Merge pull request #841 from KelvinF97/master

Optimize some code and fix some bugs

README.md

@@ -97,7 +97,7 @@ cd gpt_academic
 
 2. 配置API_KEY
 
-在`config.py`中，配置API KEY等设置，[特殊网络环境设置](https://github.com/binary-husky/gpt_academic/issues/1) 。
+在`config.py`中，配置API KEY等设置，[点击查看特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1) 。
 
 (P.S. 程序运行时会优先检查是否存在名为`config_private.py`的私密配置文件，并用其中的配置覆盖`config.py`的同名配置。因此，如果您能理解我们的配置读取逻辑，我们强烈建议您在`config.py`旁边创建一个名为`config_private.py`的新配置文件，并把`config.py`中的配置转移（复制）到`config_private.py`中。`config_private.py`不受git管控，可以让您的隐私信息更加安全。P.S.项目同样支持通过`环境变量`配置大多数选项，环境变量的书写格式参考`docker-compose`文件。读取优先级: `环境变量` > `config_private.py` > `config.py`)
 
@@ -140,15 +140,9 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-
 python main.py
 ```
 
-5. 测试函数插件
-```
-- 测试函数插件模板函数（要求gpt回答历史上的今天发生了什么），您可以根据此函数为模板，实现更复杂的功能
-    点击 "[函数插件模板Demo] 历史上的今天"
-```
-
 ## 安装-方法2：使用Docker
 
-1. 仅ChatGPT（推荐大多数人选择）
+1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
 
 ``` sh
 git clone https://github.com/binary-husky/gpt_academic.git  # 下载项目
@@ -161,41 +155,43 @@ docker run --rm -it --net=host gpt-academic
 #（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口
 docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic
 ```
-P.S. 如果需要依赖Latex的插件功能，请见Wiki
+P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以直接使用docker-compose获取Latex功能（修改docker-compose.yml，保留方案4并删除其他方案）。
 
 2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker）
 
 ``` sh
-# 修改docker-compose.yml，删除方案1和方案3，保留方案2。修改docker-compose.yml中方案2的配置，参考其中注释即可
+# 修改docker-compose.yml，保留方案2并删除其他方案。修改docker-compose.yml中方案2的配置，参考其中注释即可
 docker-compose up
 ```
 
 3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
 ``` sh
-# 修改docker-compose.yml，删除方案1和方案2，保留方案3。修改docker-compose.yml中方案3的配置，参考其中注释即可
+# 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
 docker-compose up
 ```
 
 
 ## 安装-方法3：其他部署姿势
 1. 一键运行脚本。
-完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本，
-不建议电脑上已有python的用户采用此方法（在此基础上安装插件的依赖很麻烦）。
+完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。
 脚本的贡献来源是[oobabooga](https://github.com/oobabooga/one-click-installers)。
 
 2. 使用docker-compose运行。
 请阅读docker-compose.yml后，按照其中的提示操作即可
 
-3. 如何使用反代URL/微软云AzureAPI。
+3. 如何使用反代URL
 按照`config.py`中的说明配置API_URL_REDIRECT即可。
 
-4. 远程云服务器部署（需要云服务器知识与经验）。
+4. 微软云AzureAPI
+按照`config.py`中的说明配置即可（AZURE_ENDPOINT等四个配置）
+
+5. 远程云服务器部署（需要云服务器知识与经验）。
 请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
 
-5. 使用WSL2（Windows Subsystem for Linux 子系统）。
+6. 使用WSL2（Windows Subsystem for Linux 子系统）。
 请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
 
-6. 如何在二级网址（如`http://localhost/subpath`）下运行。
+7. 如何在二级网址（如`http://localhost/subpath`）下运行。
 请访问[FastAPI运行说明](docs/WithFastapi.md)
 
 ---

check_proxy.py

@@ -1,10 +1,10 @@
 
-def check_proxy(proxies):
+def check_proxy(proxies: dict):
     import requests
-    proxies_https = proxies['https'] if proxies is not None else '无'
+    proxies_https = proxies.get('https') if proxies is not None else '无'
     try:
         response = requests.get("https://ipapi.co/json/",
-                                proxies=proxies, timeout=4)
+                                proxies=proxies, timeout=30)
         data = response.json()
         print(f'查询代理的地理位置，返回的结果是{data}')
         if 'country_name' in data:
@@ -12,10 +12,12 @@ def check_proxy(proxies):
             result = f"代理配置 {proxies_https}, 代理所在地：{country}"
         elif 'error' in data:
             result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
+        else:
+            result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
         print(result)
         return result
-    except:
-        result = f"代理配置 {proxies_https}, 代理所在地查询超时，代理可能无效"
+    except Exception as e:
+        result = f"代理 {proxies_https} 查询出现异常: {e}，代理可能无效"
         print(result)
         return result
 

config.py

@@ -1,6 +1,7 @@
 # [step 1]>> 例如： API_KEY = "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" （此key无效）
 API_KEY = "sk-此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
 
+
 # [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改
 USE_PROXY = False
 if USE_PROXY:
@@ -46,8 +47,8 @@ MAX_RETRY = 2
 
 # 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 )
 LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"]
-# P.S. 其他可用的模型还包括 ["newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt35", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "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", "newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
@@ -55,6 +56,9 @@ LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
+# 是否在提交时自动清空输入框
+AUTO_CLEAR_TXT = False
+
 # 加一个live2d装饰
 ADD_WAIFU = False
 
@@ -81,3 +85,10 @@ your bing cookies here
 # 如果需要使用Slack Claude，使用教程详情见 request_llm/README.md
 SLACK_CLAUDE_BOT_ID = ''   
 SLACK_CLAUDE_USER_TOKEN = ''
+
+
+# 如果需要使用AZURE 详情请见额外文档 docs\use_azure.md
+AZURE_ENDPOINT = "https://你的api名称.openai.azure.com/"
+AZURE_API_KEY = "填入azure openai api的密钥"
+AZURE_API_VERSION = "填入api版本"
+AZURE_ENGINE = "填入ENGINE"

core_functional.py

@@ -63,6 +63,7 @@ def get_core_functions():
             "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，" +
                         r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
             "Suffix":   r"",
+            "Visible": False,
         },
         "解释代码": {
             "Prefix":   r"请解释以下代码：" + "\n```\n",
@@ -73,6 +74,5 @@ def get_core_functions():
                         r"Note that, reference styles maybe more than one kind, you should transform each item correctly." +
                         r"Items need to be transformed:",
             "Suffix":   r"",
-            "Visible": False,
         }
     }

crazy_functional.py

@@ -112,11 +112,11 @@ def get_crazy_functions():
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析项目本身)
         },
-        "[老旧的Demo] 把本项目源代码切换成全英文": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(全项目切换英文)
-        },
+        # "[老旧的Demo] 把本项目源代码切换成全英文": {
+        #     # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
+        #     "AsButton": False,  # 加入下拉菜单中
+        #     "Function": HotReload(全项目切换英文)
+        # },
         "[插件demo] 历史上的今天": {
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
             "Function": HotReload(高阶功能模板函数)
@@ -226,12 +226,20 @@ def get_crazy_functions():
     try:
         from crazy_functions.联网的ChatGPT import 连接网络回答问题
         function_plugins.update({
-            "连接网络回答问题（先输入问题，再点击按钮，需要访问谷歌）": {
+            "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
                 "Color": "stop",
                 "AsButton": False,  # 加入下拉菜单中
                 "Function": HotReload(连接网络回答问题)
             }
         })
+        from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
+        function_plugins.update({
+            "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
+                "Color": "stop",
+                "AsButton": False,  # 加入下拉菜单中
+                "Function": HotReload(连接bing搜索回答问题)
+            }
+        })
     except:
         print('Load function plugin failed')
 
@@ -348,17 +356,28 @@ def get_crazy_functions():
     try:
         from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
         function_plugins.update({
-            "[功能尚不稳定] Latex英文纠错+LatexDiff高亮修正位置": {
+            "Latex英文纠错+高亮修正位置 [需Latex]": {
                 "Color": "stop",
                 "AsButton": False,
-                # "AdvancedArgs": True,
-                # "ArgsReminder": "",
+                "AdvancedArgs": True,
+                "ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
                 "Function": HotReload(Latex英文纠错加PDF对比)
             }
         })
         from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
         function_plugins.update({
-            "Arixv翻译（输入arxivID） [需Latex]": {
+            "Arixv翻译（输入arxivID）[需Latex]": {
+                "Color": "stop",
+                "AsButton": False,
+                "AdvancedArgs": True,
+                "ArgsReminder": 
+                    "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+ 
+                    "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                "Function": HotReload(Latex翻译中文并重新编译PDF)
+            }
+        })
+        function_plugins.update({
+            "本地论文翻译（上传Latex压缩包）[需Latex]": {
                 "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
@@ -368,17 +387,6 @@ def get_crazy_functions():
                 "Function": HotReload(Latex翻译中文并重新编译PDF)
             }
         })
-        # function_plugins.update({
-        #     "本地论文翻译（上传Latex压缩包） [需Latex]": {
-        #         "Color": "stop",
-        #         "AsButton": False,
-        #         "AdvancedArgs": True,
-        #         "ArgsReminder": 
-        #             "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+ 
-        #             "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
-        #         "Function": HotReload(Latex翻译中文并重新编译PDF)
-        #     }
-        # })
     except:
         print('Load function plugin failed')
 

crazy_functions/Latex输出PDF结果.py

@@ -19,9 +19,9 @@ def switch_prompt(pfg, mode, more_requirement):
     - sys_prompt_array: A list of strings containing prompts for system prompts.
     """
     n_split = len(pfg.sp_file_contents)
-    if mode == 'proofread':
+    if mode == 'proofread_en':
         inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
+                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
                         r"Answer me only with the revised text:" + 
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
@@ -70,6 +70,12 @@ def move_project(project_folder, arxiv_id=None):
         shutil.rmtree(new_workfolder)
     except:
         pass
+
+    # align subfolder if there is a folder wrapper
+    items = glob.glob(pj(project_folder,'*'))
+    if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
+        if os.path.isdir(items[0]): project_folder = items[0]
+
     shutil.copytree(src=project_folder, dst=new_workfolder)
     return new_workfolder
 
@@ -90,7 +96,7 @@ def arxiv_download(chatbot, history, txt):
         except ValueError:
             return False
     if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
-        txt = 'https://arxiv.org/abs/' + txt
+        txt = 'https://arxiv.org/abs/' + txt.strip()
     if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
         txt = 'https://arxiv.org/abs/' + txt[:10]
     if not txt.startswith('https://arxiv.org'): 
@@ -141,7 +147,11 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     chatbot.append([ "函数插件功能？",
         "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
+    
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
 
     # <-------------- check deps ------------->
     try:
@@ -180,13 +190,13 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
 
 
     # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_proofread.tex'):
+    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
         yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='proofread_latex', switch_prompt=switch_prompt)
+                                chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
 
 
     # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread', 
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en', 
                              work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
     
 
@@ -195,6 +205,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     if success:
         chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
         yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
     else:
         chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
         yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
@@ -278,6 +289,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     if success:
         chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
         yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
     else:
         chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
         yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面

crazy_functions/crazy_functions_test.py

@@ -188,7 +188,16 @@ def test_Latex():
     # txt = r"https://arxiv.org/abs/2305.17608"
     # txt = r"https://arxiv.org/abs/2211.16068"                     #  ACE
     # txt = r"C:\Users\x\arxiv_cache\2211.16068\workfolder"  #  ACE
-    txt = r"https://arxiv.org/abs/2002.09253"
+    # txt = r"https://arxiv.org/abs/2002.09253"
+    # txt = r"https://arxiv.org/abs/2306.07831"
+    # txt = r"https://arxiv.org/abs/2212.10156"
+    # txt = r"https://arxiv.org/abs/2211.11559"
+    # 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！
+    
+
     for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
         cli_printer.print(cb)   #  print(cb)
 
@@ -217,6 +226,7 @@ def test_Latex():
 # test_数学动画生成manim()
 # test_Langchain知识库()
 # test_Langchain知识库读取()
-test_Latex()
-input("程序完成，回车退出。")
-print("退出。")
+if __name__ == "__main__":
+    test_Latex()
+    input("程序完成，回车退出。")
+    print("退出。")

crazy_functions/crazy_utils.py

@@ -1,16 +1,19 @@
 from toolbox import update_ui, get_conf, trimmed_format_exc
 import threading
 
+
 def input_clipping(inputs, history, max_token_limit):
     import numpy as np
     from request_llm.bridge_all import model_info
     enc = model_info["gpt-3.5-turbo"]['tokenizer']
-    def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
+
+    def get_token_num(txt):
+        return len(enc.encode(txt, disallowed_special=()))
 
     mode = 'input-and-history'
     # 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
     input_token_num = get_token_num(inputs)
-    if input_token_num < max_token_limit//2: 
+    if input_token_num < max_token_limit // 2:
         mode = 'only-history'
         max_token_limit = max_token_limit - input_token_num
 
@@ -18,13 +21,13 @@ def input_clipping(inputs, history, max_token_limit):
     everything.extend(history)
     n_token = get_token_num('\n'.join(everything))
     everything_token = [get_token_num(e) for e in everything]
-    delta = max(everything_token) // 16 # 截断时的颗粒度
-        
+    delta = max(everything_token) // 16  # 截断时的颗粒度
+
     while n_token > max_token_limit:
         where = np.argmax(everything_token)
         encoded = enc.encode(everything[where], disallowed_special=())
-        clipped_encoded = encoded[:len(encoded)-delta]
-        everything[where] = enc.decode(clipped_encoded)[:-1]    # -1 to remove the may-be illegal char
+        clipped_encoded = encoded[:len(encoded) - delta]
+        everything[where] = enc.decode(clipped_encoded)[:-1]  # -1 to remove the may-be illegal char
         everything_token[where] = get_token_num(everything[where])
         n_token = get_token_num('\n'.join(everything))
 
@@ -35,12 +38,13 @@ def input_clipping(inputs, history, max_token_limit):
     history = everything[1:]
     return inputs, history
 
+
 def request_gpt_model_in_new_thread_with_ui_alive(
-        inputs, inputs_show_user, llm_kwargs, 
+        inputs, inputs_show_user, llm_kwargs,
         chatbot, history, sys_prompt, refresh_interval=0.2,
-        handle_token_exceed=True, 
+        handle_token_exceed=True,
         retry_times_at_unknown_error=2,
-        ):
+):
     """
     Request GPT model，请求GPT模型同时维持用户界面活跃。
 
@@ -64,15 +68,16 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     from request_llm.bridge_all import predict_no_ui_long_connection
     # 用户反馈
     chatbot.append([inputs_show_user, ""])
-    yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
     executor = ThreadPoolExecutor(max_workers=16)
     mutable = ["", time.time(), ""]
+
     def _req_gpt(inputs, history, sys_prompt):
         retry_op = retry_times_at_unknown_error
         exceeded_cnt = 0
         while True:
             # watchdog error
-            if len(mutable) >= 2 and (time.time()-mutable[1]) > 5: 
+            if len(mutable) >= 2 and (time.time() - mutable[1]) > 5:
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
@@ -89,14 +94,14 @@ def request_gpt_model_in_new_thread_with_ui_alive(
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
                     MAX_TOKEN = 4096
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
-                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
+                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN - EXCEED_ALLO)
                     mutable[0] += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
-                    continue # 返回重试
+                    continue  # 返回重试
                 else:
                     # 【选择放弃】
                     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
+                    return mutable[0]  # 放弃
             except:
                 # 【第三种情况】：其他错误：重试几次
                 tb_str = '```\n' + trimmed_format_exc() + '```'
@@ -104,14 +109,15 @@ def request_gpt_model_in_new_thread_with_ui_alive(
                 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:
                     retry_op -= 1
-                    mutable[0] += f"[Local Message] 重试中，请稍等 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}：\n\n"
+                    mutable[
+                        0] += f"[Local Message] 重试中，请稍等 {retry_times_at_unknown_error - retry_op}/{retry_times_at_unknown_error}：\n\n"
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
                         time.sleep(30)
                     time.sleep(5)
-                    continue # 返回重试
+                    continue  # 返回重试
                 else:
                     time.sleep(5)
-                    return mutable[0] # 放弃
+                    return mutable[0]  # 放弃
 
     # 提交任务
     future = executor.submit(_req_gpt, inputs, history, sys_prompt)
@@ -123,21 +129,21 @@ def request_gpt_model_in_new_thread_with_ui_alive(
         if future.done():
             break
         chatbot[-1] = [chatbot[-1][0], mutable[0]]
-        yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
 
     final_result = future.result()
     chatbot[-1] = [chatbot[-1][0], final_result]
-    yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
+    yield from update_ui(chatbot=chatbot, history=[])  # 如果最后成功了，则删除报错信息
     return final_result
 
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-        inputs_array, inputs_show_user_array, llm_kwargs, 
-        chatbot, history_array, sys_prompt_array, 
+        inputs_array, inputs_show_user_array, llm_kwargs,
+        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,
-        ):
+):
     """
     Request GPT model using multiple threads with UI and high efficiency
     请求GPT模型的[多线程]版。
@@ -170,19 +176,21 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     from request_llm.bridge_all import predict_no_ui_long_connection
     assert len(inputs_array) == len(history_array)
     assert len(inputs_array) == len(sys_prompt_array)
-    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 == -1:  # 读取配置文件
+        try:
+            max_workers, = get_conf('DEFAULT_WORKER_NUM')
+        except:
+            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
-        
+
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
     chatbot.append(["请开始多线程操作。", ""])
-    yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
     # 跨线程传递
     mutable = [["", time.time(), "等待中"] for _ in range(n_frag)]
 
@@ -194,13 +202,13 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         mutable[index][2] = "执行中"
         while True:
             # watchdog error
-            if len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > 5: 
+            if len(mutable[index]) >= 2 and (time.time() - mutable[index][1]) > 5:
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
                 # time.sleep(10); raise RuntimeError("测试")
                 gpt_say = predict_no_ui_long_connection(
-                    inputs=inputs, llm_kwargs=llm_kwargs, history=history, 
+                    inputs=inputs, llm_kwargs=llm_kwargs, history=history,
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
                 )
                 mutable[index][2] = "已成功"
@@ -214,24 +222,26 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
                     MAX_TOKEN = 4096
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
-                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
+                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN - EXCEED_ALLO)
                     gpt_say += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
                     mutable[index][2] = f"截断重试"
-                    continue # 返回重试
+                    continue  # 返回重试
                 else:
                     # 【选择放弃】
                     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]
+                    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:
+                    return gpt_say  # 放弃
+            except Exception as e:
                 # 【第三种情况】：其他错误
                 tb_str = '```\n' + trimmed_format_exc() + '```'
-                print(tb_str)
+                print(f"发生异常：{e}, 调用栈信息：{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]
-                if retry_op > 0: 
+                if len(mutable[index][0]) > 0:
+                    gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
+                if retry_op > 0:
                     retry_op -= 1
                     wait = random.randint(5, 20)
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
@@ -241,19 +251,22 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                         fail_info = ""
                     # 也许等待十几秒后，情况会好转
                     for i in range(wait):
-                        mutable[index][2] = f"{fail_info}等待重试 {wait-i}"; time.sleep(1)
+                        mutable[index][2] = f"{fail_info}等待重试 {wait - i}";
+                        time.sleep(1)
                     # 开始重试
-                    mutable[index][2] = f"重试中 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}"
-                    continue # 返回重试
+                    mutable[index][
+                        2] = f"重试中 {retry_times_at_unknown_error - retry_op}/{retry_times_at_unknown_error}"
+                    continue  # 返回重试
                 else:
                     mutable[index][2] = "已失败"
                     wait = 5
                     time.sleep(5)
-                    return gpt_say # 放弃
+                    return gpt_say  # 放弃
 
     # 异步任务开始
-    futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in zip(
-        range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
+    futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in
+               zip(
+                   range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
     cnt = 0
     while True:
         # yield一次以刷新前端页面
@@ -267,17 +280,17 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             mutable[thread_index][1] = time.time()
         # 在前端打印些好玩的东西
         for thread_index, _ in enumerate(worker_done):
-            print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
+            print_something_really_funny = "[ ...`" + mutable[thread_index][0][-scroller_max_len:]. \
                 replace('\n', '').replace('```', '...').replace(
-                    ' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
+                ' ', '.').replace('<br/>', '.....').replace('$', '.') + "`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
-        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n' 
-                            if not done else f'`{mutable[thread_index][2]}`\n\n' 
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
+                            if not done else f'`{mutable[thread_index][2]}`\n\n'
                             for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
         # 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
+        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
         if all(worker_done):
             executor.shutdown()
             break
@@ -287,13 +300,13 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     for inputs_show_user, f in zip(inputs_show_user_array, futures):
         gpt_res = f.result()
         gpt_response_collection.extend([inputs_show_user, gpt_res])
-    
+
     # 是否在结束时，在界面上显示结果
     if show_user_at_complete:
         for inputs_show_user, f in zip(inputs_show_user_array, futures):
             gpt_res = f.result()
             chatbot.append([inputs_show_user, gpt_res])
-            yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+            yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
             time.sleep(0.3)
     return gpt_response_collection
 
@@ -306,6 +319,7 @@ def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
             lines = txt_tocut.split('\n')
             estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
             estimated_line_cut = int(estimated_line_cut)
+            cnt = 0
             for cnt in reversed(range(estimated_line_cut)):
                 if must_break_at_empty_line:
                     if lines[cnt] != "":
@@ -322,6 +336,7 @@ def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
             result = [prev]
             result.extend(cut(post, must_break_at_empty_line))
             return result
+
     try:
         return cut(txt, must_break_at_empty_line=True)
     except RuntimeError:
@@ -337,9 +352,10 @@ def force_breakdown(txt, limit, get_token_fn):
             return txt[:i], txt[i:]
     return "Tiktoken未知错误", "Tiktoken未知错误"
 
+
 def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
     # 递归
-    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):  
+    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):
         if get_token_fn(txt_tocut) <= limit:
             return [txt_tocut]
         else:
@@ -365,6 +381,7 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
             result = [prev]
             result.extend(cut(post, must_break_at_empty_line, break_anyway=break_anyway))
             return result
+
     try:
         # 第1次尝试，将双空行（\n\n）作为切分点
         return cut(txt, must_break_at_empty_line=True)
@@ -375,7 +392,7 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
         except RuntimeError:
             try:
                 # 第3次尝试，将英文句号（.）作为切分点
-                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
+                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False)  # 这个中文的句号是故意的，作为一个标识而存在
                 return [r.replace('。\n', '.') for r in res]
             except RuntimeError as e:
                 try:
@@ -387,7 +404,6 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
                     return cut(txt, must_break_at_empty_line=False, break_anyway=True)
 
 
-
 def read_and_clean_pdf_text(fp):
     """
     这个函数用于分割pdf，用了很多trick，逻辑较乱，效果奇好
@@ -415,8 +431,9 @@ def read_and_clean_pdf_text(fp):
     fc = 0  # Index 0 文本
     fs = 1  # Index 1 字体
     fb = 2  # Index 2 框框
-    REMOVE_FOOT_NOTE = True # 是否丢弃掉 不是正文的内容 （比正文字体小，如参考文献、脚注、图注等）
-    REMOVE_FOOT_FFSIZE_PERCENT = 0.95 # 小于正文的？时，判定为不是正文（有些文章的正文部分字体大小不是100%统一的，有肉眼不可见的小变化）
+    REMOVE_FOOT_NOTE = True  # 是否丢弃掉 不是正文的内容 （比正文字体小，如参考文献、脚注、图注等）
+    REMOVE_FOOT_FFSIZE_PERCENT = 0.95  # 小于正文的？时，判定为不是正文（有些文章的正文部分字体大小不是100%统一的，有肉眼不可见的小变化）
+
     def primary_ffsize(l):
         """
         提取文本块主字体
@@ -426,12 +443,12 @@ def read_and_clean_pdf_text(fp):
             if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
             fsize_statiscs[wtf['size']] += len(wtf['text'])
         return max(fsize_statiscs, key=fsize_statiscs.get)
-        
-    def ffsize_same(a,b):
+
+    def ffsize_same(a, b):
         """
         提取字体大小是否近似相等
         """
-        return abs((a-b)/max(a,b)) < 0.02
+        return abs((a - b) / max(a, b)) < 0.02
 
     with fitz.open(fp) as doc:
         meta_txt = []
@@ -451,18 +468,19 @@ def read_and_clean_pdf_text(fp):
                         if len(txt_line) == 0: continue
                         pf = primary_ffsize(l)
                         meta_line.append([txt_line, pf, l['bbox'], l])
-                        for wtf in l['spans']: # for l in t['lines']:
+                        for wtf in l['spans']:  # for l in t['lines']:
                             meta_span.append([wtf['text'], wtf['size'], len(wtf['text'])])
                     # meta_line.append(["NEW_BLOCK", pf])
-            # 块元提取                           for each word segment with in line                       for each line         cross-line words                          for each block
+            # 块元提取                           for each word segment with in line                       for each line
+            # cross-line words                          for each block
             meta_txt.extend([" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
                 '- ', '') for t in text_areas['blocks'] if 'lines' in t])
             meta_font.extend([np.mean([np.mean([wtf['size'] for wtf in l['spans']])
-                             for l in t['lines']]) for t in text_areas['blocks'] if 'lines' in t])
+                                       for l in t['lines']]) for t in text_areas['blocks'] if 'lines' in t])
             if index == 0:
                 page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
                     '- ', '') for t in text_areas['blocks'] if 'lines' in t]
-                
+
         ############################## <第 2 步，获取正文主字体> ##################################
         fsize_statiscs = {}
         for span in meta_span:
@@ -476,32 +494,33 @@ def read_and_clean_pdf_text(fp):
         mega_sec = []
         sec = []
         for index, line in enumerate(meta_line):
-            if index == 0: 
+            if index == 0:
                 sec.append(line[fc])
                 continue
             if REMOVE_FOOT_NOTE:
                 if meta_line[index][fs] <= give_up_fize_threshold:
                     continue
-            if ffsize_same(meta_line[index][fs], meta_line[index-1][fs]):
+            if ffsize_same(meta_line[index][fs], meta_line[index - 1][fs]):
                 # 尝试识别段落
-                if meta_line[index][fc].endswith('.') and\
-                    (meta_line[index-1][fc] != 'NEW_BLOCK') and \
-                    (meta_line[index][fb][2] - meta_line[index][fb][0]) < (meta_line[index-1][fb][2] - meta_line[index-1][fb][0]) * 0.7:
+                if meta_line[index][fc].endswith('.') and \
+                        (meta_line[index - 1][fc] != 'NEW_BLOCK') and \
+                        (meta_line[index][fb][2] - meta_line[index][fb][0]) < (
+                        meta_line[index - 1][fb][2] - meta_line[index - 1][fb][0]) * 0.7:
                     sec[-1] += line[fc]
                     sec[-1] += "\n\n"
                 else:
                     sec[-1] += " "
                     sec[-1] += line[fc]
             else:
-                if (index+1 < len(meta_line)) and \
-                    meta_line[index][fs] > main_fsize:
+                if (index + 1 < len(meta_line)) and \
+                        meta_line[index][fs] > main_fsize:
                     # 单行 + 字体大
                     mega_sec.append(copy.deepcopy(sec))
                     sec = []
                     sec.append("# " + line[fc])
                 else:
                     # 尝试识别section
-                    if meta_line[index-1][fs] > meta_line[index][fs]:
+                    if meta_line[index - 1][fs] > meta_line[index][fs]:
                         sec.append("\n" + line[fc])
                     else:
                         sec.append(line[fc])
@@ -520,13 +539,15 @@ def read_and_clean_pdf_text(fp):
                 if len(block_txt) < 100:
                     meta_txt[index] = '\n'
             return meta_txt
+
         meta_txt = 把字符太少的块清除为回车(meta_txt)
 
         def 清理多余的空行(meta_txt):
             for index in reversed(range(1, len(meta_txt))):
-                if meta_txt[index] == '\n' and meta_txt[index-1] == '\n':
+                if meta_txt[index] == '\n' and meta_txt[index - 1] == '\n':
                     meta_txt.pop(index)
             return meta_txt
+
         meta_txt = 清理多余的空行(meta_txt)
 
         def 合并小写开头的段落块(meta_txt):
@@ -537,16 +558,18 @@ def read_and_clean_pdf_text(fp):
                     return True
                 else:
                     return False
+
             for _ in range(100):
                 for index, block_txt in enumerate(meta_txt):
                     if starts_with_lowercase_word(block_txt):
-                        if meta_txt[index-1] != '\n':
-                            meta_txt[index-1] += ' '
+                        if meta_txt[index - 1] != '\n':
+                            meta_txt[index - 1] += ' '
                         else:
-                            meta_txt[index-1] = ''
-                        meta_txt[index-1] += meta_txt[index]
+                            meta_txt[index - 1] = ''
+                        meta_txt[index - 1] += meta_txt[index]
                         meta_txt[index] = '\n'
             return meta_txt
+
         meta_txt = 合并小写开头的段落块(meta_txt)
         meta_txt = 清理多余的空行(meta_txt)
 
@@ -566,7 +589,7 @@ def read_and_clean_pdf_text(fp):
     return meta_txt, page_one_meta
 
 
-def get_files_from_everything(txt, type): # type='.md'
+def get_files_from_everything(txt, type):  # type='.md'
     """
     这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
     下面是对每个参数和返回值的说明：
@@ -588,9 +611,10 @@ def get_files_from_everything(txt, type): # type='.md'
         from toolbox import get_conf
         proxies, = get_conf('proxies')
         r = requests.get(txt, proxies=proxies)
-        with open('./gpt_log/temp'+type, 'wb+') as f: f.write(r.content)
+        with open('./gpt_log/temp' + type, 'wb+') as f:
+            f.write(r.content)
         project_folder = './gpt_log/'
-        file_manifest = ['./gpt_log/temp'+type]
+        file_manifest = ['./gpt_log/temp' + type]
     elif txt.endswith(type):
         # 直接给定文件
         file_manifest = [txt]
@@ -598,7 +622,7 @@ def get_files_from_everything(txt, type): # type='.md'
     elif os.path.exists(txt):
         # 本地路径，递归搜索
         project_folder = txt
-        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*'+type, recursive=True)]
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*' + type, recursive=True)]
         if len(file_manifest) == 0:
             success = False
     else:
@@ -609,16 +633,14 @@ def get_files_from_everything(txt, type): # type='.md'
     return success, file_manifest, project_folder
 
 
-
-
 def Singleton(cls):
     _instance = {}
- 
+
     def _singleton(*args, **kargs):
         if cls not in _instance:
             _instance[cls] = cls(*args, **kargs)
         return _instance[cls]
- 
+
     return _singleton
 
 
@@ -637,31 +659,30 @@ class knowledge_archive_interface():
             from toolbox import ProxyNetworkActivate
             print('Checking Text2vec ...')
             from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-            with ProxyNetworkActivate():    # 临时地激活代理网络
+            with ProxyNetworkActivate():  # 临时地激活代理网络
                 self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
 
         return self.text2vec_large_chinese
 
-
     def feed_archive(self, file_manifest, id="default"):
         self.threadLock.acquire()
         # import uuid
         self.current_id = id
         from zh_langchain import construct_vector_store
-        self.qa_handle, self.kai_path = construct_vector_store(   
-            vs_id=self.current_id, 
-            files=file_manifest, 
+        self.qa_handle, self.kai_path = construct_vector_store(
+            vs_id=self.current_id,
+            files=file_manifest,
             sentence_size=100,
             history=[],
             one_conent="",
             one_content_segmentation="",
-            text2vec = self.get_chinese_text2vec(),
+            text2vec=self.get_chinese_text2vec(),
         )
         self.threadLock.release()
 
     def get_current_archive_id(self):
         return self.current_id
-    
+
     def get_loaded_file(self):
         return self.qa_handle.get_loaded_file()
 
@@ -670,30 +691,31 @@ class knowledge_archive_interface():
         if not self.current_id == id:
             self.current_id = id
             from zh_langchain import construct_vector_store
-            self.qa_handle, self.kai_path = construct_vector_store(   
-                vs_id=self.current_id, 
-                files=[], 
+            self.qa_handle, self.kai_path = construct_vector_store(
+                vs_id=self.current_id,
+                files=[],
                 sentence_size=100,
                 history=[],
                 one_conent="",
                 one_content_segmentation="",
-                text2vec = self.get_chinese_text2vec(),
+                text2vec=self.get_chinese_text2vec(),
             )
         VECTOR_SEARCH_SCORE_THRESHOLD = 0
         VECTOR_SEARCH_TOP_K = 4
         CHUNK_SIZE = 512
         resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
-            query = txt,
-            vs_path = self.kai_path,
+            query=txt,
+            vs_path=self.kai_path,
             score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-            vector_search_top_k=VECTOR_SEARCH_TOP_K, 
+            vector_search_top_k=VECTOR_SEARCH_TOP_K,
             chunk_conent=True,
             chunk_size=CHUNK_SIZE,
-            text2vec = self.get_chinese_text2vec(),
+            text2vec=self.get_chinese_text2vec(),
         )
         self.threadLock.release()
         return resp, prompt
 
+
 def try_install_deps(deps):
     for dep in deps:
         import subprocess, sys

crazy_functions/latex_utils.py

@@ -8,24 +8,49 @@ pj = os.path.join
 """
 ========================================================================
 Part One
-Latex segmentation to a linklist
+Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
 ========================================================================
 """
 PRESERVE = 0
 TRANSFORM = 1
 
-def split_worker(text, mask, pattern, flags=0):
+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 split_worker_careful_brace(text, mask, pattern, flags=0):
+def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
     """
-    Move area into preserve area 
+    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):
@@ -40,9 +65,12 @@ def split_worker_careful_brace(text, mask, pattern, flags=0):
         mask[begin:end] = PRESERVE
     return text, mask
 
-def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
+def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
     """
-    Move area out of preserve area 
+    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):
@@ -55,9 +83,12 @@ def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
             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 split_worker_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
+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
@@ -110,19 +141,41 @@ 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
+    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') as f:
             file_content = f.read()
         if r'\documentclass' in file_content:
-            return texf
+            canidates.append(texf)
         else:
             continue
-    raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
 
+    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') 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():
@@ -132,6 +185,7 @@ def rm_comments(main_file):
         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
 
@@ -149,6 +203,7 @@ def merge_tex_files_(project_foler, main_file, mode):
                 c = fx.read()
         else:  
             # e.g., \input{srcs/07_appendix}
+            assert os.path.exists(fp+'.tex'), f'即找不到{fp}，也找不到{fp}.tex，Tex源文件缺失！'
             with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
                 c = fx.read()
         c = merge_tex_files_(project_foler, c, mode)
@@ -178,9 +233,11 @@ def merge_tex_files(project_foler, main_file, mode):
         main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
         main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
         # find paper abstract
-        pattern = re.compile(r'\\begin\{abstract\}.*\n')
-        match = pattern.search(main_file)
-        assert match is not None, "Cannot find paper abstract section!"
+        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
 
 
@@ -212,6 +269,8 @@ def fix_content(final_tex, node_string):
     final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
     final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
 
+    if "Traceback" in final_tex and "[Local Message]" in final_tex:
+        final_tex = node_string # 出问题了，还原原文
     if node_string.count('\\begin') != final_tex.count('\\begin'):
         final_tex = node_string # 出问题了，还原原文
     if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
@@ -259,45 +318,34 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
 
     # 吸收title与作者以上的部分
-    text, mask = split_worker(text, mask, r"(.*?)\\maketitle", re.DOTALL)
-    # 删除iffalse注释
-    text, mask = split_worker(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
-    # 吸收在25行以内的begin-end组合
-    text, mask = split_worker_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=25)
+    text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL)
+    # 吸收iffalse注释
+    text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
+    # 吸收在42行以内的begin-end组合
+    text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
     # 吸收匿名公式
-    text, mask = split_worker(text, mask, r"\$\$(.*?)\$\$", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [ r"\$\$(.*?)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
     # 吸收其他杂项
-    text, mask = split_worker(text, mask, r"\\section\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\section\*\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\subsection\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\subsubsection\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\bibliography\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\bibliographystyle\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{figure\}(.*?)\\end\{figure\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{multline\}(.*?)\\end\{multline\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{table\}(.*?)\\end\{table\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{table\*\}(.*?)\\end\{table\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{minipage\}(.*?)\\end\{minipage\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{align\*\}(.*?)\\end\{align\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{align\}(.*?)\\end\{align\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{equation\}(.*?)\\end\{equation\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}", re.DOTALL)
-    text, mask = split_worker(text, mask, r"\\item ")
-    text, mask = split_worker(text, mask, r"\\label\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\begin\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\vspace\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\hspace\{(.*?)\}")
-    text, mask = split_worker(text, mask, r"\\end\{(.*?)\}")
-    text, mask = split_worker_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
-    text, mask = split_worker_reverse_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [ r"\\section\{(.*?)\}", r"\\section\*\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, [ r"\\bibliography\{(.*?)\}", r"\\bibliographystyle\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{thebibliography\}.*?\\end\{thebibliography\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{figure\}(.*?)\\end\{figure\}", r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{multline\}(.*?)\\end\{multline\}", r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{table\}(.*?)\\end\{table\}", r"\\begin\{table\*\}(.*?)\\end\{table\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{minipage\}(.*?)\\end\{minipage\}", r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{align\*\}(.*?)\\end\{align\*\}", r"\\begin\{align\}(.*?)\\end\{align\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{equation\}(.*?)\\end\{equation\}", r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\includepdf\[(.*?)\]\{(.*?)\}", r"\\clearpage", r"\\newpage", r"\\appendix", r"\\tableofcontents", r"\\include\{(.*?)\}"])
+    text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item "])
+    text, mask = set_forbidden_text_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
+    # reverse 操作必须放在最后
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\abstract\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    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
@@ -371,7 +419,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
         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 = []
         nodes = []
@@ -402,7 +450,7 @@ class LatexPaperSplit():
     """
     def __init__(self) -> None:
         self.nodes = None
-        self.msg = "{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
+        self.msg = "*{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
             "版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
             "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
         # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
@@ -423,8 +471,14 @@ class LatexPaperSplit():
         if mode == 'translate_zh':
             pattern = re.compile(r'\\begin\{abstract\}.*\n')
             match = pattern.search(result_string)
-            assert match is not None, "Cannot find paper abstract section!"
-            position = match.end()
+            if not match:
+                # match \abstract{xxxx}
+                pattern_compile = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
+                match = pattern_compile.search(result_string)
+                position = match.regs[1][0]
+            else:
+                # match \begin{abstract}xxxx\end{abstract}
+                position = match.end()
             result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
         return result_string
 
@@ -443,6 +497,7 @@ class LatexPaperSplit():
             args=(txt, project_folder, return_dict, opts))
         p.start()
         p.join()
+        p.close()
         self.nodes = return_dict['nodes']
         self.sp = return_dict['segment_parts_for_gpt']
         return self.sp
@@ -497,11 +552,11 @@ class LatexPaperFileGroup():
                 f.write(res)
         return manifest
 
-def write_html(sp_file_contents, sp_file_result, chatbot):
+def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
 
     # write html
     try:
-        import copy
+        import shutil
         from .crazy_utils import construct_html
         from toolbox import gen_time_str
         ch = construct_html() 
@@ -519,6 +574,7 @@ def write_html(sp_file_contents, sp_file_result, chatbot):
                 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
@@ -599,7 +655,7 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
         pfg.get_token_num = None
         objdump(pfg, file=pj(project_folder,'temp.pkl'))
 
-    write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot)
+    write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
 
     #  <-------- 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']}。"
@@ -636,10 +692,9 @@ def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work
         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, timeout=60):
+def compile_latex_with_timeout(command, cwd, timeout=60):
     import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
     try:
         stdout, stderr = process.communicate(timeout=timeout)
     except subprocess.TimeoutExpired:
@@ -663,24 +718,24 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
         # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
-        os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
 
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
-        os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
         
         if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
             # 只有第二步成功，才能继续下面的步骤
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
             if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
-                os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
             if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
-                os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
 
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
-            os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
-            os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
 
             if mode!='translate_zh':
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
@@ -688,13 +743,11 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
 
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
-                os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
+                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)
 
-        # <--------------------->
-        os.chdir(current_dir)
 
         # <---------- 检查结果 ----------->
         results_ = ""
@@ -706,13 +759,15 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
         results_ += f"对比PDF编译是否成功: {diff_pdf_success};" 
         yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
 
+        if diff_pdf_success:
+            result_pdf = pj(work_folder_modified, f'merge_diff.pdf')    # get pdf path
+            promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
         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
-            os.chdir(current_dir)
-            result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
+            result_pdf = pj(work_folder_modified, f'{main_file_modified}.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_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
             return True # 成功啦
         else:
             if n_fix>=max_try: break
@@ -728,7 +783,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
             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
 
-    os.chdir(current_dir)
     return False # 失败啦
 
 

crazy_functions/图片生成.py

@@ -27,8 +27,10 @@ def gen_image(llm_kwargs, prompt, resolution="256x256"):
     }
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
     print(response.content)
-    image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
-
+    try:
+        image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
+    except:
+        raise RuntimeError(response.content.decode())
     # 文件保存到本地
     r = requests.get(image_url, proxies=proxies)
     file_path = 'gpt_log/image_gen/'

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, report_execption, write_results_to_file
-from toolbox import update_ui
+from toolbox import update_ui, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 from .crazy_utils import read_and_clean_pdf_text
@@ -147,23 +147,14 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
             print('writing html result failed:', trimmed_format_exc())
 
     # 准备文件的下载
-    import shutil
     for pdf_path in generated_conclusion_files:
         # 重命名文件
-        rename_file = f'./gpt_log/翻译-{os.path.basename(pdf_path)}'
-        if os.path.exists(rename_file):
-            os.remove(rename_file)
-        shutil.copyfile(pdf_path, rename_file)
-        if os.path.exists(pdf_path):
-            os.remove(pdf_path)
+        rename_file = f'翻译-{os.path.basename(pdf_path)}'
+        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
     for html_path in generated_html_files:
         # 重命名文件
-        rename_file = f'./gpt_log/翻译-{os.path.basename(html_path)}'
-        if os.path.exists(rename_file):
-            os.remove(rename_file)
-        shutil.copyfile(html_path, rename_file)
-        if os.path.exists(html_path):
-            os.remove(html_path)
+        rename_file = f'翻译-{os.path.basename(html_path)}'
+        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
     chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 

crazy_functions/理解PDF文档内容.py

@@ -13,7 +13,9 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
     # 的长度必须小于 2500 个 Token
     file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
-
+    file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+    page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
+    
     TOKEN_LIMIT_PER_FRAGMENT = 2500
 
     from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf

crazy_functions/联网的ChatGPT_bing版.py

@@ -0,0 +1,102 @@
+from toolbox import CatchException, update_ui
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
+import requests
+from bs4 import BeautifulSoup
+from request_llm.bridge_all import model_info
+
+
+def bing_search(query, proxies=None):
+    query = query
+    url = f"https://cn.bing.com/search?q={query}"
+    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36'}
+    response = requests.get(url, headers=headers, proxies=proxies)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    results = []
+    for g in soup.find_all('li', class_='b_algo'):
+        anchors = g.find_all('a')
+        if anchors:
+            link = anchors[0]['href']
+            if not link.startswith('http'):
+                continue
+            title = g.find('h2').text
+            item = {'title': title, 'link': link}
+            results.append(item)
+
+    for r in results:
+        print(r['link'])
+    return results
+
+
+def scrape_text(url, proxies) -> str:
+    """Scrape text from a webpage
+
+    Args:
+        url (str): The URL to scrape text from
+
+    Returns:
+        str: The scraped text
+    """
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
+        'Content-Type': 'text/plain',
+    }
+    try:
+        response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
+        if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
+    except:
+        return "无法连接到该网页"
+    soup = BeautifulSoup(response.text, "html.parser")
+    for script in soup(["script", "style"]):
+        script.extract()
+    text = soup.get_text()
+    lines = (line.strip() for line in text.splitlines())
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    text = "\n".join(chunk for chunk in chunks if chunk)
+    return text
+
+@CatchException
+def 连接bing搜索回答问题(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
+    """
+    history = []    # 清空历史，以免输入溢出
+    chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
+                    "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板。您若希望分享新的功能模组，请不吝PR！"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
+
+    # ------------- < 第1步：爬取搜索引擎的结果 > -------------
+    from toolbox import get_conf
+    proxies, = get_conf('proxies')
+    urls = bing_search(txt, proxies)
+    history = []
+
+    # ------------- < 第2步：依次访问网页 > -------------
+    max_search_result = 8   # 最多收纳多少个网页的结果
+    for index, url in enumerate(urls[:max_search_result]):
+        res = scrape_text(url['link'], proxies)
+        history.extend([f"第{index}份搜索结果：", res])
+        chatbot.append([f"第{index}份搜索结果：", res[:500]+"......"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
+
+    # ------------- < 第3步：ChatGPT综合 > -------------
+    i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
+    i_say, history = input_clipping(    # 裁剪输入，从最长的条目开始裁剪，防止爆token
+        inputs=i_say,
+        history=history,
+        max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
+    )
+    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=history,
+        sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
+    )
+    chatbot[-1] = (i_say, gpt_say)
+    history.append(i_say);history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+

crazy_functions/读文章写摘要.py

@@ -1,67 +1,78 @@
-from toolbox import update_ui
 from toolbox import CatchException, report_execption, write_results_to_file
+from toolbox import update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
 fast_debug = False
 
 
 def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    import time, glob, os
+    import time
+    import os
     print('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
         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论文文件，概括其内容" if index==0 else ""
+        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index == 0 else ""
         i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
         i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
-        if not fast_debug: 
+        if not fast_debug:
             msg = '正常'
             # ** gpt request **
-            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs, chatbot, history=[], sys_prompt=system_prompt)   # 带超时倒计时
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs,
+                                                                               chatbot, history=[],
+                                                                               sys_prompt=system_prompt)  # 带超时倒计时
 
             chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+            history.append(i_say_show_user);
+            history.append(gpt_say)
+            yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
             if not fast_debug: time.sleep(2)
 
     all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
     i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
     chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
-    if not fast_debug: 
+    if not fast_debug:
         msg = '正常'
         # ** gpt request **
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot, history=history, sys_prompt=system_prompt)   # 带超时倒计时
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot,
+                                                                           history=history,
+                                                                           sys_prompt=system_prompt)  # 带超时倒计时
 
         chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+        history.append(i_say)
+        history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
         res = write_results_to_file(history)
         chatbot.append(("完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-
+        yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
 
 
 @CatchException
-def 读文章写摘要(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
+def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, system_prompt, web_port, history=None):
+    # history = []    # 清空历史，以免输入溢出
+    if history is None:
+        history = []  # 清空历史，以免输入溢出
+    import glob
+    import 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
+        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}/**/*.tex', recursive=True)] # + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]  # + \
+    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
+    # [f for f in glob.glob(f'{project_folder}/**/*.c', 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.tex文件: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
     yield from 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/辅助回答.py

@@ -0,0 +1,28 @@
+# encoding: utf-8
+# @Time   : 2023/4/19
+# @Author : Spike
+# @Descr   :
+from toolbox import update_ui
+from toolbox import CatchException, report_execption, write_results_to_file
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+
+@CatchException
+def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    if txt:
+        show_say = txt
+        prompt = txt+'\n回答完问题后，再列出用户可能提出的三个问题。'
+    else:
+        prompt = history[-1]+"\n分析上述回答，再列出用户可能提出的三个问题。"
+        show_say = '分析上述回答，再列出用户可能提出的三个问题。'
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt,
+        inputs_show_user=show_say,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history=history,
+        sys_prompt=system_prompt
+    )
+    chatbot[-1] = (show_say, gpt_say)
+    history.extend([show_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面

crazy_functions/高级功能函数模板.py

@@ -1,6 +1,7 @@
 from toolbox import CatchException, update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime
+import datetime, re
+
 @CatchException
 def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
     """
@@ -18,12 +19,34 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     for i in range(5):
         currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
         currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
-        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
+        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？用中文列举两条，然后分别给出描述事件的两个英文单词。' + '当你给出关键词时，使用以下json格式：{"KeyWords":[EnglishKeyWord1,EnglishKeyWord2]}。'
         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=[], 
-            sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
+            sys_prompt='输出格式示例：1908年，美国消防救援事业发展的“美国消防协会”成立。关键词：{"KeyWords":["Fire","American"]}。'
         )
+        gpt_say = get_images(gpt_say)
         chatbot[-1] = (i_say, gpt_say)
         history.append(i_say);history.append(gpt_say)
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+
+def get_images(gpt_say):
+    def get_image_by_keyword(keyword):
+        import requests
+        from bs4 import BeautifulSoup
+        response = requests.get(f'https://wallhaven.cc/search?q={keyword}', timeout=2)
+        for image_element in BeautifulSoup(response.content, 'html.parser').findAll("img"):
+            if "data-src" in image_element: break
+        return image_element["data-src"]
+
+    for keywords in re.findall('{"KeyWords":\[(.*?)\]}', gpt_say):
+        keywords = [n.strip('"') for n in keywords.split(',')]
+        try:
+            description = keywords[0]
+            url = get_image_by_keyword(keywords[0])
+            img_tag = f"\n\n![{description}]({url})"
+            gpt_say += img_tag
+        except:
+            continue
+    return gpt_say

docker-compose.yml

@@ -103,3 +103,30 @@ services:
                       echo '[jittorllms] 正在从github拉取最新代码...' &&
                       git --git-dir=request_llm/jittorllms/.git --work-tree=request_llm/jittorllms pull --force &&
                       python3 -u main.py"
+
+
+## ===================================================
+## 【方案四】 chatgpt + Latex
+## ===================================================
+version: '3'
+services:
+  gpt_academic_with_latex:
+    image: ghcr.io/binary-husky/gpt_academic_with_latex:master
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                              '
+      USE_PROXY:                '    True                                                                             '
+      proxies:                  '    { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", }   '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                                    '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "gpt-4"]                                                       '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                                             '
+      DEFAULT_WORKER_NUM:       '    10                                                                               '
+      WEB_PORT:                 '    12303                                                                            '
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      bash -c "python3 -u main.py"
+

docs/use_azure.md

@@ -0,0 +1,152 @@
+# 通过微软Azure云服务申请 Openai API
+
+由于Openai和微软的关系，现在是可以通过微软的Azure云计算服务直接访问openai的api，免去了注册和网络的问题。
+
+快速入门的官方文档的链接是：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
+
+# 申请API
+
+按文档中的“先决条件”的介绍，出了编程的环境以外，还需要以下三个条件：
+
+1.  Azure账号并创建订阅
+
+2.  为订阅添加Azure OpenAI 服务
+
+3.  部署模型
+
+## Azure账号并创建订阅
+
+### Azure账号
+
+创建Azure的账号时最好是有微软的账号，这样似乎更容易获得免费额度（第一个月的200美元，实测了一下，如果用一个刚注册的微软账号登录Azure的话，并没有这一个月的免费额度）。
+
+创建Azure账号的网址是：[立即创建 Azure 免费帐户 | Microsoft Azure](https://azure.microsoft.com/zh-cn/free/)
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_944786_iH6AECuZ_tY0EaBd_1685327219?w=1327\&h=695\&type=image/png)
+
+打开网页后，点击 “免费开始使用” 会跳转到登录或注册页面，如果有微软的账户，直接登录即可，如果没有微软账户，那就需要到微软的网页再另行注册一个。
+
+注意，Azure的页面和政策时不时会变化，已实际最新显示的为准就好。
+
+### 创建订阅
+
+注册好Azure后便可进入主页：
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_444847_tk-9S-pxOYuaLs_K_1685327675?w=1865\&h=969\&type=image/png)
+
+首先需要在订阅里进行添加操作，点开后即可进入订阅的页面：
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_612820_z_1AlaEgnJR-rUl0_1685327892?w=1865\&h=969\&type=image/png)
+
+第一次进来应该是空的，点添加即可创建新的订阅（可以是“免费”或者“即付即用”的订阅），其中订阅ID是后面申请Azure OpenAI需要使用的。
+
+## 为订阅添加Azure OpenAI服务
+
+之后回到首页，点Azure OpenAI即可进入OpenAI服务的页面（如果不显示的话，则在首页上方的搜索栏里搜索“openai”即可）。
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_269759_nExkGcPC0EuAR5cp_1685328130?w=1865\&h=969\&type=image/png)
+
+不过现在这个服务还不能用。在使用前，还需要在这个网址申请一下：
+
+[Request Access to Azure OpenAI Service (microsoft.com)](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOFA5Qk1UWDRBMjg0WFhPMkIzTzhKQ1dWNyQlQCN0PWcu)
+
+这里有二十来个问题，按照要求和自己的实际情况填写即可。
+
+其中需要注意的是
+
+1.  千万记得填对"订阅ID"
+
+2.  需要填一个公司邮箱（可以不是注册用的邮箱）和公司网址
+
+之后，在回到上面那个页面，点创建，就会进入创建页面了：
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_72708_9d9JYhylPVz3dFWL_1685328372?w=824\&h=590\&type=image/png)
+
+需要填入“资源组”和“名称”，按照自己的需要填入即可。
+
+完成后，在主页的“资源”里就可以看到刚才创建的“资源”了，点击进入后，就可以进行最后的部署了。
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_871541_CGCnbgtV9Uk1Jccy_1685329861?w=1217\&h=628\&type=image/png)
+
+## 部署模型
+
+进入资源页面后，在部署模型前，可以先点击“开发”，把密钥和终结点记下来。
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_852567_dxCZOrkMlWDSLH0d_1685330736?w=856\&h=568\&type=image/png)
+
+之后，就可以去部署模型了，点击“部署”即可，会跳转到 Azure OpenAI Stuido 进行下面的操作：
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_169225_uWs1gMhpNbnwW4h2_1685329901?w=1865\&h=969\&type=image/png)
+
+进入 Azure OpenAi Studio 后，点击新建部署，会弹出如下对话框：
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_391255_iXUSZAzoud5qlxjJ_1685330224?w=656\&h=641\&type=image/png)
+
+在这里选 gpt-35-turbo 或需要的模型并按需要填入“部署名”即可完成模型的部署。
+
+![](https://wdcdn.qpic.cn/MTY4ODg1Mjk4NzI5NTU1NQ_724099_vBaHcUilsm1EtPgK_1685330396?w=1869\&h=482\&type=image/png)
+
+这个部署名需要记下来。
+
+到现在为止，申请操作就完成了，需要记下来的有下面几个东西：
+
+● 密钥（1或2都可以）
+
+● 终结点
+
+● 部署名（不是模型名）
+
+# 修改 config.py
+
+```
+AZURE_ENDPOINT = "填入终结点"
+AZURE_API_KEY = "填入azure openai api的密钥"
+AZURE_API_VERSION = "2023-05-15"  # 默认使用 2023-05-15 版本，无需修改
+AZURE_ENGINE = "填入部署名"
+
+```
+# API的使用
+
+接下来就是具体怎么使用API了，还是可以参考官方文档：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
+
+和openai自己的api调用有点类似，都需要安装openai库，不同的是调用方式
+
+```
+import openai
+openai.api_type = "azure" #固定格式，无需修改
+openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") #这里填入“终结点”
+openai.api_version = "2023-05-15" #固定格式，无需修改
+openai.api_key = os.getenv("AZURE_OPENAI_KEY") #这里填入“密钥1”或“密钥2”
+
+response = openai.ChatCompletion.create(
+    engine="gpt-35-turbo", #这里填入的不是模型名，是部署名
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
+        {"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
+        {"role": "user", "content": "Do other Azure Cognitive Services support this too?"}
+    ]
+)
+
+print(response)
+print(response['choices'][0]['message']['content'])
+
+```
+
+需要注意的是：
+
+1.  engine那里填入的是部署名，不是模型名
+
+2.  通过openai库获得的这个 response 和通过 request 库访问 url 获得的 response 不同，不需要 decode，已经是解析好的 json 了，直接根据键值读取即可。
+
+更细节的使用方法，详见官方API文档。
+
+# 关于费用
+
+Azure OpenAI API 还是需要一些费用的（免费订阅只有1个月有效期），费用如下：
+
+![image.png](https://note.youdao.com/yws/res/18095/WEBRESOURCEeba0ab6d3127b79e143ef2d5627c0e44)
+
+具体可以可以看这个网址 ：[Azure OpenAI 服务 - 定价| Microsoft Azure](https://azure.microsoft.com/zh-cn/pricing/details/cognitive-services/openai-service/?cdn=disable)
+
+并非网上说的什么“一年白嫖”，但注册方法以及网络问题都比直接使用openai的api要简单一些。

main.py

@@ -6,8 +6,8 @@ def main():
     from request_llm.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 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
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS')
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
+        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
 
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
@@ -104,7 +104,7 @@ def main():
                     system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
                     top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
                     temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
-                    max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="Local LLM MaxLength",)
+                    max_length_sl = gr.Slider(minimum=256, maximum=8192, value=4096, step=1, interactive=True, label="Local LLM MaxLength",)
                     checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
                     md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
 
@@ -144,6 +144,11 @@ def main():
         resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
         clearBtn.click(lambda: ("",""), None, [txt, txt2])
         clearBtn2.click(lambda: ("",""), None, [txt, txt2])
+        if AUTO_CLEAR_TXT:
+            submitBtn.click(lambda: ("",""), None, [txt, txt2])
+            submitBtn2.click(lambda: ("",""), None, [txt, txt2])
+            txt.submit(lambda: ("",""), None, [txt, txt2])
+            txt2.submit(lambda: ("",""), None, [txt, txt2])
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue

request_llm/bridge_all.py

@@ -16,6 +16,9 @@ from toolbox import get_conf, trimmed_format_exc
 from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
 from .bridge_chatgpt import predict as chatgpt_ui
 
+from .bridge_azure_test import predict_no_ui_long_connection as azure_noui
+from .bridge_azure_test import predict as azure_ui
+
 from .bridge_chatglm import predict_no_ui_long_connection as chatglm_noui
 from .bridge_chatglm import predict as chatglm_ui
 
@@ -93,6 +96,24 @@ model_info = {
         "token_cnt": get_token_num_gpt35,
     },
 
+    "gpt-3.5-turbo-0613": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 4096,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    "gpt-3.5-turbo-16k-0613": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 1024 * 16,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     "gpt-4": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -102,6 +123,16 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    # azure openai
+    "azure-gpt35":{
+        "fn_with_ui": azure_ui,
+        "fn_without_ui": azure_noui,
+        "endpoint": get_conf("AZURE_ENDPOINT"),
+        "max_token": 4096,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     # api_2d
     "api2d-gpt-3.5-turbo": {
         "fn_with_ui": chatgpt_ui,
@@ -121,7 +152,7 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # chatglm
+    # 将 chatglm 直接对齐到 chatglm2
     "chatglm": {
         "fn_with_ui": chatglm_ui,
         "fn_without_ui": chatglm_noui,
@@ -130,6 +161,15 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    "chatglm2": {
+        "fn_with_ui": chatglm_ui,
+        "fn_without_ui": chatglm_noui,
+        "endpoint": None,
+        "max_token": 1024,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    
     # newbing
     "newbing": {
         "fn_with_ui": newbing_ui,

request_llm/bridge_azure_test.py

@@ -0,0 +1,241 @@
+"""
+    该文件中主要包含三个函数
+
+    不具备多线程能力的函数：
+    1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
+
+    具备多线程调用能力的函数
+    2. predict_no_ui：高级实验性功能模块调用，不会实时显示在界面上，参数简单，可以多线程并行，方便实现复杂的功能逻辑
+    3. predict_no_ui_long_connection：在实验过程中发现调用predict_no_ui处理长文档时，和openai的连接容易断掉，这个函数用stream的方式解决这个问题，同样支持多线程
+"""
+
+import logging
+import traceback
+import importlib
+import openai
+import time
+
+
+# 读取config.py文件中关于AZURE OPENAI API的信息
+from toolbox import get_conf, update_ui, clip_history, trimmed_format_exc
+TIMEOUT_SECONDS, MAX_RETRY, AZURE_ENGINE, AZURE_ENDPOINT, AZURE_API_VERSION, AZURE_API_KEY = \
+    get_conf('TIMEOUT_SECONDS', 'MAX_RETRY',"AZURE_ENGINE","AZURE_ENDPOINT", "AZURE_API_VERSION", "AZURE_API_KEY")
+
+
+def get_full_error(chunk, stream_response):
+    """
+        获取完整的从Openai返回的报错
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+    发送至azure openai api，流式获取输出。
+    用于基础的对话功能。
+    inputs 是本次问询的输入
+    top_p, temperature是chatGPT的内部调优参数
+    history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
+    chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
+    additional_fn代表点击的哪个按钮，按钮见functional.py
+    """
+    print(llm_kwargs["llm_model"])    
+
+    if additional_fn is not None:
+        import core_functional
+        importlib.reload(core_functional)    # 热更新prompt
+        core_functional = core_functional.get_core_functions()
+        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
+        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+
+    raw_input = inputs
+    logging.info(f'[raw_input] {raw_input}')
+    chatbot.append((inputs, ""))
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+
+    
+    payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream)    
+        
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:            
+                
+            openai.api_type = "azure"            
+            openai.api_version = AZURE_API_VERSION
+            openai.api_base = AZURE_ENDPOINT
+            openai.api_key = AZURE_API_KEY
+            response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
+        
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], "获取response失败，重试中。。。"))
+            retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
+            yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
+            if retry > MAX_RETRY: raise TimeoutError
+            
+    gpt_replying_buffer = ""    
+    is_head_of_the_stream = True
+    if stream:
+
+        stream_response = response
+
+        while True:
+            try:
+                chunk = next(stream_response)
+                    
+            except StopIteration:                
+                from toolbox import regular_txt_to_markdown; tb_str = '```\n' + trimmed_format_exc() + '```'
+                chatbot[-1] = (chatbot[-1][0], f"[Local Message] 远程返回错误: \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk)}")
+                yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk) # 刷新界面
+                return            
+            
+            if is_head_of_the_stream and (r'"object":"error"' not in chunk):
+                # 数据流的第一帧不携带content
+                is_head_of_the_stream = False; continue
+            
+            if chunk:
+                #print(chunk)
+                try:                     
+                    if "delta" in chunk["choices"][0]:
+                        if chunk["choices"][0]["finish_reason"] == "stop":
+                            logging.info(f'[response] {gpt_replying_buffer}')
+                            break
+                    status_text = f"finish_reason: {chunk['choices'][0]['finish_reason']}"    
+                    gpt_replying_buffer = gpt_replying_buffer + chunk["choices"][0]["delta"]["content"]                               
+                       
+                    history[-1] = gpt_replying_buffer
+                    chatbot[-1] = (history[-2], history[-1])
+                    yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
+
+                except Exception as e:
+                    traceback.print_exc()
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
+                    chunk = get_full_error(chunk, stream_response)
+                    
+                    error_msg = chunk                    
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    return
+
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+    """
+    发送至AZURE OPENAI API，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
+    inputs：
+        是本次问询的输入
+    sys_prompt:
+        系统静默prompt
+    llm_kwargs：
+        chatGPT的内部调优参数
+    history：
+        是之前的对话列表
+    observe_window = None：
+        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
+    """
+    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
+    payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    while True:
+
+        try:
+            openai.api_type = "azure"            
+            openai.api_version = AZURE_API_VERSION
+            openai.api_base = AZURE_ENDPOINT
+            openai.api_key = AZURE_API_KEY
+            response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
+        
+        except:  
+            retry += 1
+            traceback.print_exc()
+            if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')     
+        
+
+    stream_response =  response
+    result = ''
+    while True:
+        try: chunk = next(stream_response)
+        except StopIteration: 
+            break
+        except:
+            chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+
+        if len(chunk)==0: continue
+        if not chunk.startswith('data:'): 
+            error_msg = get_full_error(chunk, stream_response)
+            if "reduce the length" in error_msg:
+                raise ConnectionAbortedError("AZURE OPENAI API拒绝了请求:" + error_msg)
+            else:
+                raise RuntimeError("AZURE OPENAI API拒绝了请求：" + error_msg)
+        if ('data: [DONE]' in chunk): break 
+        
+        delta = chunk["delta"]
+        if len(delta) == 0: break
+        if "role" in delta: continue
+        if "content" in delta: 
+            result += delta["content"]
+            if not console_slience: print(delta["content"], end='')
+            if observe_window is not None: 
+                # 观测窗，把已经获取的数据显示出去
+                if len(observe_window) >= 1: observe_window[0] += delta["content"]
+                # 看门狗，如果超过期限没有喂狗，则终止
+                if len(observe_window) >= 2:  
+                    if (time.time()-observe_window[1]) > watch_dog_patience:
+                        raise RuntimeError("用户取消了程序。")
+        else: raise RuntimeError("意外Json结构："+delta)
+    if chunk['finish_reason'] == 'length':
+        raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
+    return result
+
+
+def generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream):
+    """
+    整合所有信息，选择LLM模型，生成 azure openai api请求，为发送请求做准备
+    """    
+
+    conversation_cnt = len(history) // 2
+
+    messages = [{"role": "system", "content": system_prompt}]
+    if conversation_cnt:
+        for index in range(0, 2*conversation_cnt, 2):
+            what_i_have_asked = {}
+            what_i_have_asked["role"] = "user"
+            what_i_have_asked["content"] = history[index]
+            what_gpt_answer = {}
+            what_gpt_answer["role"] = "assistant"
+            what_gpt_answer["content"] = history[index+1]
+            if what_i_have_asked["content"] != "":
+                if what_gpt_answer["content"] == "": continue                
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+            else:
+                messages[-1]['content'] = what_gpt_answer['content']
+
+    what_i_ask_now = {}
+    what_i_ask_now["role"] = "user"
+    what_i_ask_now["content"] = inputs
+    messages.append(what_i_ask_now)
+
+    payload = {
+        "model": llm_kwargs['llm_model'],
+        "messages": messages, 
+        "temperature": llm_kwargs['temperature'],  # 1.0,
+        "top_p": llm_kwargs['top_p'],  # 1.0,
+        "n": 1,
+        "stream": stream,
+        "presence_penalty": 0,
+        "frequency_penalty": 0,
+        "engine": AZURE_ENGINE
+    }
+    try:
+        print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
+    except:
+        print('输入中可能存在乱码。')
+    return payload
+
+

request_llm/bridge_chatglm.py

@@ -40,12 +40,12 @@ class GetGLMHandle(Process):
         while True:
             try:
                 if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
                     device, = get_conf('LOCAL_MODEL_DEVICE')
                     if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
                     self.chatglm_model = self.chatglm_model.eval()
                     break
                 else:

request_llm/bridge_chatgpt.py

@@ -28,6 +28,7 @@ proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \
 timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
                   '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
 
+
 def get_full_error(chunk, stream_response):
     """
         获取完整的从Openai返回的报错
@@ -40,7 +41,9 @@ def get_full_error(chunk, stream_response):
     return chunk
 
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+def predict_no_ui_long_connection(
+        inputs, llm_kwargs, history=None, sys_prompt="", observe_window=None, console_slience=False
+):
     """
     发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
     inputs：
@@ -54,45 +57,59 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     observe_window = None：
         用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
     """
-    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
+    if history is None:
+        history = []
+    watch_dog_patience = 5  # 看门狗的耐心, 设置5秒即可
     headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
     retry = 0
+    from bridge_all import model_info
     while True:
         try:
             # make a POST request to the API endpoint, stream=False
-            from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
             response = requests.post(endpoint, headers=headers, proxies=proxies,
-                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
-        except requests.exceptions.ReadTimeout as e:
+                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS)
+            stream_response = response.iter_lines()
+            break
+        except (requests.exceptions.ReadTimeout, requests.exceptions.ConnectionError):
             retry += 1
             traceback.print_exc()
-            if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+            if retry > MAX_RETRY:
+                raise TimeoutError
+            if MAX_RETRY != 0:
+                print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+        except Exception as e:
+            print(f"出现异常：{e}")
+            raise e
 
-    stream_response =  response.iter_lines()
     result = ''
     while True:
-        try: chunk = next(stream_response).decode()
+        try:
+            chunk = next(stream_response).decode()
         except StopIteration: 
             break
-        except requests.exceptions.ConnectionError:
-            chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。
-        if len(chunk)==0: continue
+        # except requests.exceptions.ConnectionError:
+        #     chunk = next(stream_response).decode()  # 失败了，重试一次？再失败就没办法了。
+        if len(chunk) == 0:
+            continue
         if not chunk.startswith('data:'): 
             error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
             else:
                 raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
-        if ('data: [DONE]' in chunk): break # api2d 正常完成
+        if 'data: [DONE]' in chunk:
+            break  # api2d 正常完成
         json_data = json.loads(chunk.lstrip('data:'))['choices'][0]
         delta = json_data["delta"]
-        if len(delta) == 0: break
-        if "role" in delta: continue
+        if len(delta) == 0:
+            break
+        if "role" in delta:
+            continue
         if "content" in delta: 
             result += delta["content"]
-            if not console_slience: print(delta["content"], end='')
+            if not console_slience:
+                print(delta["content"], end='')
             if observe_window is not None: 
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1: observe_window[0] += delta["content"]
@@ -100,7 +117,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                 if len(observe_window) >= 2:  
                     if (time.time()-observe_window[1]) > watch_dog_patience:
                         raise RuntimeError("用户取消了程序。")
-        else: raise RuntimeError("意外Json结构："+delta)
+        else:
+            raise RuntimeError("意外Json结构："+delta)
     if json_data['finish_reason'] == 'length':
         raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
     return result
@@ -228,6 +246,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
                     return
 
+
 def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     """
     整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
@@ -247,23 +266,19 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     messages = [{"role": "system", "content": system_prompt}]
     if conversation_cnt:
         for index in range(0, 2*conversation_cnt, 2):
-            what_i_have_asked = {}
-            what_i_have_asked["role"] = "user"
-            what_i_have_asked["content"] = history[index]
-            what_gpt_answer = {}
-            what_gpt_answer["role"] = "assistant"
-            what_gpt_answer["content"] = history[index+1]
+            what_i_have_asked = {"role": "user", "content": history[index]}
+            what_gpt_answer = {"role": "assistant", "content": history[index + 1]}
             if what_i_have_asked["content"] != "":
-                if what_gpt_answer["content"] == "": continue
-                if what_gpt_answer["content"] == timeout_bot_msg: continue
+                if what_gpt_answer["content"] == "":
+                    continue
+                if what_gpt_answer["content"] == timeout_bot_msg:
+                    continue
                 messages.append(what_i_have_asked)
                 messages.append(what_gpt_answer)
             else:
                 messages[-1]['content'] = what_gpt_answer['content']
 
-    what_i_ask_now = {}
-    what_i_ask_now["role"] = "user"
-    what_i_ask_now["content"] = inputs
+    what_i_ask_now = {"role": "user", "content": inputs}
     messages.append(what_i_ask_now)
 
     payload = {
@@ -278,8 +293,8 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     }
     try:
         print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
-    except:
-        print('输入中可能存在乱码。')
-    return headers,payload
+    except Exception as e:
+        print(f'输入中可能存在乱码。抛出异常: {e}')
+    return headers, payload
 
 

requirements.txt

@@ -1,4 +1,4 @@
-./docs/gradio-3.32.2-py3-none-any.whl
+gradio>=3.33.1
 tiktoken>=0.3.3
 requests[socks]
 transformers
@@ -15,4 +15,6 @@ pymupdf
 openai
 numpy
 arxiv
-rich
+rich
+langchain
+zh_langchain

toolbox.py

@@ -21,6 +21,7 @@ pj = os.path.join
 ========================================================================
 """
 
+
 class ChatBotWithCookies(list):
     def __init__(self, cookie):
         self._cookies = cookie
@@ -71,11 +72,13 @@ 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 update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
     """
     刷新用户界面
     """
-    if len(chatbot) == 0: chatbot.append(["update_ui_last_msg", lastmsg])
+    if len(chatbot) == 0:
+        chatbot.append(["update_ui_last_msg", lastmsg])
     chatbot[-1] = list(chatbot[-1])
     chatbot[-1][-1] = lastmsg
     yield from update_ui(chatbot=chatbot, history=history)
@@ -83,24 +86,25 @@ def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
 
 
 def trimmed_format_exc():
-    import os, traceback
-    str = traceback.format_exc()
+    import os
+    import traceback
+    _str = traceback.format_exc()
     current_path = os.getcwd()
     replace_path = "."
-    return str.replace(current_path, 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=-1):
         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
+            # from toolbox import get_conf  # 不需要导入本文件内容
             proxies, = get_conf('proxies')
             tb_str = '```\n' + trimmed_format_exc() + '```'
             if len(chatbot) == 0:
@@ -108,7 +112,7 @@ def CatchException(f):
                 chatbot.append(["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
+            yield from update_ui(chatbot=chatbot, history=history, msg=f'异常 {e}')  # 刷新界面
     return decorated
 
 
@@ -148,6 +152,7 @@ def HotReload(f):
 ========================================================================
 """
 
+
 def get_reduce_token_percent(text):
     """
         * 此函数未来将被弃用
@@ -207,8 +212,6 @@ def regular_txt_to_markdown(text):
     return text
 
 
-
-
 def report_execption(chatbot, history, a, b):
     """
     向chatbot中添加错误信息
@@ -238,6 +241,7 @@ def text_divide_paragraph(text):
         text = "</br>".join(lines)
         return pre + text + suf
 
+
 @lru_cache(maxsize=128) # 使用 lru缓存 加快转换速度
 def markdown_convertion(txt):
     """
@@ -440,6 +444,7 @@ def find_recent_files(directory):
 
     return recent_files
 
+
 def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
     # 将文件复制一份到下载区
     import shutil
@@ -452,6 +457,7 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
         else: current = []
         chatbot._cookies.update({'file_to_promote': [new_path] + current})
 
+
 def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
     """
     当文件被上传时的回调函数
@@ -498,24 +504,27 @@ def on_report_generated(cookies, files, chatbot):
     else:
         report_files = find_recent_files('gpt_log')
     if len(report_files) == 0:
-        return None, chatbot
+        return cookies, None, chatbot
     # files.extend(report_files)
     file_links = ''
     for f in report_files: file_links += f'<br/><a href="file={os.path.abspath(f)}" target="_blank">{f}</a>'
     chatbot.append(['报告如何远程获取？', f'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。{file_links}'])
     return cookies, report_files, chatbot
 
+
 def is_openai_api_key(key):
     API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
     API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{32}$", key)
     return bool(API_MATCH_ORIGINAL) or bool(API_MATCH_AZURE)
 
+
 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(',')
@@ -525,6 +534,7 @@ def is_any_api_key(key):
     else:
         return is_openai_api_key(key) or is_api2d_key(key)
 
+
 def what_keys(keys):
     avail_key_list = {'OpenAI Key':0, "API2D Key":0}
     key_list = keys.split(',')
@@ -539,6 +549,7 @@ def what_keys(keys):
 
     return f"检测到： OpenAI Key {avail_key_list['OpenAI Key']} 个，API2D Key {avail_key_list['API2D Key']} 个"
 
+
 def select_api_key(keys, llm_model):
     import random
     avail_key_list = []
@@ -558,6 +569,7 @@ def select_api_key(keys, llm_model):
     api_key = random.choice(avail_key_list) # 随机负载均衡
     return api_key
 
+
 def read_env_variable(arg, default_value):
     """
     环境变量可以是 `GPT_ACADEMIC_CONFIG`(优先)，也可以直接是`CONFIG`
@@ -612,6 +624,7 @@ def read_env_variable(arg, default_value):
     print亮绿(f"[ENV_VAR] 成功读取环境变量{arg}")
     return r
 
+
 @lru_cache(maxsize=128)
 def read_single_conf_with_lru_cache(arg):
     from colorful import print亮红, print亮绿, print亮蓝
@@ -676,6 +689,7 @@ class DummyWith():
     def __exit__(self, exc_type, exc_value, traceback):
         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
@@ -770,6 +784,7 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
 ========================================================================
 """
 
+
 def zip_folder(source_folder, dest_folder, zip_name):
     import zipfile
     import os
@@ -801,6 +816,7 @@ def zip_folder(source_folder, dest_folder, zip_name):
 
     print(f"Zip file created at {zip_file}")
 
+
 def zip_result(folder):
     import time
     t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
@@ -811,6 +827,7 @@ def gen_time_str():
     import time
     return time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
 
+
 class ProxyNetworkActivate():
     """
     这段代码定义了一个名为TempProxy的空上下文管理器, 用于给一小段代码上代理
@@ -830,12 +847,14 @@ class ProxyNetworkActivate():
         if 'HTTPS_PROXY' in os.environ: os.environ.pop('HTTPS_PROXY')
         return
 
+
 def objdump(obj, file='objdump.tmp'):
     import pickle
     with open(file, 'wb+') as f:
         pickle.dump(obj, f)
     return
 
+
 def objload(file='objdump.tmp'):
     import pickle, os
     if not os.path.exists(file): 

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.41,
+  "version": 3.42,
   "show_feature": true,
-  "new_feature": "增加gpt-3.5-16k的支持 <-> 新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持"
+  "new_feature": "完善本地Latex矫错和翻译功能 <-> 增加gpt-3.5-16k的支持 <-> 新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持"
 }