Spaces:
Sleeping
Sleeping
File size: 19,889 Bytes
0079733 9ca7a90 2c963cc 0666fec 3725122 0666fec 3725122 0079733 24780ee 9bd8511 24780ee 91609d6 24780ee 0666fec 3725122 91609d6 0666fec 91609d6 0666fec 3725122 0666fec 1f6defe 0666fec 24780ee 0666fec ea031ab 0666fec 42d366b 9bd8511 24780ee 5e8eb62 47445fd 9593b0d 0079733 5e8eb62 9593b0d 5e8eb62 9593b0d 5e8eb62 9593b0d 7186d9b 0079733 32f36a6 fedc748 9bd8511 fedc748 0079733 32f36a6 043a9ea 0079733 32f36a6 0079733 32f36a6 d58802a 0079733 d58802a 0079733 32f36a6 77408f7 32f36a6 93c13aa 0079733 93c13aa fedc748 9bd8511 fedc748 93c13aa 0079733 363e455 0079733 93c13aa fedc748 9bd8511 fedc748 93c13aa 0079733 93c13aa fedc748 9bd8511 fedc748 93c13aa 6dd83fb 93c13aa 0079733 93c13aa fedc748 9bd8511 fedc748 7b8de78 9ca7a90 e2770fe 9ca7a90 e2770fe 9ca7a90 e2770fe 9ca7a90 93c13aa e2770fe 0079733 93c13aa 5b9de09 e371b82 5b9de09 0079733 5b9de09 9719306 5b9de09 93c13aa fedc748 9bd8511 fedc748 0079733 93c13aa 0079733 42d366b 93c13aa 42d366b 93c13aa fedc748 9bd8511 fedc748 93c13aa 81741bc 1805f08 81741bc a360cd7 44e77dc a360cd7 44e77dc a098d08 e470ee1 44e77dc a360cd7 e470ee1 a360cd7 44e77dc a098d08 81741bc a098d08 1805f08 0079733 81741bc 0079733 1055fda 81741bc 0079733 81741bc 51bde97 d84c96c 0079733 51bde97 0079733 51bde97 a098d08 51bde97 a098d08 0079733 d84c96c 51bde97 a360cd7 0079733 4c486f2 d84c96c 51bde97 0079733 51bde97 5e8eb62 51bde97 2bf30d8 3725122 9bd8511 7317d79 9bd8511 0079733 1533c4b 2c963cc ac219f4 0079733 2c963cc 0079733 ac219f4 9bd8511 3725122 2c963cc 3eef2d5 0079733 3eef2d5 0079733 3725122 2c963cc 0079733 2bf30d8 2c963cc 2bf30d8 44155bc 0079733 44155bc ab879ca c96a253 0079733 c96a253 e371b82 c96a253 0079733 c96a253 0079733 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 |
import markdown
import importlib
import traceback
import inspect
import re
from latex2mathml.converter import convert as tex2mathml
from functools import wraps, lru_cache
############################### 插件输入输出接驳区 #######################################
class ChatBotWithCookies(list):
def __init__(self, cookie):
self._cookies = cookie
def write_list(self, list):
for t in list:
self.append(t)
def get_list(self):
return [t for t in self]
def get_cookies(self):
return self._cookies
def ArgsGeneralWrapper(f):
"""
装饰器函数,用于重组输入参数,改变输入参数的顺序与结构。
"""
def decorated(cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, *args):
txt_passon = txt
if txt == "" and txt2 != "": txt_passon = txt2
# 引入一个有cookie的chatbot
cookies.update({
'top_p':top_p,
'temperature':temperature,
})
llm_kwargs = {
'api_key': cookies['api_key'],
'llm_model': llm_model,
'top_p':top_p,
'max_length': max_length,
'temperature':temperature,
}
plugin_kwargs = {
# 目前还没有
}
chatbot_with_cookie = ChatBotWithCookies(cookies)
chatbot_with_cookie.write_list(chatbot)
yield from f(txt_passon, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, system_prompt, *args)
return decorated
def update_ui(chatbot, history, msg='正常', **kwargs): # 刷新界面
"""
刷新用户界面
"""
assert isinstance(chatbot, ChatBotWithCookies), "在传递chatbot的过程中不要将其丢弃。必要时,可用clear将其清空,然后用for+append循环重新赋值。"
yield chatbot.get_cookies(), chatbot, history, msg
def CatchException(f):
"""
装饰器函数,捕捉函数f中的异常并封装到一个生成器中返回,并显示到聊天当中。
"""
@wraps(f)
def decorated(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
try:
yield from f(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT)
except Exception as e:
from check_proxy import check_proxy
from toolbox import get_conf
proxies, = get_conf('proxies')
tb_str = '```\n' + traceback.format_exc() + '```'
if chatbot is None or len(chatbot) == 0:
chatbot = [["插件调度异常", "异常原因"]]
chatbot[-1] = (chatbot[-1][0],
f"[Local Message] 实验性函数调用出错: \n\n{tb_str} \n\n当前代理可用性: \n\n{check_proxy(proxies)}")
yield from update_ui(chatbot=chatbot, history=history, msg=f'异常 {e}') # 刷新界面
return decorated
def HotReload(f):
"""
HotReload的装饰器函数,用于实现Python函数插件的热更新。
函数热更新是指在不停止程序运行的情况下,更新函数代码,从而达到实时更新功能。
在装饰器内部,使用wraps(f)来保留函数的元信息,并定义了一个名为decorated的内部函数。
内部函数通过使用importlib模块的reload函数和inspect模块的getmodule函数来重新加载并获取函数模块,
然后通过getattr函数获取函数名,并在新模块中重新加载函数。
最后,使用yield from语句返回重新加载过的函数,并在被装饰的函数上执行。
最终,装饰器函数返回内部函数。这个内部函数可以将函数的原始定义更新为最新版本,并执行函数的新版本。
"""
@wraps(f)
def decorated(*args, **kwargs):
fn_name = f.__name__
f_hot_reload = getattr(importlib.reload(inspect.getmodule(f)), fn_name)
yield from f_hot_reload(*args, **kwargs)
return decorated
####################################### 其他小工具 #####################################
def get_reduce_token_percent(text):
"""
* 此函数未来将被弃用
"""
try:
# text = "maximum context length is 4097 tokens. However, your messages resulted in 4870 tokens"
pattern = r"(\d+)\s+tokens\b"
match = re.findall(pattern, text)
EXCEED_ALLO = 500 # 稍微留一点余地,否则在回复时会因余量太少出问题
max_limit = float(match[0]) - EXCEED_ALLO
current_tokens = float(match[1])
ratio = max_limit/current_tokens
assert ratio > 0 and ratio < 1
return ratio, str(int(current_tokens-max_limit))
except:
return 0.5, '不详'
def write_results_to_file(history, file_name=None):
"""
将对话记录history以Markdown格式写入文件中。如果没有指定文件名,则使用当前时间生成文件名。
"""
import os
import time
if file_name is None:
# file_name = time.strftime("chatGPT分析报告%Y-%m-%d-%H-%M-%S", time.localtime()) + '.md'
file_name = 'chatGPT分析报告' + \
time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.md'
os.makedirs('./gpt_log/', exist_ok=True)
with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
f.write('# chatGPT 分析报告\n')
for i, content in enumerate(history):
try: # 这个bug没找到触发条件,暂时先这样顶一下
if type(content) != str:
content = str(content)
except:
continue
if i % 2 == 0:
f.write('## ')
f.write(content)
f.write('\n\n')
res = '以上材料已经被写入' + os.path.abspath(f'./gpt_log/{file_name}')
print(res)
return res
def regular_txt_to_markdown(text):
"""
将普通文本转换为Markdown格式的文本。
"""
text = text.replace('\n', '\n\n')
text = text.replace('\n\n\n', '\n\n')
text = text.replace('\n\n\n', '\n\n')
return text
def report_execption(chatbot, history, a, b):
"""
向chatbot中添加错误信息
"""
chatbot.append((a, b))
history.append(a)
history.append(b)
def text_divide_paragraph(text):
"""
将文本按照段落分隔符分割开,生成带有段落标签的HTML代码。
"""
if '```' in text:
# careful input
return text
else:
# wtf input
lines = text.split("\n")
for i, line in enumerate(lines):
lines[i] = lines[i].replace(" ", " ")
text = "</br>".join(lines)
return text
def markdown_convertion(txt):
"""
将Markdown格式的文本转换为HTML格式。如果包含数学公式,则先将公式转换为HTML格式。
"""
pre = '<div class="markdown-body">'
suf = '</div>'
markdown_extension_configs = {
'mdx_math': {
'enable_dollar_delimiter': True,
'use_gitlab_delimiters': False,
},
}
find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
def tex2mathml_catch_exception(content, *args, **kwargs):
try:
content = tex2mathml(content, *args, **kwargs)
except:
content = content
return content
def replace_math_no_render(match):
content = match.group(1)
if 'mode=display' in match.group(0):
content = content.replace('\n', '</br>')
return f"<font color=\"#00FF00\">$$</font><font color=\"#FF00FF\">{content}</font><font color=\"#00FF00\">$$</font>"
else:
return f"<font color=\"#00FF00\">$</font><font color=\"#FF00FF\">{content}</font><font color=\"#00FF00\">$</font>"
def replace_math_render(match):
content = match.group(1)
if 'mode=display' in match.group(0):
if '\\begin{aligned}' in content:
content = content.replace('\\begin{aligned}', '\\begin{array}')
content = content.replace('\\end{aligned}', '\\end{array}')
content = content.replace('&', ' ')
content = tex2mathml_catch_exception(content, display="block")
return content
else:
return tex2mathml_catch_exception(content)
def markdown_bug_hunt(content):
"""
解决一个mdx_math的bug(单$包裹begin命令时多余<script>)
"""
content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
content = content.replace('</script>\n</script>', '</script>')
return content
if ('$' in txt) and ('```' not in txt): # 有$标识的公式符号,且没有代码段```的标识
# convert everything to html format
split = markdown.markdown(text='---')
convert_stage_1 = markdown.markdown(text=txt, extensions=['mdx_math', 'fenced_code', 'tables', 'sane_lists'], extension_configs=markdown_extension_configs)
convert_stage_1 = markdown_bug_hunt(convert_stage_1)
# re.DOTALL: Make the '.' special character match any character at all, including a newline; without this flag, '.' will match anything except a newline. Corresponds to the inline flag (?s).
# 1. convert to easy-to-copy tex (do not render math)
convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL)
# 2. convert to rendered equation
convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1, flags=re.DOTALL)
# cat them together
return pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf
else:
return pre + markdown.markdown(txt, extensions=['fenced_code', 'codehilite', 'tables', 'sane_lists']) + suf
def close_up_code_segment_during_stream(gpt_reply):
"""
在gpt输出代码的中途(输出了前面的```,但还没输出完后面的```),补上后面的```
Args:
gpt_reply (str): GPT模型返回的回复字符串。
Returns:
str: 返回一个新的字符串,将输出代码片段的“后面的```”补上。
"""
if '```' not in gpt_reply:
return gpt_reply
if gpt_reply.endswith('```'):
return gpt_reply
# 排除了以上两个情况,我们
segments = gpt_reply.split('```')
n_mark = len(segments) - 1
if n_mark % 2 == 1:
# print('输出代码片段中!')
return gpt_reply+'\n```'
else:
return gpt_reply
def format_io(self, y):
"""
将输入和输出解析为HTML格式。将y中最后一项的输入部分段落化,并将输出部分的Markdown和数学公式转换为HTML格式。
"""
if y is None or y == []:
return []
i_ask, gpt_reply = y[-1]
i_ask = text_divide_paragraph(i_ask) # 输入部分太自由,预处理一波
gpt_reply = close_up_code_segment_during_stream(gpt_reply) # 当代码输出半截的时候,试着补上后个```
y[-1] = (
None if i_ask is None else markdown.markdown(i_ask, extensions=['fenced_code', 'tables']),
None if gpt_reply is None else markdown_convertion(gpt_reply)
)
return y
def find_free_port():
"""
返回当前系统中可用的未使用端口。
"""
import socket
from contextlib import closing
with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as s:
s.bind(('', 0))
s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
return s.getsockname()[1]
def extract_archive(file_path, dest_dir):
import zipfile
import tarfile
import os
# Get the file extension of the input file
file_extension = os.path.splitext(file_path)[1]
# Extract the archive based on its extension
if file_extension == '.zip':
with zipfile.ZipFile(file_path, 'r') as zipobj:
zipobj.extractall(path=dest_dir)
print("Successfully extracted zip archive to {}".format(dest_dir))
elif file_extension in ['.tar', '.gz', '.bz2']:
with tarfile.open(file_path, 'r:*') as tarobj:
tarobj.extractall(path=dest_dir)
print("Successfully extracted tar archive to {}".format(dest_dir))
# 第三方库,需要预先pip install rarfile
# 此外,Windows上还需要安装winrar软件,配置其Path环境变量,如"C:\Program Files\WinRAR"才可以
elif file_extension == '.rar':
try:
import rarfile
with rarfile.RarFile(file_path) as rf:
rf.extractall(path=dest_dir)
print("Successfully extracted rar archive to {}".format(dest_dir))
except:
print("Rar format requires additional dependencies to install")
return '\n\n需要安装pip install rarfile来解压rar文件'
# 第三方库,需要预先pip install py7zr
elif file_extension == '.7z':
try:
import py7zr
with py7zr.SevenZipFile(file_path, mode='r') as f:
f.extractall(path=dest_dir)
print("Successfully extracted 7z archive to {}".format(dest_dir))
except:
print("7z format requires additional dependencies to install")
return '\n\n需要安装pip install py7zr来解压7z文件'
else:
return ''
return ''
def find_recent_files(directory):
"""
me: find files that is created with in one minutes under a directory with python, write a function
gpt: here it is!
"""
import os
import time
current_time = time.time()
one_minute_ago = current_time - 60
recent_files = []
for filename in os.listdir(directory):
file_path = os.path.join(directory, filename)
if file_path.endswith('.log'):
continue
created_time = os.path.getmtime(file_path)
if created_time >= one_minute_ago:
if os.path.isdir(file_path):
continue
recent_files.append(file_path)
return recent_files
def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
if len(files) == 0:
return chatbot, txt
import shutil
import os
import time
import glob
from toolbox import extract_archive
try:
shutil.rmtree('./private_upload/')
except:
pass
time_tag = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
os.makedirs(f'private_upload/{time_tag}', exist_ok=True)
err_msg = ''
for file in files:
file_origin_name = os.path.basename(file.orig_name)
shutil.copy(file.name, f'private_upload/{time_tag}/{file_origin_name}')
err_msg += extract_archive(f'private_upload/{time_tag}/{file_origin_name}',
dest_dir=f'private_upload/{time_tag}/{file_origin_name}.extract')
moved_files = [fp for fp in glob.glob(
'private_upload/**/*', recursive=True)]
if "底部输入区" in checkboxes:
txt = ""
txt2 = f'private_upload/{time_tag}'
else:
txt = f'private_upload/{time_tag}'
txt2 = ""
moved_files_str = '\t\n\n'.join(moved_files)
chatbot.append(['我上传了文件,请查收',
f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
f'\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
def on_report_generated(files, chatbot):
from toolbox import find_recent_files
report_files = find_recent_files('gpt_log')
if len(report_files) == 0:
return None, chatbot
# files.extend(report_files)
chatbot.append(['汇总报告如何远程获取?', '汇总报告已经添加到右侧“文件上传区”(可能处于折叠状态),请查收。'])
return report_files, chatbot
def is_openai_api_key(key):
API_MATCH = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
return bool(API_MATCH)
def is_api2d_key(key):
if key.startswith('fk') and len(key) == 41:
return True
else:
return False
def is_any_api_key(key):
if ',' in key:
keys = key.split(',')
for k in keys:
if is_any_api_key(k): return True
return False
else:
return is_openai_api_key(key) or is_api2d_key(key)
def select_api_key(keys, llm_model):
import random
avail_key_list = []
key_list = keys.split(',')
if llm_model.startswith('gpt-'):
for k in key_list:
if is_openai_api_key(k): avail_key_list.append(k)
if llm_model.startswith('api2d-'):
for k in key_list:
if is_api2d_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。")
api_key = random.choice(avail_key_list) # 随机负载均衡
return api_key
@lru_cache(maxsize=128)
def read_single_conf_with_lru_cache(arg):
from colorful import print亮红, print亮绿, print亮蓝
try:
r = getattr(importlib.import_module('config_private'), arg)
except:
r = getattr(importlib.import_module('config'), 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] 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。")
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。')
else:
print亮绿('[PROXY] 网络代理状态:已配置。配置信息如下:', r)
assert isinstance(r, dict), 'proxies格式错误,请注意proxies选项的格式,不要遗漏括号。'
return r
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 = []
for arg in args:
r = read_single_conf_with_lru_cache(arg)
res.append(r)
return res
def clear_line_break(txt):
txt = txt.replace('\n', ' ')
txt = txt.replace(' ', ' ')
txt = txt.replace(' ', ' ')
return txt
class DummyWith():
"""
这段代码定义了一个名为DummyWith的空上下文管理器,
它的作用是……额……没用,即在代码结构不变得情况下取代其他的上下文管理器。
上下文管理器是一种Python对象,用于与with语句一起使用,
以确保一些资源在代码块执行期间得到正确的初始化和清理。
上下文管理器必须实现两个方法,分别为 __enter__()和 __exit__()。
在上下文执行开始的情况下,__enter__()方法会在代码块被执行前被调用,
而在上下文执行结束时,__exit__()方法则会被调用。
"""
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
return
|