diff --git a/requirements.txt b/requirements.txt index 3f39924..265a3cb 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,10 +1,3 @@ gradio>=3.23 -requests[socks]~=2.28.2 -mdtex2html~=1.2.0 - -markdown~=3.4.3 -latex2mathml~=3.75.1 -numpy~=1.21.6 - -rarfile~=4.0 -py7zr~=0.20.4 \ No newline at end of file +requests[socks] +mdtex2html \ No newline at end of file diff --git a/toolbox.py b/toolbox.py index 968ca60..30399de 100644 --- a/toolbox.py +++ b/toolbox.py @@ -2,7 +2,6 @@ import markdown, mdtex2html, threading, importlib, traceback from show_math import convert as convert_math from functools import wraps - def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[], sys_prompt=''): """ 调用简单的predict_no_ui接口,但是依然保留了些许界面心跳功能,当对话太长时,会自动采用二分法截断 @@ -14,43 +13,36 @@ def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temp # 多线程的时候,需要一个mutable结构在不同线程之间传递信息 # list就是最简单的mutable结构,我们第一个位置放gpt输出,第二个位置传递报错信息 mutable = [None, ''] - # multi-threading worker def mt(i_say, history): while True: try: - mutable[0] = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature, history=history, - sys_prompt=sys_prompt) + mutable[0] = predict_no_ui(inputs=i_say, top_p=top_p, temperature=temperature, history=history, sys_prompt=sys_prompt) break except ConnectionAbortedError as e: if len(history) > 0: - history = [his[len(his) // 2:] for his in history if his is not None] + history = [his[len(his)//2:] for his in history if his is not None] mutable[1] = 'Warning! History conversation is too long, cut into half. ' else: - i_say = i_say[:len(i_say) // 2] + i_say = i_say[:len(i_say)//2] mutable[1] = 'Warning! Input file is too long, cut into half. ' except TimeoutError as e: mutable[0] = '[Local Message] Failed with timeout.' raise TimeoutError - # 创建新线程发出http请求 - thread_name = threading.Thread(target=mt, args=(i_say, history)); - thread_name.start() + thread_name = threading.Thread(target=mt, args=(i_say, history)); thread_name.start() # 原来的线程则负责持续更新UI,实现一个超时倒计时,并等待新线程的任务完成 cnt = 0 while thread_name.is_alive(): cnt += 1 - chatbot[-1] = (i_say_show_user, - f"[Local Message] {mutable[1]}waiting gpt response {cnt}/{TIMEOUT_SECONDS * 2 * (MAX_RETRY + 1)}" + ''.join( - ['.'] * (cnt % 4))) + chatbot[-1] = (i_say_show_user, f"[Local Message] {mutable[1]}waiting gpt response {cnt}/{TIMEOUT_SECONDS*2*(MAX_RETRY+1)}"+''.join(['.']*(cnt%4))) yield chatbot, history, '正常' time.sleep(1) # 把gpt的输出从mutable中取出来 gpt_say = mutable[0] - if gpt_say == '[Local Message] Failed with timeout.': raise TimeoutError + if gpt_say=='[Local Message] Failed with timeout.': raise TimeoutError return gpt_say - 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。 @@ -60,17 +52,16 @@ def write_results_to_file(history, file_name=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: + 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): - if i % 2 == 0: f.write('## ') + 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。 @@ -80,12 +71,10 @@ def regular_txt_to_markdown(text): text = text.replace('\n\n\n', '\n\n') return text - 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: @@ -95,21 +84,16 @@ def CatchException(f): from toolbox import get_conf proxies, = get_conf('proxies') tb_str = regular_txt_to_markdown(traceback.format_exc()) - 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)}") + 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 chatbot, history, f'异常 {e}' - return decorated - 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) - + history.append(a); history.append(b) def text_divide_paragraph(text): """ @@ -126,16 +110,15 @@ def text_divide_paragraph(text): text = "
".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。 """ if ('$' in txt) and ('```' not in txt): - return markdown.markdown(txt, extensions=['fenced_code', 'tables']) + '

' + \ - markdown.markdown(convert_math(txt, splitParagraphs=False), extensions=['fenced_code', 'tables']) + return markdown.markdown(txt,extensions=['fenced_code','tables']) + '

' + \ + markdown.markdown(convert_math(txt, splitParagraphs=False),extensions=['fenced_code','tables']) else: - return markdown.markdown(txt, extensions=['fenced_code', 'tables']) + return markdown.markdown(txt,extensions=['fenced_code','tables']) def format_io(self, y): @@ -144,9 +127,9 @@ def format_io(self, y): """ 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 + i_ask = text_divide_paragraph(i_ask) # 输入部分太自由,预处理一波 y[-1] = ( - None if i_ask is None else markdown.markdown(i_ask, extensions=['fenced_code', 'tables']), + 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 @@ -168,7 +151,6 @@ 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] @@ -183,17 +165,18 @@ def extract_archive(file_path, dest_dir): 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': - # 这是个第三方库,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 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格式需要安装额外依赖") + print("Rar format requires additional dependencies to install") + # 第三方库,需要预先pip install py7zr elif file_extension == '.7z': try: import py7zr @@ -201,12 +184,11 @@ def extract_archive(file_path, dest_dir): f.extractall(path=dest_dir) print("Successfully extracted 7z archive to {}".format(dest_dir)) except: - print("7z格式需要安装额外依赖") + print("7z format requires additional dependencies to install") else: return - def find_recent_files(directory): """ me: find files that is created with in one minutes under a directory with python, write a function @@ -233,10 +215,8 @@ def on_file_uploaded(files, chatbot, txt): if len(files) == 0: return chatbot, txt import shutil, os, time, glob from toolbox import extract_archive - try: - shutil.rmtree('./private_upload/') - except: - pass + 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) for file in files: @@ -260,25 +240,21 @@ def on_report_generated(files, chatbot): 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,请查收。']) return report_files, chatbot - 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: - try: - r = getattr(importlib.import_module('config_private'), arg) - except: - r = getattr(importlib.import_module('config'), arg) + try: r = getattr(importlib.import_module('config_private'), arg) + except: r = getattr(importlib.import_module('config'), arg) res.append(r) # 在读取API_KEY时,检查一下是不是忘了改config - if arg == 'API_KEY' and len(r) != 51: + if arg=='API_KEY' and len(r) != 51: assert False, "正确的API_KEY密钥是51位,请在config文件中修改API密钥, 添加海外代理之后再运行。" + \ - "(如果您刚更新过代码,请确保旧版config_private文件中没有遗留任何新增键值)" + "(如果您刚更新过代码,请确保旧版config_private文件中没有遗留任何新增键值)" return res - def clear_line_break(txt): txt = txt.replace('\n', ' ') txt = txt.replace(' ', ' ') txt = txt.replace(' ', ' ') - return txt + return txt \ No newline at end of file