Merge branch 'master' of github.com:binary-husky/chatgpt_academic

Update README.md

README.md

@@ -1,15 +1,3 @@
----
-title: ChatImprovement
-emoji: 😻
-colorFrom: blue
-colorTo: blue
-sdk: gradio
-sdk_version: 3.32.0
-app_file: app.py
-pinned: false
----
-
-# ChatGPT 学术优化
 > **Note**
 >
 > 2023.5.27 对Gradio依赖进行了调整，Fork并解决了官方Gradio的若干Bugs。请及时**更新代码**并重新更新pip依赖。安装依赖时，请严格选择`requirements.txt`中**指定的版本**： 
@@ -109,7 +97,7 @@ cd gpt_academic
 
 2. 配置API_KEY
 
-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) 。
+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) 。
 
 (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`)
 
@@ -152,9 +140,15 @@ 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，等价于docker-compose方案1）
+1. 仅ChatGPT（推荐大多数人选择）
 
 ``` sh
 git clone https://github.com/binary-husky/gpt_academic.git  # 下载项目
@@ -167,43 +161,41 @@ 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。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）。
+P.S. 如果需要依赖Latex的插件功能，请见Wiki
 
 2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker）
 
 ``` sh
-# 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
+# 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
 docker-compose up
 ```
 
 3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
 ``` sh
-# 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
+# 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
 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。
+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）。
 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
+3. 如何使用反代URL/微软云AzureAPI。
 按照`config.py`中的说明配置API_URL_REDIRECT即可。
 
-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）。
+4. 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)
 
-6. 使用WSL2（Windows Subsystem for Linux 子系统）。
+5. 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)
 
-7. 如何在二级网址（如`http://localhost/subpath`）下运行。
+6. 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)
 
 ---

config.py

@@ -1,7 +1,6 @@
 # [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:
@@ -45,9 +44,10 @@ WEB_PORT = -1
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
-# OpenAI模型选择是（gpt4现在只对申请成功的人开放）
-LLM_MODEL = "gpt-3.5-turbo" # 可选 "chatglm"
-AVAIL_LLM_MODELS = ["newbing-free", "gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo"]
+# 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"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
@@ -81,10 +81,3 @@ 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"

crazy_functional.py

@@ -226,20 +226,12 @@ 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（输入问题后点击该插件，需要访问谷歌）": {
+            "连接网络回答问题（先输入问题，再点击按钮，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')
 
@@ -356,28 +348,17 @@ 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({
-            "Latex英文纠错+高亮修正位置 [需Latex]": {
+            "[功能尚不稳定] Latex英文纠错+LatexDiff高亮修正位置": {
                 "Color": "stop",
                 "AsButton": False,
-                "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）。",
+                # "AdvancedArgs": True,
+                # "ArgsReminder": "",
                 "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]": {
-                "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]": {
+            "Arixv翻译（输入arxivID） [需Latex]": {
                 "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
@@ -387,6 +368,17 @@ 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_en':
+    if mode == 'proofread':
         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. " + more_requirement +
+                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
                         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)]
@@ -70,12 +70,6 @@ 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
 
@@ -147,11 +141,7 @@ 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:
@@ -190,13 +180,13 @@ 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_en.tex'):
+    if not os.path.exists(project_folder + '/merge_proofread.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_en', switch_prompt=_switch_prompt_)
+                                chatbot, history, system_prompt, mode='proofread_latex', switch_prompt=switch_prompt)
 
 
     # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en', 
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread', 
                              work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
     
 
@@ -205,7 +195,6 @@ 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
@@ -289,7 +278,6 @@ 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

@@ -188,15 +188,7 @@ 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/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"https://arxiv.org/abs/2002.09253"
     for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
         cli_printer.print(cb)   #  print(cb)
 
@@ -225,7 +217,6 @@ def test_Latex():
 # test_数学动画生成manim()
 # test_Langchain知识库()
 # test_Langchain知识库读取()
-if __name__ == "__main__":
-    test_Latex()
-    input("程序完成，回车退出。")
-    print("退出。")
+test_Latex()
+input("程序完成，回车退出。")
+print("退出。")

crazy_functions/latex_utils.py

@@ -8,49 +8,24 @@ pj = os.path.join
 """
 ========================================================================
 Part One
-Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
+Latex segmentation to a linklist
 ========================================================================
 """
 PRESERVE = 0
 TRANSFORM = 1
 
-def set_forbidden_text(text, mask, pattern, flags=0):
+def split_worker(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper
-    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
-    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
-    everything between "\begin{equation}" and "\end{equation}"
     """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         mask[res.span()[0]:res.span()[1]] = PRESERVE
     return text, mask
 
-def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
+def split_worker_careful_brace(text, mask, pattern, flags=0):
     """
-    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.} 
+    Move area into preserve area 
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
@@ -65,12 +40,9 @@ def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
         mask[begin:end] = PRESERVE
     return text, mask
 
-def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
+def split_worker_reverse_careful_brace(text, mask, pattern, flags=0):
     """
-    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.} 
+    Move area out of preserve area 
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
@@ -83,12 +55,9 @@ def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wr
             p += 1
         end = p
         mask[begin:end] = TRANSFORM
-        if forbid_wrapper:
-            mask[res.regs[0][0]:begin] = PRESERVE
-            mask[end:res.regs[0][1]] = PRESERVE
     return text, mask
 
-def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
+def split_worker_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
@@ -141,41 +110,19 @@ Latex Merge File
 def 寻找Latex主文件(file_manifest, mode):
     """
     在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
-    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
+    P.S. 但愿没人把latex模板放在里面传进来
     """
-    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:
-            canidates.append(texf)
+            return 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():
@@ -185,7 +132,6 @@ 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
 
@@ -232,11 +178,9 @@ 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_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!"
+        pattern = re.compile(r'\\begin\{abstract\}.*\n')
+        match = pattern.search(main_file)
+        assert match is not None, "Cannot find paper abstract section!"
     return main_file
 
 
@@ -268,8 +212,6 @@ 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('\_'):
@@ -317,34 +259,45 @@ 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 = 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)
+    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)
     # 吸收匿名公式
-    text, mask = set_forbidden_text(text, mask, [ r"\$\$(.*?)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
+    text, mask = split_worker(text, mask, r"\$\$(.*?)\$\$", re.DOTALL)
     # 吸收其他杂项
-    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)
+    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)
     root = convert_to_linklist(text, mask)
 
     # 修复括号
@@ -418,7 +371,7 @@ 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 = []
@@ -449,7 +402,7 @@ 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）
@@ -470,14 +423,8 @@ class LatexPaperSplit():
         if mode == 'translate_zh':
             pattern = re.compile(r'\\begin\{abstract\}.*\n')
             match = pattern.search(result_string)
-            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()
+            assert match is not None, "Cannot find paper abstract section!"
+            position = match.end()
             result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
         return result_string
 
@@ -496,7 +443,6 @@ 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
@@ -551,11 +497,11 @@ class LatexPaperFileGroup():
                 f.write(res)
         return manifest
 
-def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
+def write_html(sp_file_contents, sp_file_result, chatbot):
 
     # write html
     try:
-        import shutil
+        import copy
         from .crazy_utils import construct_html
         from toolbox import gen_time_str
         ch = construct_html() 
@@ -573,7 +519,6 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
                 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
@@ -654,7 +599,7 @@ 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, project_folder=project_folder)
+    write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot)
 
     #  <-------- 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']}。"
@@ -691,9 +636,10 @@ 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, cwd, timeout=60):
+
+def compile_latex_with_timeout(command, timeout=60):
     import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
+    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
     try:
         stdout, stderr = process.communicate(timeout=timeout)
     except subprocess.TimeoutExpired:
@@ -717,24 +663,24 @@ 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
-        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+        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)
 
         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
-        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+        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)
         
         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')):
-                ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
+                os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux'); os.chdir(current_dir)
             if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
-                ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
+                os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux'); os.chdir(current_dir)
 
             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
-            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)
+            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)
 
             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
@@ -742,11 +688,13 @@ 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
-                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(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)
 
+        # <--------------------->
+        os.chdir(current_dir)
 
         # <---------- 检查结果 ----------->
         results_ = ""
@@ -758,15 +706,13 @@ 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
-            result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
+            os.chdir(current_dir)
+            result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf')
             if os.path.exists(pj(work_folder, '..', 'translation')):
                 shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
-            promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
+            promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)
             return True # 成功啦
         else:
             if n_fix>=max_try: break
@@ -782,6 +728,7 @@ 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/理解PDF文档内容.py

@@ -13,9 +13,7 @@ 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

@@ -1,102 +0,0 @@
-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/询问多个大语言模型.py

@@ -13,11 +13,11 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     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((txt, "正在同时咨询gpt-3.5和gpt-4……"))
+    chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
     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
 
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
-    llm_kwargs['llm_model'] = 'gpt-3.5-turbo&gpt-4' # 支持任意数量的llm接口，用&符号分隔
+    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt, 
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 

crazy_functions/谷歌检索小助手.py

@@ -104,7 +104,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             meta_paper_info_list = meta_paper_info_list[batchsize:]
 
     chatbot.append(["状态？", 
-        "已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write an academic \"Related Works\" section about \"你搜索的研究领域\" for me."])
+        "已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
     msg = '正常'
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
     res = write_results_to_file(history)

crazy_functions/高级功能函数模板.py

@@ -1,7 +1,6 @@
 from toolbox import CatchException, update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime, re
-
+import datetime
 @CatchException
 def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
     """
@@ -19,34 +18,12 @@ 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？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]}。'
+        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。'
         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='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"]}。'
+            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 >)。"
         )
-        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

@@ -103,30 +103,3 @@ 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

@@ -1,152 +0,0 @@
-# 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

@@ -1,10 +1,8 @@
 import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
 
 def main():
-    import subprocess, sys
-    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'gradio-stable-fork'])
     import gradio as gr
-    if gr.__version__ not in ['3.28.3','3.32.3']: assert False, "请用 pip install -r requirements.txt 安装依赖"
+    if gr.__version__ not in ['3.28.3','3.32.2']: assert False, "需要特殊依赖，请务必用 pip install -r requirements.txt 指令安装依赖，详情信息见requirements.txt"
     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
@@ -56,7 +54,6 @@ def main():
     cancel_handles = []
     with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
         gr.HTML(title_html)
-        gr.HTML('''<center><a href="https://huggingface.co/spaces/qingxu98/gpt-academic?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>请您打开此页面后务必点击上方的“复制空间”（Duplicate Space）按钮！<font color="#FF00FF">使用时，先在输入框填入API-KEY然后回车。</font><br/>切忌在“复制空间”（Duplicate Space）之前填入API_KEY或进行提问，否则您的API_KEY将极可能被空间所有者攫取！<br/>支持任意数量的OpenAI的密钥和API2D的密钥共存，例如输入"OpenAI密钥1,API2D密钥2"，然后提交，即可同时使用两种模型接口。</center>''')
         cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
         with gr_L1():
             with gr_L2(scale=2):
@@ -66,7 +63,7 @@ def main():
             with gr_L2(scale=1):
                 with gr.Accordion("输入区", open=True) as area_input_primary:
                     with gr.Row():
-                        txt = gr.Textbox(show_label=False, lines=2, placeholder="输入问题或API密钥，输入多个密钥时，用英文逗号间隔。支持OpenAI密钥和API2D密钥共存。").style(container=False)
+                        txt = gr.Textbox(show_label=False, placeholder="Input question here.").style(container=False)
                     with gr.Row():
                         submitBtn = gr.Button("提交", variant="primary")
                     with gr.Row():
@@ -200,7 +197,10 @@ def main():
         threading.Thread(target=warm_up_modules, name="warm-up", daemon=True).start()
 
     auto_opentab_delay()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png", blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
+    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
+        server_name="0.0.0.0", server_port=PORT,
+        favicon_path="docs/logo.png", auth=AUTHENTICATION,
+        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
 
     # 如果需要在二级路径下运行
     # CUSTOM_PATH, = get_conf('CUSTOM_PATH')

request_llm/bridge_all.py

@@ -16,9 +16,6 @@ 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
 
@@ -96,24 +93,6 @@ 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,
@@ -123,16 +102,6 @@ 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,
@@ -152,7 +121,7 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # 将 chatglm 直接对齐到 chatglm2
+    # chatglm
     "chatglm": {
         "fn_with_ui": chatglm_ui,
         "fn_without_ui": chatglm_noui,
@@ -161,15 +130,6 @@ 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

@@ -1,241 +0,0 @@
-"""
-    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/chatglm2-6b", trust_remote_code=True)
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
                     device, = get_conf('LOCAL_MODEL_DEVICE')
                     if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float()
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
                     self.chatglm_model = self.chatglm_model.eval()
                     break
                 else:

requirements.txt

@@ -1,3 +1,4 @@
+./docs/gradio-3.32.2-py3-none-any.whl
 tiktoken>=0.3.3
 requests[socks]
 transformers
@@ -14,4 +15,4 @@ pymupdf
 openai
 numpy
 arxiv
-rich
+rich

toolbox.py

@@ -498,7 +498,7 @@ def on_report_generated(cookies, files, chatbot):
     else:
         report_files = find_recent_files('gpt_log')
     if len(report_files) == 0:
-        return cookies, None, chatbot
+        return 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>'
@@ -842,4 +842,4 @@ def objload(file='objdump.tmp'):
         return
     with open(file, 'rb') as f:
         return pickle.load(f)
-    
+    

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.42,
+  "version": 3.41,
   "show_feature": true,
-  "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"
+  "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"
 }