. import numpy as np
|
||||
|
||||
class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
|
||||
|
||||
def run(self, path): # The name of the function must be `run`, it takes only a positional argument.
|
||||
# rewrite the function you have just written here
|
||||
...
|
||||
return generated_file_path
|
||||
```
|
||||
"""
|
||||
|
||||
def inspect_dependency(chatbot, history):
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return True
|
||||
|
||||
def get_code_block(reply):
|
||||
import re
|
||||
pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
|
||||
matches = re.findall(pattern, reply) # find all code blocks in text
|
||||
if len(matches) == 1:
|
||||
return matches[0].strip('python') # code block
|
||||
for match in matches:
|
||||
if 'class TerminalFunction' in match:
|
||||
return match.strip('python') # code block
|
||||
raise RuntimeError("GPT is not generating proper code.")
|
||||
|
||||
def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
# 输入
|
||||
prompt_compose = [
|
||||
f'Your job:\n'
|
||||
f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
|
||||
f"2. You should write this function to perform following task: " + txt + "\n",
|
||||
f"3. Wrap the output python function with markdown codeblock."
|
||||
]
|
||||
i_say = "".join(prompt_compose)
|
||||
demo = []
|
||||
|
||||
# 第一步
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# 第二步
|
||||
prompt_compose = [
|
||||
"If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
|
||||
templete
|
||||
]
|
||||
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt= r"You are a programmer."
|
||||
)
|
||||
code_to_return = gpt_say
|
||||
history.extend([i_say, gpt_say])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
# # 第三步
|
||||
# i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
|
||||
# i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
# # # 第三步
|
||||
# i_say = "Show me how to use `pip` to install packages to run the code above. "
|
||||
# i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
|
||||
# installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
# inputs=i_say, inputs_show_user=i_say,
|
||||
# llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
# sys_prompt= r"You are a programmer."
|
||||
# )
|
||||
installation_advance = ""
|
||||
|
||||
return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
|
||||
|
||||
def make_module(code):
|
||||
module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
|
||||
with open(f'gpt_log/{module_file}.py', 'w', encoding='utf8') as f:
|
||||
f.write(code)
|
||||
|
||||
def get_class_name(class_string):
|
||||
import re
|
||||
# Use regex to extract the class name
|
||||
class_name = re.search(r'class (\w+)\(', class_string).group(1)
|
||||
return class_name
|
||||
|
||||
class_name = get_class_name(code)
|
||||
return f"gpt_log.{module_file}->{class_name}"
|
||||
|
||||
def init_module_instance(module):
|
||||
import importlib
|
||||
module_, class_ = module.split('->')
|
||||
init_f = getattr(importlib.import_module(module_), class_)
|
||||
return init_f()
|
||||
|
||||
def for_immediate_show_off_when_possible(file_type, fp, chatbot):
|
||||
if file_type in ['png', 'jpg']:
|
||||
image_path = os.path.abspath(fp)
|
||||
chatbot.append(['这是一张图片, 展示如下:',
|
||||
f'本地文件地址: <br/>`{image_path}`<br/>'+
|
||||
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
|
||||
])
|
||||
return chatbot
|
||||
|
||||
def subprocess_worker(instance, file_path, return_dict):
|
||||
return_dict['result'] = instance.run(file_path)
|
||||
|
||||
@CatchException
|
||||
def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
"""
|
||||
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
|
||||
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行
|
||||
plugin_kwargs 插件模型的参数，暂时没有用武之地
|
||||
chatbot 聊天显示框的句柄，用于显示给用户
|
||||
history 聊天历史，前情提要
|
||||
system_prompt 给gpt的静默提醒
|
||||
web_port 当前软件运行的端口号
|
||||
"""
|
||||
# 清空历史，以免输入溢出
|
||||
history = []; clear_file_downloadzone(chatbot)
|
||||
|
||||
# 基本信息：功能、贡献者
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 作者: binary-husky, 插件初始化中 ..."
|
||||
])
|
||||
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
|
||||
dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
|
||||
if not dep_ok: return
|
||||
|
||||
# 读取文件
|
||||
if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
|
||||
recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
|
||||
file_path = recently_uploaded_files[-1]
|
||||
file_type = file_path.split('.')[-1]
|
||||
|
||||
# 粗心检查
|
||||
if 'private_upload' in txt:
|
||||
chatbot.append([
|
||||
"...",
|
||||
f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
|
||||
])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 开始干正事
|
||||
for j in range(5): # 最多重试5次
|
||||
try:
|
||||
code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
|
||||
yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
|
||||
code = get_code_block(code)
|
||||
res = make_module(code)
|
||||
instance = init_module_instance(res)
|
||||
break
|
||||
except Exception as e:
|
||||
chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 代码生成结束, 开始执行
|
||||
try:
|
||||
import multiprocessing
|
||||
manager = multiprocessing.Manager()
|
||||
return_dict = manager.dict()
|
||||
|
||||
p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
|
||||
# only has 10 seconds to run
|
||||
p.start(); p.join(timeout=10)
|
||||
if p.is_alive(): p.terminate(); p.join()
|
||||
p.close()
|
||||
res = return_dict['result']
|
||||
# res = instance.run(file_path)
|
||||
except Exception as e:
|
||||
chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
# chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# 顺利完成，收尾
|
||||
res = str(res)
|
||||
if os.path.exists(res):
|
||||
chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
|
||||
new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
|
||||
chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
else:
|
||||
chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
|
||||
|
||||
"""
|
||||
测试：
|
||||
裁剪图像，保留下半部分
|
||||
交换图像的蓝色通道和红色通道
|
||||
将图像转为灰度图像
|
||||
将csv文件转excel表格
|
||||
"""
|
||||
137
crazy_functions/解析项目源代码炫酷版.py
Normal file
137
crazy_functions/解析项目源代码炫酷版.py
Normal file
@ -0,0 +1,137 @@
|
||||
from toolbox import update_ui
|
||||
from toolbox import CatchException, report_execption, write_results_to_file
|
||||
from toolbox import objdump, objload
|
||||
from .crazy_utils import input_clipping
|
||||
|
||||
class ThreeJSPlot():
|
||||
def __init__(self) -> None:
|
||||
self.files = None
|
||||
|
||||
def read_files(self, files):
|
||||
self.files = files
|
||||
|
||||
def launch_render_interface(self):
|
||||
from vhmap.mcom import mcom
|
||||
self.visual_bridge = mcom()
|
||||
|
||||
|
||||
|
||||
def 解析源代码炫酷版(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
|
||||
import os, copy
|
||||
from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
msg = '正常'
|
||||
summary_batch_isolation = True
|
||||
inputs_array = []
|
||||
inputs_show_user_array = []
|
||||
history_array = []
|
||||
sys_prompt_array = []
|
||||
report_part_1 = []
|
||||
|
||||
assert len(file_manifest) <= 512, "源文件太多（超过512个）, 请缩减输入文件的数量。或者，您也可以选择删除此行警告，并修改代码拆分file_manifest列表，从而实现分批次处理。"
|
||||
############################## <第一步，逐个文件分析，多线程> ##################################
|
||||
for index, fp in enumerate(file_manifest):
|
||||
# 读取文件
|
||||
with open(fp, 'r', encoding='utf-8', errors='replace') as f:
|
||||
file_content = f.read()
|
||||
prefix = "接下来请你逐文件分析下面的工程" if index==0 else ""
|
||||
i_say = prefix + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)}，文件代码是 ```{file_content}```'
|
||||
i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {os.path.abspath(fp)}'
|
||||
# 装载请求内容
|
||||
inputs_array.append(i_say)
|
||||
inputs_show_user_array.append(i_say_show_user)
|
||||
history_array.append([])
|
||||
sys_prompt_array.append("你是一个程序架构分析师，正在分析一个源代码项目。你的回答必须简单明了。")
|
||||
|
||||
def callback_when_intel_update(gpt_reply_array):
|
||||
objdump((gpt_reply_array, file_manifest))
|
||||
return
|
||||
|
||||
|
||||
# 文件读取完成，对每一个源代码文件，生成一个请求线程，发送到chatgpt进行分析
|
||||
gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
inputs_array = inputs_array,
|
||||
inputs_show_user_array = inputs_show_user_array,
|
||||
history_array = history_array,
|
||||
sys_prompt_array = sys_prompt_array,
|
||||
llm_kwargs = llm_kwargs,
|
||||
chatbot = chatbot,
|
||||
show_user_at_complete = True,
|
||||
callback_fn=callback_when_intel_update,
|
||||
)
|
||||
|
||||
# 全部文件解析完成，结果写入文件，准备对工程源代码进行汇总分析
|
||||
report_part_1 = copy.deepcopy(gpt_response_collection)
|
||||
history_to_return = report_part_1
|
||||
res = write_results_to_file(report_part_1)
|
||||
chatbot.append(("完成？", "逐个文件分析已完成。" + res + "\n\n正在开始汇总。"))
|
||||
yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
|
||||
############################## <第二步，综合，单线程，分组+迭代处理> ##################################
|
||||
|
||||
|
||||
############################## <END> ##################################
|
||||
history_to_return.extend([])
|
||||
res = write_results_to_file(history_to_return)
|
||||
chatbot.append(("完成了吗？", res))
|
||||
yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析一个Python项目炫酷版(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
history = [] # 清空历史，以免输入溢出
|
||||
import glob, os
|
||||
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
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.py', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
yield from 解析源代码炫酷版(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
|
||||
|
||||
|
||||
@CatchException
|
||||
def 解析任意code项目炫酷版(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
txt_pattern = plugin_kwargs.get("advanced_arg")
|
||||
txt_pattern = txt_pattern.replace("，", ",")
|
||||
# 将要匹配的模式(例如: *.c, *.cpp, *.py, config.toml)
|
||||
pattern_include = [_.lstrip(" ,").rstrip(" ,") for _ in txt_pattern.split(",") if _ != "" and not _.strip().startswith("^")]
|
||||
if not pattern_include: pattern_include = ["*"] # 不输入即全部匹配
|
||||
# 将要忽略匹配的文件后缀(例如: ^*.c, ^*.cpp, ^*.py)
|
||||
pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
|
||||
pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
|
||||
# 将要忽略匹配的文件名(例如: ^README.md)
|
||||
pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
|
||||
# 生成正则表达式
|
||||
pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
|
||||
pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
|
||||
|
||||
history.clear()
|
||||
import glob, os, re
|
||||
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
|
||||
# 若上传压缩文件, 先寻找到解压的文件夹路径, 从而避免解析压缩文件
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir)>0 and maybe_dir[0].endswith('.extract'):
|
||||
extract_folder_path = maybe_dir[0]
|
||||
else:
|
||||
extract_folder_path = project_folder
|
||||
# 按输入的匹配模式寻找上传的非压缩文件和已解压的文件
|
||||
file_manifest = [f for pattern in pattern_include for f in glob.glob(f'{extract_folder_path}/**/{pattern}', recursive=True) if "" != extract_folder_path and \
|
||||
os.path.isfile(f) and (not re.search(pattern_except, f) or pattern.endswith('.' + re.search(pattern_except, f).group().split('.')[-1]))]
|
||||
if len(file_manifest) == 0:
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
8
main.py
8
main.py
@ -22,8 +22,10 @@ def main():
|
||||
# 问询记录, python 版本建议3.9+（越新越好）
|
||||
import logging, uuid
|
||||
os.makedirs("gpt_log", exist_ok=True)
|
||||
try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8")
|
||||
except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO)
|
||||
try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
|
||||
# Disable logging output from the 'httpx' logger
|
||||
logging.getLogger("httpx").setLevel(logging.WARNING)
|
||||
print("所有问询记录将自动保存在本地目录./gpt_log/chat_secrets.log, 请注意自我隐私保护哦！")
|
||||
|
||||
# 一些普通功能模块
|
||||
@ -158,7 +160,7 @@ def main():
|
||||
click_handle = functional[k]["Button"].click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(k)], outputs=output_combo)
|
||||
cancel_handles.append(click_handle)
|
||||
# 文件上传区，接收文件后与chatbot的互动
|
||||
file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes], [chatbot, txt, txt2])
|
||||
file_upload.upload(on_file_uploaded, [cookies, file_upload, chatbot, txt, txt2, checkboxes], [cookies, chatbot, txt, txt2])
|
||||
# 函数插件-固定按钮区
|
||||
for k in crazy_fns:
|
||||
if not crazy_fns[k].get("AsButton", True): continue
|
||||
|
||||
@ -248,7 +248,6 @@ if "moss" in AVAIL_LLM_MODELS:
|
||||
if "stack-claude" in AVAIL_LLM_MODELS:
|
||||
from .bridge_stackclaude import predict_no_ui_long_connection as claude_noui
|
||||
from .bridge_stackclaude import predict as claude_ui
|
||||
# claude
|
||||
model_info.update({
|
||||
"stack-claude": {
|
||||
"fn_with_ui": claude_ui,
|
||||
@ -263,7 +262,6 @@ if "newbing-free" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
|
||||
from .bridge_newbingfree import predict as newbingfree_ui
|
||||
# claude
|
||||
model_info.update({
|
||||
"newbing-free": {
|
||||
"fn_with_ui": newbingfree_ui,
|
||||
@ -280,7 +278,6 @@ if "newbing" in AVAIL_LLM_MODELS: # same with newbing-free
|
||||
try:
|
||||
from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
|
||||
from .bridge_newbingfree import predict as newbingfree_ui
|
||||
# claude
|
||||
model_info.update({
|
||||
"newbing": {
|
||||
"fn_with_ui": newbingfree_ui,
|
||||
@ -297,7 +294,6 @@ if "chatglmft" in AVAIL_LLM_MODELS: # same with newbing-free
|
||||
try:
|
||||
from .bridge_chatglmft import predict_no_ui_long_connection as chatglmft_noui
|
||||
from .bridge_chatglmft import predict as chatglmft_ui
|
||||
# claude
|
||||
model_info.update({
|
||||
"chatglmft": {
|
||||
"fn_with_ui": chatglmft_ui,
|
||||
@ -310,7 +306,22 @@ if "chatglmft" in AVAIL_LLM_MODELS: # same with newbing-free
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
|
||||
if "internlm" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
|
||||
from .bridge_internlm import predict as internlm_ui
|
||||
model_info.update({
|
||||
"internlm": {
|
||||
"fn_with_ui": internlm_ui,
|
||||
"fn_without_ui": internlm_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
})
|
||||
except:
|
||||
print(trimmed_format_exc())
|
||||
|
||||
def LLM_CATCH_EXCEPTION(f):
|
||||
"""
|
||||
|
||||
@ -174,9 +174,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
# 非OpenAI官方接口的出现这样的报错，OpenAI和API2D不会走这里
|
||||
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.decode())}")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk.decode()) # 刷新界面
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
|
||||
return
|
||||
|
||||
# print(chunk.decode()[6:])
|
||||
@ -187,7 +188,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
if chunk:
|
||||
try:
|
||||
chunk_decoded = chunk.decode()
|
||||
# 前者API2D的
|
||||
# 前者是API2D的结束条件，后者是OPENAI的结束条件
|
||||
if ('data: [DONE]' in chunk_decoded) or (len(json.loads(chunk_decoded[6:])['choices'][0]["delta"]) == 0):
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
logging.info(f'[response] {gpt_replying_buffer}')
|
||||
@ -200,13 +201,18 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
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)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
print(error_msg)
|
||||
return
|
||||
|
||||
def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
|
||||
from .bridge_all import model_info
|
||||
openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
|
||||
if "reduce the length" in error_msg:
|
||||
if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
|
||||
@ -232,8 +238,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
from toolbox import regular_txt_to_markdown
|
||||
tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
return
|
||||
return chatbot, history
|
||||
|
||||
def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
|
||||
315
request_llm/bridge_internlm.py
Normal file
315
request_llm/bridge_internlm.py
Normal file
@ -0,0 +1,315 @@
|
||||
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
import time
|
||||
import threading
|
||||
import importlib
|
||||
from toolbox import update_ui, get_conf, Singleton
|
||||
from multiprocessing import Process, Pipe
|
||||
|
||||
model_name = "InternLM"
|
||||
cmd_to_install = "`pip install ???`"
|
||||
load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
|
||||
def try_to_import_special_deps():
|
||||
import sentencepiece
|
||||
|
||||
user_prompt = "<|User|>:{user}<eoh>\n"
|
||||
robot_prompt = "<|Bot|>:{robot}<eoa>\n"
|
||||
cur_query_prompt = "<|User|>:{user}<eoh>\n<|Bot|>:"
|
||||
|
||||
|
||||
def combine_history(prompt, hist):
|
||||
messages = hist
|
||||
total_prompt = ""
|
||||
for message in messages:
|
||||
cur_content = message
|
||||
cur_prompt = user_prompt.replace("{user}", cur_content[0])
|
||||
total_prompt += cur_prompt
|
||||
cur_prompt = robot_prompt.replace("{robot}", cur_content[1])
|
||||
total_prompt += cur_prompt
|
||||
total_prompt = total_prompt + cur_query_prompt.replace("{user}", prompt)
|
||||
return total_prompt
|
||||
|
||||
|
||||
@Singleton
|
||||
class GetInternlmHandle(Process):
|
||||
def __init__(self):
|
||||
# ⭐主进程执行
|
||||
super().__init__(daemon=True)
|
||||
self.parent, self.child = Pipe()
|
||||
self._model = None
|
||||
self._tokenizer = None
|
||||
self.info = ""
|
||||
self.success = True
|
||||
self.check_dependency()
|
||||
self.start()
|
||||
self.threadLock = threading.Lock()
|
||||
|
||||
def ready(self):
|
||||
# ⭐主进程执行
|
||||
return self._model is not None
|
||||
|
||||
def load_model_and_tokenizer(self):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
device, = get_conf('LOCAL_MODEL_DEVICE')
|
||||
if self._model is None:
|
||||
tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
|
||||
if device=='cpu':
|
||||
model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16)
|
||||
else:
|
||||
model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16).cuda()
|
||||
|
||||
model = model.eval()
|
||||
return model, tokenizer
|
||||
|
||||
def llm_stream_generator(self, **kwargs):
|
||||
import torch
|
||||
import logging
|
||||
import copy
|
||||
import warnings
|
||||
import torch.nn as nn
|
||||
from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig
|
||||
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
def adaptor():
|
||||
model = self._model
|
||||
tokenizer = self._tokenizer
|
||||
prompt = kwargs['query']
|
||||
max_length = kwargs['max_length']
|
||||
top_p = kwargs['top_p']
|
||||
temperature = kwargs['temperature']
|
||||
history = kwargs['history']
|
||||
real_prompt = combine_history(prompt, history)
|
||||
return model, tokenizer, real_prompt, max_length, top_p, temperature
|
||||
|
||||
model, tokenizer, prompt, max_length, top_p, temperature = adaptor()
|
||||
prefix_allowed_tokens_fn = None
|
||||
logits_processor = None
|
||||
stopping_criteria = None
|
||||
additional_eos_token_id = 103028
|
||||
generation_config = None
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
# 🏃♂️🏃♂️🏃♂️ https://github.com/InternLM/InternLM/blob/efbf5335709a8c8faeac6eaf07193973ff1d56a1/web_demo.py#L25
|
||||
|
||||
inputs = tokenizer([prompt], padding=True, return_tensors="pt")
|
||||
input_length = len(inputs["input_ids"][0])
|
||||
for k, v in inputs.items():
|
||||
inputs[k] = v.cuda()
|
||||
input_ids = inputs["input_ids"]
|
||||
batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
|
||||
if generation_config is None:
|
||||
generation_config = model.generation_config
|
||||
generation_config = copy.deepcopy(generation_config)
|
||||
model_kwargs = generation_config.update(**kwargs)
|
||||
bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
|
||||
if isinstance(eos_token_id, int):
|
||||
eos_token_id = [eos_token_id]
|
||||
if additional_eos_token_id is not None:
|
||||
eos_token_id.append(additional_eos_token_id)
|
||||
has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
|
||||
if has_default_max_length and generation_config.max_new_tokens is None:
|
||||
warnings.warn(
|
||||
f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
|
||||
"This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
|
||||
" recommend using `max_new_tokens` to control the maximum length of the generation.",
|
||||
UserWarning,
|
||||
)
|
||||
elif generation_config.max_new_tokens is not None:
|
||||
generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
|
||||
if not has_default_max_length:
|
||||
logging.warn(
|
||||
f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
|
||||
f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
|
||||
"Please refer to the documentation for more information. "
|
||||
"(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
|
||||
UserWarning,
|
||||
)
|
||||
|
||||
if input_ids_seq_length >= generation_config.max_length:
|
||||
input_ids_string = "input_ids"
|
||||
logging.warning(
|
||||
f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
|
||||
f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
|
||||
" increasing `max_new_tokens`."
|
||||
)
|
||||
|
||||
# 2. Set generation parameters if not already defined
|
||||
logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
|
||||
stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
|
||||
|
||||
logits_processor = model._get_logits_processor(
|
||||
generation_config=generation_config,
|
||||
input_ids_seq_length=input_ids_seq_length,
|
||||
encoder_input_ids=input_ids,
|
||||
prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
|
||||
logits_processor=logits_processor,
|
||||
)
|
||||
|
||||
stopping_criteria = model._get_stopping_criteria(
|
||||
generation_config=generation_config, stopping_criteria=stopping_criteria
|
||||
)
|
||||
logits_warper = model._get_logits_warper(generation_config)
|
||||
|
||||
unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
|
||||
scores = None
|
||||
while True:
|
||||
model_inputs = model.prepare_inputs_for_generation(input_ids, **model_kwargs)
|
||||
# forward pass to get next token
|
||||
outputs = model(
|
||||
**model_inputs,
|
||||
return_dict=True,
|
||||
output_attentions=False,
|
||||
output_hidden_states=False,
|
||||
)
|
||||
|
||||
next_token_logits = outputs.logits[:, -1, :]
|
||||
|
||||
# pre-process distribution
|
||||
next_token_scores = logits_processor(input_ids, next_token_logits)
|
||||
next_token_scores = logits_warper(input_ids, next_token_scores)
|
||||
|
||||
# sample
|
||||
probs = nn.functional.softmax(next_token_scores, dim=-1)
|
||||
if generation_config.do_sample:
|
||||
next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
|
||||
else:
|
||||
next_tokens = torch.argmax(probs, dim=-1)
|
||||
|
||||
# update generated ids, model inputs, and length for next step
|
||||
input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
|
||||
model_kwargs = model._update_model_kwargs_for_generation(
|
||||
outputs, model_kwargs, is_encoder_decoder=False
|
||||
)
|
||||
unfinished_sequences = unfinished_sequences.mul((min(next_tokens != i for i in eos_token_id)).long())
|
||||
|
||||
output_token_ids = input_ids[0].cpu().tolist()
|
||||
output_token_ids = output_token_ids[input_length:]
|
||||
for each_eos_token_id in eos_token_id:
|
||||
if output_token_ids[-1] == each_eos_token_id:
|
||||
output_token_ids = output_token_ids[:-1]
|
||||
response = tokenizer.decode(output_token_ids)
|
||||
|
||||
yield response
|
||||
# stop when each sentence is finished, or if we exceed the maximum length
|
||||
if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
|
||||
return
|
||||
|
||||
|
||||
|
||||
def check_dependency(self):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
try:
|
||||
try_to_import_special_deps()
|
||||
self.info = "依赖检测通过"
|
||||
self.success = True
|
||||
except:
|
||||
self.info = f"缺少{model_name}的依赖，如果要使用{model_name}，除了基础的pip依赖以外，您还需要运行{cmd_to_install}安装{model_name}的依赖。"
|
||||
self.success = False
|
||||
|
||||
def run(self):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
# 第一次运行，加载参数
|
||||
try:
|
||||
self._model, self._tokenizer = self.load_model_and_tokenizer()
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
self.child.send(f'[Local Message] 不能正常加载{model_name}的参数.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
|
||||
raise RuntimeError(f"不能正常加载{model_name}的参数！")
|
||||
|
||||
while True:
|
||||
# 进入任务等待状态
|
||||
kwargs = self.child.recv()
|
||||
# 收到消息，开始请求
|
||||
try:
|
||||
for response_full in self.llm_stream_generator(**kwargs):
|
||||
self.child.send(response_full)
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
self.child.send(f'[Local Message] 调用{model_name}失败.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
|
||||
# 请求处理结束，开始下一个循环
|
||||
self.child.send('[Finish]')
|
||||
|
||||
def stream_chat(self, **kwargs):
|
||||
# ⭐主进程执行
|
||||
self.threadLock.acquire()
|
||||
self.parent.send(kwargs)
|
||||
while True:
|
||||
res = self.parent.recv()
|
||||
if res != '[Finish]':
|
||||
yield res
|
||||
else:
|
||||
break
|
||||
self.threadLock.release()
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
# 🔌💻 GPT-Academic
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llm/bridge_all.py
|
||||
"""
|
||||
_llm_handle = GetInternlmHandle()
|
||||
if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + _llm_handle.info
|
||||
if not _llm_handle.success:
|
||||
error = _llm_handle.info
|
||||
_llm_handle = None
|
||||
raise RuntimeError(error)
|
||||
|
||||
# chatglm 没有 sys_prompt 接口，因此把prompt加入 history
|
||||
history_feedin = []
|
||||
history_feedin.append(["What can I do?", sys_prompt])
|
||||
for i in range(len(history)//2):
|
||||
history_feedin.append([history[2*i], history[2*i+1]] )
|
||||
|
||||
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
|
||||
response = ""
|
||||
for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
|
||||
if len(observe_window) >= 1: observe_window[0] = response
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("程序终止。")
|
||||
return response
|
||||
|
||||
|
||||
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
⭐单线程方法
|
||||
函数的说明请见 request_llm/bridge_all.py
|
||||
"""
|
||||
chatbot.append((inputs, ""))
|
||||
|
||||
_llm_handle = GetInternlmHandle()
|
||||
chatbot[-1] = (inputs, load_message + "\n\n" + _llm_handle.info)
|
||||
yield from update_ui(chatbot=chatbot, history=[])
|
||||
if not _llm_handle.success:
|
||||
_llm_handle = None
|
||||
return
|
||||
|
||||
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"]
|
||||
|
||||
# 处理历史信息
|
||||
history_feedin = []
|
||||
history_feedin.append(["What can I do?", system_prompt] )
|
||||
for i in range(len(history)//2):
|
||||
history_feedin.append([history[2*i], history[2*i+1]] )
|
||||
|
||||
# 开始接收chatglm的回复
|
||||
response = f"[Local Message]: 等待{model_name}响应中 ..."
|
||||
for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
|
||||
chatbot[-1] = (inputs, response)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
# 总结输出
|
||||
if response == f"[Local Message]: 等待{model_name}响应中 ...":
|
||||
response = f"[Local Message]: {model_name}响应异常 ..."
|
||||
history.extend([inputs, response])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@ -447,6 +447,15 @@ class _ChatHub:
|
||||
"""
|
||||
Ask a question to the bot
|
||||
"""
|
||||
req_header = HEADERS
|
||||
if self.cookies is not None:
|
||||
ws_cookies = []
|
||||
for cookie in self.cookies:
|
||||
ws_cookies.append(f"{cookie['name']}={cookie['value']}")
|
||||
req_header.update({
|
||||
'Cookie': ';'.join(ws_cookies),
|
||||
})
|
||||
|
||||
timeout = aiohttp.ClientTimeout(total=30)
|
||||
self.session = aiohttp.ClientSession(timeout=timeout)
|
||||
|
||||
@ -455,7 +464,7 @@ class _ChatHub:
|
||||
# Check if websocket is closed
|
||||
self.wss = await self.session.ws_connect(
|
||||
wss_link,
|
||||
headers=HEADERS,
|
||||
headers=req_header,
|
||||
ssl=ssl_context,
|
||||
proxy=self.proxy,
|
||||
autoping=False,
|
||||
@ -510,7 +519,11 @@ class _ChatHub:
|
||||
resp_txt_no_link = ""
|
||||
while not final:
|
||||
msg = await self.wss.receive()
|
||||
try:
|
||||
objects = msg.data.split(DELIMITER)
|
||||
except :
|
||||
continue
|
||||
|
||||
for obj in objects:
|
||||
if obj is None or not obj:
|
||||
continue
|
||||
|
||||
@ -14,7 +14,8 @@ if __name__ == "__main__":
|
||||
# from request_llm.bridge_moss import predict_no_ui_long_connection
|
||||
# from request_llm.bridge_jittorllms_pangualpha import predict_no_ui_long_connection
|
||||
# from request_llm.bridge_jittorllms_llama import predict_no_ui_long_connection
|
||||
from request_llm.bridge_claude import predict_no_ui_long_connection
|
||||
# from request_llm.bridge_claude import predict_no_ui_long_connection
|
||||
from request_llm.bridge_internlm import predict_no_ui_long_connection
|
||||
|
||||
llm_kwargs = {
|
||||
'max_length': 512,
|
||||
@ -22,45 +23,8 @@ if __name__ == "__main__":
|
||||
'temperature': 1,
|
||||
}
|
||||
|
||||
result = predict_no_ui_long_connection(inputs="你好",
|
||||
result = predict_no_ui_long_connection( inputs="请问什么是质子？",
|
||||
llm_kwargs=llm_kwargs,
|
||||
history=[],
|
||||
history=["你好", "我好！"],
|
||||
sys_prompt="")
|
||||
print('final result:', result)
|
||||
|
||||
|
||||
|
||||
# # print(result)
|
||||
# from multiprocessing import Process, Pipe
|
||||
# class GetGLMHandle(Process):
|
||||
# def __init__(self):
|
||||
# super().__init__(daemon=True)
|
||||
# pass
|
||||
# def run(self):
|
||||
# # 子进程执行
|
||||
# # 第一次运行，加载参数
|
||||
# def validate_path():
|
||||
# import os, sys
|
||||
# dir_name = os.path.dirname(__file__)
|
||||
# root_dir_assume = os.path.abspath(os.path.dirname(__file__) + '/..')
|
||||
# os.chdir(root_dir_assume + '/request_llm/jittorllms')
|
||||
# sys.path.append(root_dir_assume + '/request_llm/jittorllms')
|
||||
# validate_path() # validate path so you can run from base directory
|
||||
# jittorllms_model = None
|
||||
# import types
|
||||
# try:
|
||||
# if jittorllms_model is None:
|
||||
# from models import get_model
|
||||
# # availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
# args_dict = {'model': 'chatrwkv'}
|
||||
# print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
|
||||
# jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
|
||||
# print('done get model')
|
||||
# except:
|
||||
# # self.child.send('[Local Message] Call jittorllms fail 不能正常加载jittorllms的参数。')
|
||||
# raise RuntimeError("不能正常加载jittorllms的参数！")
|
||||
# x = GetGLMHandle()
|
||||
# x.start()
|
||||
|
||||
|
||||
# input()
|
||||
@ -18,3 +18,4 @@ openai
|
||||
numpy
|
||||
arxiv
|
||||
rich
|
||||
pypdf2==2.12.1
|
||||
|
||||
38
toolbox.py
38
toolbox.py
@ -60,6 +60,9 @@ def ArgsGeneralWrapper(f):
|
||||
plugin_kwargs = {
|
||||
"advanced_arg": plugin_advanced_arg,
|
||||
}
|
||||
if "recently_uploaded_files" in cookies:
|
||||
plugin_kwargs.update({"recently_uploaded_files": cookies["recently_uploaded_files"]})
|
||||
|
||||
chatbot_with_cookie = ChatBotWithCookies(cookies)
|
||||
chatbot_with_cookie.write_list(chatbot)
|
||||
if cookies.get('lock_plugin', None) is None:
|
||||
@ -462,6 +465,10 @@ def find_recent_files(directory):
|
||||
|
||||
return recent_files
|
||||
|
||||
def clear_file_downloadzone(chatbot):
|
||||
if chatbot:
|
||||
chatbot._cookies.update({'file_to_promote': []})
|
||||
|
||||
def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
|
||||
# 将文件复制一份到下载区
|
||||
import shutil
|
||||
@ -476,13 +483,14 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
|
||||
if 'file_to_promote' in chatbot._cookies: current = chatbot._cookies['file_to_promote']
|
||||
else: current = []
|
||||
chatbot._cookies.update({'file_to_promote': [new_path] + current})
|
||||
return new_path
|
||||
|
||||
def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
|
||||
def on_file_uploaded(cookies, files, chatbot, txt, txt2, checkboxes):
|
||||
"""
|
||||
当文件被上传时的回调函数
|
||||
"""
|
||||
if len(files) == 0:
|
||||
return chatbot, txt
|
||||
return cookies, chatbot, txt
|
||||
import shutil
|
||||
import os
|
||||
import time
|
||||
@ -512,7 +520,8 @@ def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
|
||||
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, txt2
|
||||
cookies.update({"recently_uploaded_files": moved_files})
|
||||
return cookies, chatbot, txt, txt2
|
||||
|
||||
|
||||
def on_report_generated(cookies, files, chatbot):
|
||||
@ -538,6 +547,10 @@ def load_chat_cookies():
|
||||
return {'api_key': API_KEY, 'llm_model': LLM_MODEL}
|
||||
|
||||
def is_openai_api_key(key):
|
||||
CUSTOM_API_KEY_PATTERN, = get_conf('CUSTOM_API_KEY_PATTERN')
|
||||
if len(CUSTOM_API_KEY_PATTERN) != 0:
|
||||
API_MATCH_ORIGINAL = re.match(CUSTOM_API_KEY_PATTERN, key)
|
||||
else:
|
||||
API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
|
||||
return bool(API_MATCH_ORIGINAL)
|
||||
|
||||
@ -594,7 +607,7 @@ def select_api_key(keys, llm_model):
|
||||
if is_azure_api_key(k): avail_key_list.append(k)
|
||||
|
||||
if len(avail_key_list) == 0:
|
||||
raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure和api2d请求源）")
|
||||
raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure,claude,api2d等请求源）。")
|
||||
|
||||
api_key = random.choice(avail_key_list) # 随机负载均衡
|
||||
return api_key
|
||||
@ -670,12 +683,12 @@ def read_single_conf_with_lru_cache(arg):
|
||||
|
||||
# 在读取API_KEY时，检查一下是不是忘了改config
|
||||
if arg == 'API_KEY':
|
||||
print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和API2D的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,api2d-key3\"")
|
||||
print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和Azure的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,azure-key3\"")
|
||||
print亮蓝(f"[API_KEY] 您既可以在config.py中修改api-key(s)，也可以在问题输入区输入临时的api-key(s)，然后回车键提交后即可生效。")
|
||||
if is_any_api_key(r):
|
||||
print亮绿(f"[API_KEY] 您的 API_KEY 是: {r[:15]}*** API_KEY 导入成功")
|
||||
else:
|
||||
print亮红( "[API_KEY] 正确的 API_KEY 是'sk'开头的51位密钥（OpenAI），或者 'fk'开头的41位密钥，请在config文件中修改API密钥之后再运行。")
|
||||
print亮红( "[API_KEY] 您的 API_KEY 不满足任何一种已知的密钥格式，请在config文件中修改API密钥之后再运行。")
|
||||
if arg == 'proxies':
|
||||
if r is None:
|
||||
print亮红('[PROXY] 网络代理状态：未配置。无代理状态下很可能无法访问OpenAI家族的模型。建议：检查USE_PROXY选项是否修改。')
|
||||
@ -685,6 +698,7 @@ def read_single_conf_with_lru_cache(arg):
|
||||
return r
|
||||
|
||||
|
||||
@lru_cache(maxsize=128)
|
||||
def get_conf(*args):
|
||||
# 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
|
||||
res = []
|
||||
@ -884,3 +898,15 @@ def objload(file='objdump.tmp'):
|
||||
with open(file, 'rb') as f:
|
||||
return pickle.load(f)
|
||||
|
||||
def Singleton(cls):
|
||||
"""
|
||||
一个单实例装饰器
|
||||
"""
|
||||
_instance = {}
|
||||
|
||||
def _singleton(*args, **kargs):
|
||||
if cls not in _instance:
|
||||
_instance[cls] = cls(*args, **kargs)
|
||||
return _instance[cls]
|
||||
|
||||
return _singleton
|
||||
|
||||
Reference in New Issue
Block a user