diff --git a/README.md b/README.md index 0dac72a..973ffd5 100644 --- a/README.md +++ b/README.md @@ -25,24 +25,26 @@ If you like this project, please give it a Star. If you've come up with more use --- | --- 一键润色 | 支持一键润色、一键查找论文语法错误 一键中英互译 | 一键中英互译 -一键代码解释 | 可以正确显示代码、解释代码 +一键代码解释 | 显示代码、解释代码、生成代码、给代码加注释 [自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键 [配置代理服务器](https://www.bilibili.com/video/BV1rc411W7Dr) | 支持代理连接OpenAI/Google等，秒解锁ChatGPT互联网[实时信息聚合](https://www.bilibili.com/video/BV1om4y127ck/)能力 模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/chatgpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97) [自我程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] [一键读懂](https://github.com/binary-husky/chatgpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)本项目的源代码 [程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] 一键可以剖析其他Python/C/C++/Java/Lua/...项目树 -读论文 | [函数插件] 一键解读latex论文全文并生成摘要 +读论文、翻译论文 | [函数插件] 一键解读latex/pdf论文全文并生成摘要 Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [函数插件] 一键翻译或润色latex论文 批量注释生成 | [函数插件] 一键批量生成函数注释 -chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/chatgpt_academic/blob/master/docs/README_EN.md)了吗？ -[arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF +chat分析报告生成 | [函数插件] 运行后自动生成总结汇报 [PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文（多线程） +[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载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ChatGPT先Google搜索，再回答问题，信息流永不过时 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 启动暗色gradio[主题](https://github.com/binary-husky/chatgpt_academic/issues/173) | 在浏览器url后面添加```/?__dark-theme=true```可以切换dark主题 [多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持，[API2D](https://api2d.com/)接口支持 | 同时被GPT3.5、GPT4和[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)伺候的感觉一定会很不错吧？ +更多LLM模型接入 | 新加入Newbing测试接口(新必应AI) huggingface免科学上网[在线体验](https://huggingface.co/spaces/qingxu98/gpt-academic) | 登陆huggingface后复制[此空间](https://huggingface.co/spaces/qingxu98/gpt-academic) …… | …… diff --git a/config.py b/config.py index b2727da..688f35d 100644 --- a/config.py +++ b/config.py @@ -45,7 +45,7 @@ MAX_RETRY = 2 # OpenAI模型选择是（gpt4现在只对申请成功的人开放，体验gpt-4可以试试api2d） LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓ -AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm"] +AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing"] # 本地LLM模型如ChatGLM的执行方式 CPU/GPU LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda" @@ -58,8 +58,14 @@ CONCURRENT_COUNT = 100 AUTHENTICATION = [] # 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!!） -# 格式 {"https://api.openai.com/v1/chat/completions": "重定向的URL"} +# 格式 {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"} API_URL_REDIRECT = {} # 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!） CUSTOM_PATH = "/" + +# 如果需要使用newbing，把newbing的长长的cookie放到这里 +NEWBING_STYLE = "creative" # ["creative", "balanced", "precise"] +NEWBING_COOKIES = """ +your bing cookies here +""" \ No newline at end of file diff --git a/crazy_functions/crazy_utils.py b/crazy_functions/crazy_utils.py index 4e0eba4..6af956f 100644 --- a/crazy_functions/crazy_utils.py +++ b/crazy_functions/crazy_utils.py @@ -1,5 +1,4 @@ -import traceback -from toolbox import update_ui, get_conf +from toolbox import update_ui, get_conf, trimmed_format_exc def input_clipping(inputs, history, max_token_limit): import numpy as np @@ -94,12 +93,12 @@ def request_gpt_model_in_new_thread_with_ui_alive( continue # 返回重试 else: # 【选择放弃】 - tb_str = '```\n' + traceback.format_exc() + '```' + tb_str = '```\n' + trimmed_format_exc() + '```' mutable[0] += f"[Local Message] 警告，在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n" return mutable[0] # 放弃 except: # 【第三种情况】：其他错误：重试几次 - tb_str = '```\n' + traceback.format_exc() + '```' + tb_str = '```\n' + trimmed_format_exc() + '```' print(tb_str) mutable[0] += f"[Local Message] 警告，在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n" if retry_op > 0: @@ -173,7 +172,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency( if max_workers == -1: # 读取配置文件 try: max_workers, = get_conf('DEFAULT_WORKER_NUM') except: max_workers = 8 - if max_workers <= 0 or max_workers >= 20: max_workers = 8 + if max_workers <= 0: max_workers = 3 # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿 if not (llm_kwargs['llm_model'].startswith('gpt-') or llm_kwargs['llm_model'].startswith('api2d-')): max_workers = 1 @@ -220,14 +219,14 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency( continue # 返回重试 else: # 【选择放弃】 - tb_str = '```\n' + traceback.format_exc() + '```' + tb_str = '```\n' + trimmed_format_exc() + '```' gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n" if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0] mutable[index][2] = "输入过长已放弃" return gpt_say # 放弃 except: # 【第三种情况】：其他错误 - tb_str = '```\n' + traceback.format_exc() + '```' + tb_str = '```\n' + trimmed_format_exc() + '```' print(tb_str) gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n" if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0] diff --git a/crazy_functions/解析项目源代码.py b/crazy_functions/解析项目源代码.py index bfa473a..49f41b1 100644 --- a/crazy_functions/解析项目源代码.py +++ b/crazy_functions/解析项目源代码.py @@ -1,5 +1,6 @@ from toolbox import update_ui from toolbox import CatchException, report_execption, write_results_to_file +from .crazy_utils import input_clipping def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt): import os, copy @@ -61,13 +62,15 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, previous_iteration_files.extend([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)]) previous_iteration_files_string = ', '.join(previous_iteration_files) current_iteration_focus = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)]) - i_say = f'根据以上分析，对程序的整体功能和构架重新做出概括。然后用一张markdown表格整理每个文件的功能（包括{previous_iteration_files_string}）。' + i_say = f'用一张Markdown表格简要描述以下文件的功能：{previous_iteration_files_string}。根据以上分析，用一句话概括程序的整体功能。' inputs_show_user = f'根据以上分析，对程序的整体功能和构架重新做出概括，由于输入长度限制，可能需要分组处理，本组文件为 {current_iteration_focus} + 已经汇总的文件组。' this_iteration_history = copy.deepcopy(this_iteration_gpt_response_collection) this_iteration_history.append(last_iteration_result) + # 裁剪input + inputs, this_iteration_history_feed = input_clipping(inputs=i_say, history=this_iteration_history, max_token_limit=2560) result = 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=this_iteration_history, # 迭代之前的分析 + inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot, + history=this_iteration_history_feed, # 迭代之前的分析 sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。") report_part_2.extend([i_say, result]) last_iteration_result = result diff --git a/main.py b/main.py index 55bd680..29ac825 100644 --- a/main.py +++ b/main.py @@ -173,9 +173,6 @@ def main(): yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs) click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo) click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot]) - # def expand_file_area(file_upload, area_file_up): - # if len(file_upload)>0: return {area_file_up: gr.update(open=True)} - # click_handle.then(expand_file_area, [file_upload, area_file_up], [area_file_up]) cancel_handles.append(click_handle) # 终止按钮的回调函数注册 stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles) diff --git a/request_llm/bridge_all.py b/request_llm/bridge_all.py index 311dc6f..fddc9a7 100644 --- a/request_llm/bridge_all.py +++ b/request_llm/bridge_all.py @@ -11,7 +11,7 @@ import tiktoken from functools import lru_cache from concurrent.futures import ThreadPoolExecutor -from toolbox import get_conf +from toolbox import get_conf, trimmed_format_exc from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui from .bridge_chatgpt import predict as chatgpt_ui @@ -19,6 +19,9 @@ from .bridge_chatgpt import predict as chatgpt_ui from .bridge_chatglm import predict_no_ui_long_connection as chatglm_noui from .bridge_chatglm import predict as chatglm_ui +from .bridge_newbing import predict_no_ui_long_connection as newbing_noui +from .bridge_newbing import predict as newbing_ui + # from .bridge_tgui import predict_no_ui_long_connection as tgui_noui # from .bridge_tgui import predict as tgui_ui @@ -48,6 +51,7 @@ class LazyloadTiktoken(object): API_URL_REDIRECT, = get_conf("API_URL_REDIRECT") openai_endpoint = "https://api.openai.com/v1/chat/completions" api2d_endpoint = "https://openai.api2d.net/v1/chat/completions" +newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub" # 兼容旧版的配置 try: API_URL, = get_conf("API_URL") @@ -59,6 +63,7 @@ except: # 新版配置 if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint] if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint] +if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint] # 获取tokenizer @@ -116,7 +121,15 @@ model_info = { "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, - + # newbing + "newbing": { + "fn_with_ui": newbing_ui, + "fn_without_ui": newbing_noui, + "endpoint": newbing_endpoint, + "max_token": 4096, + "tokenizer": tokenizer_gpt35, + "token_cnt": get_token_num_gpt35, + }, } @@ -128,10 +141,7 @@ def LLM_CATCH_EXCEPTION(f): try: return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience) except Exception as e: - from toolbox import get_conf - import traceback - proxies, = get_conf('proxies') - tb_str = '\n```\n' + traceback.format_exc() + '\n```\n' + tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n' observe_window[0] = tb_str return tb_str return decorated @@ -182,7 +192,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser def mutex_manager(window_mutex, observe_window): while True: - time.sleep(0.5) + time.sleep(0.25) if not window_mutex[-1]: break # 看门狗（watchdog） for i in range(n_model): diff --git a/request_llm/bridge_chatgpt.py b/request_llm/bridge_chatgpt.py index 5e32f45..48eaba0 100644 --- a/request_llm/bridge_chatgpt.py +++ b/request_llm/bridge_chatgpt.py @@ -21,7 +21,7 @@ import importlib # config_private.py放自己的秘密如API和代理网址 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件 -from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history +from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \ get_conf('proxies', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY') @@ -215,7 +215,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.") else: from toolbox import regular_txt_to_markdown - tb_str = '```\n' + traceback.format_exc() + '```' + 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[4:])}") yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面 return diff --git a/request_llm/bridge_newbing.py b/request_llm/bridge_newbing.py new file mode 100644 index 0000000..232eb6b --- /dev/null +++ b/request_llm/bridge_newbing.py @@ -0,0 +1,250 @@ +""" +======================================================================== +第一部分：来自EdgeGPT.py +https://github.com/acheong08/EdgeGPT +======================================================================== +""" +from .edge_gpt import NewbingChatbot +load_message = "等待NewBing响应。" + +""" +======================================================================== +第二部分：子进程Worker（调用主体） +======================================================================== +""" +import time +import json +import re +import asyncio +import importlib +import threading +from toolbox import update_ui, get_conf, trimmed_format_exc +from multiprocessing import Process, Pipe + +def preprocess_newbing_out(s): + pattern = r'\^(\d+)\^' # 匹配^数字^ + sub = lambda m: '\['+m.group(1)+'\]' # 将匹配到的数字作为替换值 + result = re.sub(pattern, sub, s) # 替换操作 + if '[1]' in result: + result += '\n\n```\n' + "\n".join([r for r in result.split('\n') if r.startswith('[')]) + '\n```\n' + return result + +def preprocess_newbing_out_simple(result): + if '[1]' in result: + result += '\n\n```\n' + "\n".join([r for r in result.split('\n') if r.startswith('[')]) + '\n```\n' + return result + +class NewBingHandle(Process): + def __init__(self): + super().__init__(daemon=True) + self.parent, self.child = Pipe() + self.newbing_model = None + self.info = "" + self.success = True + self.local_history = [] + self.check_dependency() + self.start() + self.threadLock = threading.Lock() + + def check_dependency(self): + try: + self.success = False + import certifi, httpx, rich + self.info = "依赖检测通过，等待NewBing响应。注意目前不能多人同时调用NewBing接口（有线程锁），否则将导致每个人的NewBing问询历史互相渗透。调用NewBing时，会自动使用已配置的代理。" + self.success = True + except: + self.info = "缺少的依赖，如果要使用Newbing，除了基础的pip依赖以外，您还需要运行`pip install -r request_llm/requirements_newbing.txt`安装Newbing的依赖。" + self.success = False + + def ready(self): + return self.newbing_model is not None + + async def async_run(self): + # 读取配置 + NEWBING_STYLE, = get_conf('NEWBING_STYLE') + from request_llm.bridge_all import model_info + endpoint = model_info['newbing']['endpoint'] + while True: + # 等待 + kwargs = self.child.recv() + question=kwargs['query'] + history=kwargs['history'] + system_prompt=kwargs['system_prompt'] + + # 是否重置 + if len(self.local_history) > 0 and len(history)==0: + await self.newbing_model.reset() + self.local_history = [] + + # 开始问问题 + prompt = "" + if system_prompt not in self.local_history: + self.local_history.append(system_prompt) + prompt += system_prompt + '\n' + + # 追加历史 + for ab in history: + a, b = ab + if a not in self.local_history: + self.local_history.append(a) + prompt += a + '\n' + if b not in self.local_history: + self.local_history.append(b) + prompt += b + '\n' + + # 问题 + prompt += question + self.local_history.append(question) + + # 提交 + async for final, response in self.newbing_model.ask_stream( + prompt=question, + conversation_style=NEWBING_STYLE, # ["creative", "balanced", "precise"] + wss_link=endpoint, # "wss://sydney.bing.com/sydney/ChatHub" + ): + if not final: + print(response) + self.child.send(str(response)) + else: + print('-------- receive final ---------') + self.child.send('[Finish]') + + + def run(self): + """ + 这个函数运行在子进程 + """ + # 第一次运行，加载参数 + self.success = False + self.local_history = [] + if (self.newbing_model is None) or (not self.success): + # 代理设置 + proxies, = get_conf('proxies') + if proxies is None: + self.proxies_https = None + else: + self.proxies_https = proxies['https'] + # cookie + NEWBING_COOKIES, = get_conf('NEWBING_COOKIES') + try: + cookies = json.loads(NEWBING_COOKIES) + except: + self.success = False + tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n' + self.child.send(f'[Local Message] 不能加载Newbing组件。NEWBING_COOKIES未填写或有格式错误。') + self.child.send('[Fail]') + self.child.send('[Finish]') + raise RuntimeError(f"不能加载Newbing组件。NEWBING_COOKIES未填写或有格式错误。") + + try: + self.newbing_model = NewbingChatbot(proxy=self.proxies_https, cookies=cookies) + except: + self.success = False + tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n' + self.child.send(f'[Local Message] 不能加载Newbing组件。{tb_str}') + self.child.send('[Fail]') + self.child.send('[Finish]') + raise RuntimeError(f"不能加载Newbing组件。") + + self.success = True + try: + # 进入任务等待状态 + asyncio.run(self.async_run()) + except Exception: + tb_str = '```\n' + trimmed_format_exc() + '```' + self.child.send(f'[Local Message] Newbing失败 {tb_str}.') + self.child.send('[Fail]') + self.child.send('[Finish]') + + def stream_chat(self, **kwargs): + """ + 这个函数运行在主进程 + """ + self.threadLock.acquire() + self.parent.send(kwargs) # 发送请求到子进程 + while True: + res = self.parent.recv() # 等待newbing回复的片段 + if res == '[Finish]': + break # 结束 + elif res == '[Fail]': + self.success = False + break + else: + yield res # newbing回复的片段 + self.threadLock.release() + + +""" +======================================================================== +第三部分：主进程统一调用函数接口 +======================================================================== +""" +global newbing_handle +newbing_handle = None + +def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False): + """ + 多线程方法 + 函数的说明请见 request_llm/bridge_all.py + """ + global newbing_handle + if (newbing_handle is None) or (not newbing_handle.success): + newbing_handle = NewBingHandle() + observe_window[0] = load_message + "\n\n" + newbing_handle.info + if not newbing_handle.success: + error = newbing_handle.info + newbing_handle = None + raise RuntimeError(error) + + # 没有 sys_prompt 接口，因此把prompt加入 history + history_feedin = [] + 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 = "" + observe_window[0] = "[Local Message]: 等待NewBing响应中 ..." + for response in newbing_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']): + observe_window[0] = preprocess_newbing_out_simple(response) + if len(observe_window) >= 2: + if (time.time()-observe_window[1]) > watch_dog_patience: + raise RuntimeError("程序终止。") + return preprocess_newbing_out_simple(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, "[Local Message]: 等待NewBing响应中 ...")) + + global newbing_handle + if (newbing_handle is None) or (not newbing_handle.success): + newbing_handle = NewBingHandle() + chatbot[-1] = (inputs, load_message + "\n\n" + newbing_handle.info) + yield from update_ui(chatbot=chatbot, history=[]) + if not newbing_handle.success: + newbing_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"] + + history_feedin = [] + for i in range(len(history)//2): + history_feedin.append([history[2*i], history[2*i+1]] ) + + chatbot[-1] = (inputs, "[Local Message]: 等待NewBing响应中 ...") + response = "[Local Message]: 等待NewBing响应中 ..." + yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢，尚未完成全部响应，请耐心完成后再提交新问题。") + for response in newbing_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']): + chatbot[-1] = (inputs, preprocess_newbing_out(response)) + yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢，尚未完成全部响应，请耐心完成后再提交新问题。") + + history.extend([inputs, preprocess_newbing_out(response)]) + yield from update_ui(chatbot=chatbot, history=history, msg="完成全部响应，请提交新问题。") + diff --git a/request_llm/edge_gpt.py b/request_llm/edge_gpt.py new file mode 100644 index 0000000..bbf8400 --- /dev/null +++ b/request_llm/edge_gpt.py @@ -0,0 +1,409 @@ +""" +======================================================================== +第一部分：来自EdgeGPT.py +https://github.com/acheong08/EdgeGPT +======================================================================== +""" + +import argparse +import asyncio +import json +import os +import random +import re +import ssl +import sys +import uuid +from enum import Enum +from typing import Generator +from typing import Literal +from typing import Optional +from typing import Union +import websockets.client as websockets + +DELIMITER = "\x1e" + + +# Generate random IP between range 13.104.0.0/14 +FORWARDED_IP = ( + f"13.{random.randint(104, 107)}.{random.randint(0, 255)}.{random.randint(0, 255)}" +) + +HEADERS = { + "accept": "application/json", + "accept-language": "en-US,en;q=0.9", + "content-type": "application/json", + "sec-ch-ua": '"Not_A Brand";v="99", "Microsoft Edge";v="110", "Chromium";v="110"', + "sec-ch-ua-arch": '"x86"', + "sec-ch-ua-bitness": '"64"', + "sec-ch-ua-full-version": '"109.0.1518.78"', + "sec-ch-ua-full-version-list": '"Chromium";v="110.0.5481.192", "Not A(Brand";v="24.0.0.0", "Microsoft Edge";v="110.0.1587.69"', + "sec-ch-ua-mobile": "?0", + "sec-ch-ua-model": "", + "sec-ch-ua-platform": '"Windows"', + "sec-ch-ua-platform-version": '"15.0.0"', + "sec-fetch-dest": "empty", + "sec-fetch-mode": "cors", + "sec-fetch-site": "same-origin", + "x-ms-client-request-id": str(uuid.uuid4()), + "x-ms-useragent": "azsdk-js-api-client-factory/1.0.0-beta.1 core-rest-pipeline/1.10.0 OS/Win32", + "Referer": "https://www.bing.com/search?q=Bing+AI&showconv=1&FORM=hpcodx", + "Referrer-Policy": "origin-when-cross-origin", + "x-forwarded-for": FORWARDED_IP, +} + +HEADERS_INIT_CONVER = { + "authority": "edgeservices.bing.com", + "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7", + "accept-language": "en-US,en;q=0.9", + "cache-control": "max-age=0", + "sec-ch-ua": '"Chromium";v="110", "Not A(Brand";v="24", "Microsoft Edge";v="110"', + "sec-ch-ua-arch": '"x86"', + "sec-ch-ua-bitness": '"64"', + "sec-ch-ua-full-version": '"110.0.1587.69"', + "sec-ch-ua-full-version-list": '"Chromium";v="110.0.5481.192", "Not A(Brand";v="24.0.0.0", "Microsoft Edge";v="110.0.1587.69"', + "sec-ch-ua-mobile": "?0", + "sec-ch-ua-model": '""', + "sec-ch-ua-platform": '"Windows"', + "sec-ch-ua-platform-version": '"15.0.0"', + "sec-fetch-dest": "document", + "sec-fetch-mode": "navigate", + "sec-fetch-site": "none", + "sec-fetch-user": "?1", + "upgrade-insecure-requests": "1", + "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.69", + "x-edge-shopping-flag": "1", + "x-forwarded-for": FORWARDED_IP, +} + +def get_ssl_context(): + import certifi + ssl_context = ssl.create_default_context() + ssl_context.load_verify_locations(certifi.where()) + return ssl_context + + + +class NotAllowedToAccess(Exception): + pass + + +class ConversationStyle(Enum): + creative = "h3imaginative,clgalileo,gencontentv3" + balanced = "galileo" + precise = "h3precise,clgalileo" + + +CONVERSATION_STYLE_TYPE = Optional[ + Union[ConversationStyle, Literal["creative", "balanced", "precise"]] +] + + +def _append_identifier(msg: dict) -> str: + """ + Appends special character to end of message to identify end of message + """ + # Convert dict to json string + return json.dumps(msg) + DELIMITER + + +def _get_ran_hex(length: int = 32) -> str: + """ + Returns random hex string + """ + return "".join(random.choice("0123456789abcdef") for _ in range(length)) + + +class _ChatHubRequest: + """ + Request object for ChatHub + """ + + def __init__( + self, + conversation_signature: str, + client_id: str, + conversation_id: str, + invocation_id: int = 0, + ) -> None: + self.struct: dict = {} + + self.client_id: str = client_id + self.conversation_id: str = conversation_id + self.conversation_signature: str = conversation_signature + self.invocation_id: int = invocation_id + + def update( + self, + prompt, + conversation_style, + options, + ) -> None: + """ + Updates request object + """ + if options is None: + options = [ + "deepleo", + "enable_debug_commands", + "disable_emoji_spoken_text", + "enablemm", + ] + if conversation_style: + if not isinstance(conversation_style, ConversationStyle): + conversation_style = getattr(ConversationStyle, conversation_style) + options = [ + "nlu_direct_response_filter", + "deepleo", + "disable_emoji_spoken_text", + "responsible_ai_policy_235", + "enablemm", + conversation_style.value, + "dtappid", + "cricinfo", + "cricinfov2", + "dv3sugg", + ] + self.struct = { + "arguments": [ + { + "source": "cib", + "optionsSets": options, + "sliceIds": [ + "222dtappid", + "225cricinfo", + "224locals0", + ], + "traceId": _get_ran_hex(32), + "isStartOfSession": self.invocation_id == 0, + "message": { + "author": "user", + "inputMethod": "Keyboard", + "text": prompt, + "messageType": "Chat", + }, + "conversationSignature": self.conversation_signature, + "participant": { + "id": self.client_id, + }, + "conversationId": self.conversation_id, + }, + ], + "invocationId": str(self.invocation_id), + "target": "chat", + "type": 4, + } + self.invocation_id += 1 + + +class _Conversation: + """ + Conversation API + """ + + def __init__( + self, + cookies, + proxy, + ) -> None: + self.struct: dict = { + "conversationId": None, + "clientId": None, + "conversationSignature": None, + "result": {"value": "Success", "message": None}, + } + import httpx + self.proxy = proxy + proxy = ( + proxy + or os.environ.get("all_proxy") + or os.environ.get("ALL_PROXY") + or os.environ.get("https_proxy") + or os.environ.get("HTTPS_PROXY") + or None + ) + if proxy is not None and proxy.startswith("socks5h://"): + proxy = "socks5://" + proxy[len("socks5h://") :] + self.session = httpx.Client( + proxies=proxy, + timeout=30, + headers=HEADERS_INIT_CONVER, + ) + for cookie in cookies: + self.session.cookies.set(cookie["name"], cookie["value"]) + + # Send GET request + response = self.session.get( + url=os.environ.get("BING_PROXY_URL") + or "https://edgeservices.bing.com/edgesvc/turing/conversation/create", + ) + if response.status_code != 200: + response = self.session.get( + "https://edge.churchless.tech/edgesvc/turing/conversation/create", + ) + if response.status_code != 200: + print(f"Status code: {response.status_code}") + print(response.text) + print(response.url) + raise Exception("Authentication failed") + try: + self.struct = response.json() + except (json.decoder.JSONDecodeError, NotAllowedToAccess) as exc: + raise Exception( + "Authentication failed. You have not been accepted into the beta.", + ) from exc + if self.struct["result"]["value"] == "UnauthorizedRequest": + raise NotAllowedToAccess(self.struct["result"]["message"]) + + +class _ChatHub: + """ + Chat API + """ + + def __init__(self, conversation) -> None: + self.wss = None + self.request: _ChatHubRequest + self.loop: bool + self.task: asyncio.Task + print(conversation.struct) + self.request = _ChatHubRequest( + conversation_signature=conversation.struct["conversationSignature"], + client_id=conversation.struct["clientId"], + conversation_id=conversation.struct["conversationId"], + ) + + async def ask_stream( + self, + prompt: str, + wss_link: str, + conversation_style: CONVERSATION_STYLE_TYPE = None, + raw: bool = False, + options: dict = None, + ) -> Generator[str, None, None]: + """ + Ask a question to the bot + """ + if self.wss and not self.wss.closed: + await self.wss.close() + # Check if websocket is closed + self.wss = await websockets.connect( + wss_link, + extra_headers=HEADERS, + max_size=None, + ssl=get_ssl_context() + ) + await self._initial_handshake() + # Construct a ChatHub request + self.request.update( + prompt=prompt, + conversation_style=conversation_style, + options=options, + ) + # Send request + await self.wss.send(_append_identifier(self.request.struct)) + final = False + while not final: + objects = str(await self.wss.recv()).split(DELIMITER) + for obj in objects: + if obj is None or not obj: + continue + response = json.loads(obj) + if response.get("type") != 2 and raw: + yield False, response + elif response.get("type") == 1 and response["arguments"][0].get( + "messages", + ): + resp_txt = response["arguments"][0]["messages"][0]["adaptiveCards"][ + 0 + ]["body"][0].get("text") + yield False, resp_txt + elif response.get("type") == 2: + final = True + yield True, response + + async def _initial_handshake(self) -> None: + await self.wss.send(_append_identifier({"protocol": "json", "version": 1})) + await self.wss.recv() + + async def close(self) -> None: + """ + Close the connection + """ + if self.wss and not self.wss.closed: + await self.wss.close() + + +class NewbingChatbot: + """ + Combines everything to make it seamless + """ + + def __init__( + self, + cookies, + proxy + ) -> None: + if cookies is None: + cookies = {} + self.cookies = cookies + self.proxy = proxy + self.chat_hub: _ChatHub = _ChatHub( + _Conversation(self.cookies, self.proxy), + ) + + async def ask( + self, + prompt: str, + wss_link: str, + conversation_style: CONVERSATION_STYLE_TYPE = None, + options: dict = None, + ) -> dict: + """ + Ask a question to the bot + """ + async for final, response in self.chat_hub.ask_stream( + prompt=prompt, + conversation_style=conversation_style, + wss_link=wss_link, + options=options, + ): + if final: + return response + await self.chat_hub.wss.close() + return None + + async def ask_stream( + self, + prompt: str, + wss_link: str, + conversation_style: CONVERSATION_STYLE_TYPE = None, + raw: bool = False, + options: dict = None, + ) -> Generator[str, None, None]: + """ + Ask a question to the bot + """ + async for response in self.chat_hub.ask_stream( + prompt=prompt, + conversation_style=conversation_style, + wss_link=wss_link, + raw=raw, + options=options, + ): + yield response + + async def close(self) -> None: + """ + Close the connection + """ + await self.chat_hub.close() + + async def reset(self) -> None: + """ + Reset the conversation + """ + await self.close() + self.chat_hub = _ChatHub(_Conversation(self.cookies, self.proxy)) + + diff --git a/request_llm/requirements_newbing.txt b/request_llm/requirements_newbing.txt new file mode 100644 index 0000000..73455f4 --- /dev/null +++ b/request_llm/requirements_newbing.txt @@ -0,0 +1,8 @@ +BingImageCreator +certifi +httpx +prompt_toolkit +requests +rich +websockets +httpx[socks] diff --git a/toolbox.py b/toolbox.py index c9dc207..81ff91d 100644 --- a/toolbox.py +++ b/toolbox.py @@ -5,7 +5,20 @@ 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 ####################################### + +""" +======================================================================== +第一部分 +函数插件输入输出接驳区 + - ChatBotWithCookies: 带Cookies的Chatbot类，为实现更多强大的功能做基础 + - ArgsGeneralWrapper: 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 + - update_ui: 刷新界面用 yield from update_ui(chatbot, history) + - CatchException: 将插件中出的所有问题显示在界面上 + - HotReload: 实现插件的热更新 + - trimmed_format_exc: 打印traceback，为了安全而隐藏绝对地址 +======================================================================== +""" + class ChatBotWithCookies(list): def __init__(self, cookie): self._cookies = cookie @@ -20,6 +33,7 @@ class ChatBotWithCookies(list): 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。 @@ -47,6 +61,7 @@ def ArgsGeneralWrapper(f): 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 @@ -54,10 +69,18 @@ def update_ui(chatbot, history, msg='正常', **kwargs): # 刷新界面 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 trimmed_format_exc(): + import os, traceback + str = traceback.format_exc() + current_path = os.getcwd() + replace_path = "." + return str.replace(current_path, replace_path) + 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: @@ -66,7 +89,7 @@ def CatchException(f): from check_proxy import check_proxy from toolbox import get_conf proxies, = get_conf('proxies') - tb_str = '```\n' + traceback.format_exc() + '```' + tb_str = '```\n' + trimmed_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], @@ -93,7 +116,23 @@ def HotReload(f): return decorated -####################################### 其他小工具 ##################################### +""" +======================================================================== +第二部分 +其他小工具: + - write_results_to_file: 将结果写入markdown文件中 + - regular_txt_to_markdown: 将普通文本转换为Markdown格式的文本。 + - report_execption: 向chatbot中添加简单的意外错误信息 + - text_divide_paragraph: 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。 + - markdown_convertion: 用多种方式组合，将markdown转化为好看的html + - format_io: 接管gradio默认的markdown处理方式 + - on_file_uploaded: 处理文件的上传（自动解压） + - on_report_generated: 将生成的报告自动投射到文件上传区 + - clip_history: 当历史上下文过长时，自动截断 + - get_conf: 获取设置 + - select_api_key: 根据当前的模型类别，抽取可用的api-key +======================================================================== +""" def get_reduce_token_percent(text): """ @@ -113,7 +152,6 @@ def get_reduce_token_percent(text): 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。 @@ -369,6 +407,9 @@ def find_recent_files(directory): def on_file_uploaded(files, chatbot, txt, txt2, checkboxes): + """ + 当文件被上传时的回调函数 + """ if len(files) == 0: return chatbot, txt import shutil @@ -388,8 +429,7 @@ def on_file_uploaded(files, chatbot, txt, txt2, checkboxes): 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)] + 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}' @@ -508,7 +548,7 @@ def clear_line_break(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。 + 它的作用是……额……就是不起作用，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__()。 @@ -522,6 +562,9 @@ class DummyWith(): return def run_gradio_in_subpath(demo, auth, port, custom_path): + """ + 把gradio的运行地址更改到指定的二次路径上 + """ def is_path_legal(path: str)->bool: ''' check path for sub url diff --git a/version b/version index a2a877b..076c2e7 100644 --- a/version +++ b/version @@ -1,5 +1,5 @@ { - "version": 3.2, + "version": 3.3, "show_feature": true, - "new_feature": "保存对话功能 <-> 解读任意语言代码+同时询问任意的LLM组合 <-> 添加联网（Google）回答问题插件 <-> 修复ChatGLM上下文BUG <-> 添加支持清华ChatGLM和GPT-4 <-> 改进架构，支持与多个LLM模型同时对话 <-> 添加支持API2D（国内，可支持gpt4）" + "new_feature": "支持NewBing !! <-> 保存对话功能 <-> 解读任意语言代码+同时询问任意的LLM组合 <-> 添加联网（Google）回答问题插件 <-> 修复ChatGLM上下文BUG <-> 添加支持清华ChatGLM和GPT-4 <-> 改进架构，支持与多个LLM模型同时对话 <-> 添加支持API2D（国内，可支持gpt4）" }