# fix com_zhipuglm.py illegal temperature problem (#1687 )

* Update com_zhipuglm.py # fix 用户在使用 zhipuai 界面时遇到了关于温度参数的非法参数错误
Version 3.74: Merge latest updates on dev branch (frontier) (#1621 )
2025-12-06 14:36:48 +00:00 · 2024-04-08 12:17:07 +08:00 · 2024-04-08 11:49:30 +08:00 · 2024-04-05 20:47:11 +08:00 · 2024-04-03 12:17:41 +08:00 · 2024-04-02 19:42:55 +08:00
--- a/README.md
+++ b/README.md
@@ -1,7 +1,6 @@
 > [!IMPORTANT]
+> 2024.3.11: 恭迎Claude3和Moonshot，全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！  
 > 2024.1.18: 更新3.70版本，支持Mermaid绘图库（让大模型绘制脑图）  
-> 2024.1.17: 恭迎GLM4，全力支持Qwen、GLM、DeepseekCoder等国内中文大语言基座模型！  
-> 2024.1.17: 某些依赖包尚不兼容python 3.12，推荐python 3.11。  
 > 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。

 <br>
--- a/check_proxy.py
+++ b/check_proxy.py
@@ -47,7 +47,7 @@ def backup_and_download(current_version, remote_version):
    shutil.copytree('./', backup_dir, ignore=lambda x, y: ['history'])
    proxies = get_conf('proxies')
    try:    r = requests.get('https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
-    except: r = requests.get('https://public.gpt-academic.top/publish/master.zip', proxies=proxies, stream=True)
+    except: r = requests.get('https://public.agent-matrix.com/publish/master.zip', proxies=proxies, stream=True)
    zip_file_path = backup_dir+'/master.zip'
    with open(zip_file_path, 'wb+') as f:
        f.write(r.content)
@@ -113,7 +113,7 @@ def auto_update(raise_error=False):
        import json
        proxies = get_conf('proxies')
        try:    response = requests.get("https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
-        except: response = requests.get("https://public.gpt-academic.top/publish/version", proxies=proxies, timeout=5)
+        except: response = requests.get("https://public.agent-matrix.com/publish/version", proxies=proxies, timeout=5)
        remote_json_data = json.loads(response.text)
        remote_version = remote_json_data['version']
        if remote_json_data["show_feature"]:
--- a/config.py
+++ b/config.py
@@ -30,7 +30,33 @@ if USE_PROXY:
 else:
    proxies = None

-# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
+# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
+LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
+                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
+                    "gemini-pro", "chatglm3"
+                    ]
+# --- --- --- ---
+# P.S. 其他可用的模型还包括
+# AVAIL_LLM_MODELS = [
+#   "qianfan", "deepseekcoder",
+#   "spark", "sparkv2", "sparkv3", "sparkv3.5",
+#   "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
+#   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
+#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125"
+#   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
+#   "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
+#   "yi-34b-chat-0205", "yi-34b-chat-200k"
+# ]
+# --- --- --- ---
+# 此外，为了更灵活地接入one-api多模型管理界面，您还可以在接入one-api时，
+# 使用"one-api-*"前缀直接使用非标准方式接入的模型，例如
+# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)"]
+# --- --- --- ---
+
+
+# --------------- 以下配置可以优化体验 ---------------

 # 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
 # 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
@@ -85,20 +111,6 @@ MAX_RETRY = 2
 DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']


-# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
-LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
-                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
-                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
-                    "gemini-pro", "chatglm3", "claude-2"]
-# P.S. 其他可用的模型还包括 [
-# "moss", "qwen-turbo", "qwen-plus", "qwen-max"
-# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613",
-# "gpt-3.5-turbo-16k-0613",  "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
-# "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"
-# ]
-
-
 # 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
 MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"

@@ -127,6 +139,7 @@ CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
 LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本

+
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100

@@ -144,7 +157,8 @@ ADD_WAIFU = False
 AUTHENTICATION = []


-# 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!）
+# 如果需要在二级路径下运行（常规情况下，不要修改!!）
+# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
 CUSTOM_PATH = "/"


@@ -172,14 +186,8 @@ AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.
 AZURE_CFG_ARRAY = {}


-# 使用Newbing (不推荐使用，未来将删除)
-NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
-NEWBING_COOKIES = """
-put your new bing cookies here
-"""
-
-
-# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
+# 阿里云实时语音识别 配置难度较高
+# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
 ENABLE_AUDIO = False
 ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
 ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
@@ -198,16 +206,18 @@ ZHIPUAI_API_KEY = ""
 ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写


-# # 火山引擎YUNQUE大模型
-# YUNQUE_SECRET_KEY = ""
-# YUNQUE_ACCESS_KEY = ""
-# YUNQUE_MODEL = ""
-
-
 # Claude API KEY
 ANTHROPIC_API_KEY = ""


+# 月之暗面 API KEY
+MOONSHOT_API_KEY = ""
+
+
+# 零一万物(Yi Model) API KEY
+YIMODEL_API_KEY = ""
+
+
 # Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
 MATHPIX_APPID = ""
 MATHPIX_APPKEY = ""
@@ -266,7 +276,11 @@ PLUGIN_HOT_RELOAD = False
 # 自定义按钮的最大数量限制
 NUM_CUSTOM_BASIC_BTN = 4

+
+
 """
+--------------- 配置关联关系说明 ---------------
+
 在线大模型配置关联关系示意图
 │
 ├── "gpt-3.5-turbo" 等openai模型
@@ -290,7 +304,7 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   ├── XFYUN_API_SECRET
 │   └── XFYUN_API_KEY
 │
-├── "claude-1-100k" 等claude模型
+├── "claude-3-opus-20240229" 等claude模型
 │   └── ANTHROPIC_API_KEY
 │
 ├── "stack-claude"
@@ -305,15 +319,19 @@ NUM_CUSTOM_BASIC_BTN = 4
 ├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
 │   └── ZHIPUAI_API_KEY
 │
+├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
+│   └── YIMODEL_API_KEY
+│
 ├── "qwen-turbo" 等通义千问大模型
 │   └──  DASHSCOPE_API_KEY
 │
 ├── "Gemini"
 │   └──  GEMINI_API_KEY
 │
-└── "newbing" Newbing接口不再稳定，不推荐使用
-    ├── NEWBING_STYLE
-    └── NEWBING_COOKIES
+└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
+    ├── AVAIL_LLM_MODELS
+    ├── API_KEY
+    └── API_URL_REDIRECT


 本地大模型示意图
--- a/core_functional.py
+++ b/core_functional.py
@@ -38,12 +38,12 @@ def get_core_functions():

        "总结绘制脑图": {
            # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
-            "Prefix":   r"",
+            "Prefix":   '''"""\n\n''',
            # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
            "Suffix":
                # dedent() 函数用于去除多行字符串的缩进
-                dedent("\n"+r'''
-                    ==============================
+                dedent("\n\n"+r'''
+                    """

                    使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：

@@ -57,7 +57,7 @@ def get_core_functions():
                        C --> |"箭头名2"| F["节点名6"]
                    ```

-                    警告：
+                    注意：
                    （1）使用中文
                    （2）节点名字使用引号包裹，如["Laptop"]
                    （3）`|` 和 `"`之间不要存在空格
--- a/crazy_functions/Latex全文润色.py
+++ b/crazy_functions/Latex全文润色.py
@@ -81,8 +81,8 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
    #  <-------- 多线程润色开始 ---------->
    if language == 'en':
        if mode == 'polish':
-            inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " + 
-                            "improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" + 
+            inputs_array = [r"Below is a section from an academic paper, polish this section to meet the academic standard, " +
+                            r"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
        else:
            inputs_array = [r"Below is a section from an academic paper, proofread this section." +
@@ -93,10 +93,10 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
    elif language == 'zh':
        if mode == 'polish':
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
        else:
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
        inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
        sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
--- a/crazy_functions/Latex输出PDF.py
+++ b/crazy_functions/Latex输出PDF.py
@@ -1,4 +1,4 @@
-from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
 from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
 from functools import partial
 import glob, os, requests, time, json, tarfile
@@ -438,47 +438,101 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
        return

-    # <-------------- convert pdf into tex ------------->
-    project_folder = pdf2tex_project(file_manifest[0])
+    hash_tag = map_file_to_sha256(file_manifest[0])

-    # Translate English Latex to Chinese Latex, and compile it
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
-    if len(file_manifest) == 0:
-        report_exception(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
+    # <-------------- check repeated pdf ------------->
+    chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
+    yield from update_ui(chatbot=chatbot, history=history)
+    repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)

-    # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+    except_flag = False

-    # <-------------- move latex project away from temp folder ------------->
-    project_folder = move_project(project_folder)
+    if repeat:
+        yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)

-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
-        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
-                                       chatbot, history, system_prompt, mode='translate_zh',
-                                       switch_prompt=_switch_prompt_)
+        try:
+            trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
+            promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)

-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
-                                   main_file_modified='merge_translate_zh', mode='translate_zh',
-                                   work_folder_original=project_folder, work_folder_modified=project_folder,
-                                   work_folder=project_folder)
+            translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)

-    # <-------------- zip PDF ------------->
-    zip_res = zip_result(project_folder)
-    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, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
-        yield from update_ui(chatbot=chatbot, history=history);
-        time.sleep(1)  # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+            comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)        

-    # <-------------- we are done ------------->
-    return success
+            zip_res = zip_result(project_folder)
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+            return True
+        
+        except:
+            report_exception(chatbot, history, b=f"发现重复上传，但是无法找到相关文件")
+            yield from update_ui(chatbot=chatbot, history=history)
+            
+            chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
+            yield from update_ui(chatbot=chatbot, history=history)
+
+            except_flag = True
+            
+    
+    elif not repeat or except_flag:
+        yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
+
+        # <-------------- convert pdf into tex ------------->
+        chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
+        yield from update_ui(chatbot=chatbot, history=history)
+        project_folder = pdf2tex_project(file_manifest[0])
+        if project_folder is None:
+            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"PDF转换为tex项目失败")
+            yield from update_ui(chatbot=chatbot, history=history)
+            return False
+
+        # <-------------- translate latex file into Chinese ------------->
+        yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+        if len(file_manifest) == 0:
+            report_exception(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
+
+        # <-------------- if is a zip/tar file ------------->
+        project_folder = desend_to_extracted_folder_if_exist(project_folder)
+
+        # <-------------- move latex project away from temp folder ------------->
+        project_folder = move_project(project_folder)
+
+        # <-------------- set a hash tag for repeat-checking ------------->
+        with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
+            f.write(hash_tag)
+            f.close()
+
+
+        # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+        if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
+            yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                        chatbot, history, system_prompt, mode='translate_zh',
+                                        switch_prompt=_switch_prompt_)
+
+        # <-------------- compile PDF ------------->
+        yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
+        success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                    main_file_modified='merge_translate_zh', mode='translate_zh',
+                                    work_folder_original=project_folder, work_folder_modified=project_folder,
+                                    work_folder=project_folder)
+
+        # <-------------- zip PDF ------------->
+        zip_res = zip_result(project_folder)
+        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, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
+            yield from update_ui(chatbot=chatbot, history=history);
+            time.sleep(1)  # 刷新界面
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+        # <-------------- we are done ------------->
+        return success
--- a/crazy_functions/crazy_utils.py
+++ b/crazy_functions/crazy_utils.py
@@ -135,13 +135,25 @@ def request_gpt_model_in_new_thread_with_ui_alive(
    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 can_multi_process(llm):
-    if llm.startswith('gpt-'): return True
-    if llm.startswith('api2d-'): return True
-    if llm.startswith('azure-'): return True
-    if llm.startswith('spark'): return True
-    if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
-    return False
+def can_multi_process(llm) -> bool:
+    from request_llms.bridge_all import model_info
+
+    def default_condition(llm) -> bool:
+        # legacy condition
+        if llm.startswith('gpt-'): return True
+        if llm.startswith('api2d-'): return True
+        if llm.startswith('azure-'): return True
+        if llm.startswith('spark'): return True
+        if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
+        return False
+
+    if llm in model_info:
+        if 'can_multi_thread' in model_info[llm]:
+            return model_info[llm]['can_multi_thread']
+        else:
+            return default_condition(llm)
+    else:
+        return default_condition(llm)

 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
        inputs_array, inputs_show_user_array, llm_kwargs,
--- a/crazy_functions/解析项目源代码.py
+++ b/crazy_functions/解析项目源代码.py
@@ -345,9 +345,12 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
    pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
    pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
    # 将要忽略匹配的文件名(例如: ^README.md)
-    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
+    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", r"\.") # 移除左边通配符，移除右侧逗号，转义点号
+                           for _ in txt_pattern.split(" ") # 以空格分割
+                           if (_ != "" and _.strip().startswith("^") and not _.strip().startswith("^*."))   # ^开始，但不是^*.开始
+                           ]
    # 生成正则表达式
-    pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
+    pattern_except = r'/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
    pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''

    history.clear()
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,12 +1,12 @@
 ## ===================================================
-# docker-compose.yml
+#                docker-compose.yml
 ## ===================================================
 # 1. 请在以下方案中选择任意一种，然后删除其他的方案
 # 2. 修改你选择的方案中的environment环境变量，详情请见github wiki或者config.py
 # 3. 选择一种暴露服务端口的方法，并对相应的配置做出修改：
-    # 【方法1: 适用于Linux，很方便，可惜windows不支持】与宿主的网络融合为一体，这个是默认配置
+    # 「方法1: 适用于Linux，很方便，可惜windows不支持」与宿主的网络融合为一体，这个是默认配置
    # network_mode: "host"
-    # 【方法2: 适用于所有系统包括Windows和MacOS】端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
+    # 「方法2: 适用于所有系统包括Windows和MacOS」端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
    # ports:
    #   - "12345:12345"  # 注意！12345必须与WEB_PORT环境变量相互对应
 # 4. 最后`docker-compose up`运行
@@ -25,7 +25,7 @@
 ## ===================================================

 ## ===================================================
-## 【方案零】 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
+## 「方案零」 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
 ## ===================================================
 version: '3'
 services:
@@ -63,10 +63,10 @@ services:
    #             count: 1
    #             capabilities: [gpu]

-    # 【WEB_PORT暴露方法1: 适用于Linux】与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"

-    # 【WEB_PORT暴露方法2: 适用于所有系统】端口映射
+    # 「WEB_PORT暴露方法2: 适用于所有系统」端口映射
    # ports:
    #   - "12345:12345"  # 12345必须与WEB_PORT相互对应

@@ -75,10 +75,8 @@ services:
      bash -c "python3 -u main.py"


-
-
 ## ===================================================
-## 【方案一】 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
+## 「方案一」 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
 ## ===================================================
 version: '3'
 services:
@@ -97,16 +95,16 @@ services:
      # DEFAULT_WORKER_NUM:       '    10                                                                                             '
      # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '

-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"

-    # 不使用代理网络拉取最新代码
+    # 启动命令
    command: >
      bash -c "python3 -u main.py"


 ### ===================================================
-### 【方案二】 如果需要运行ChatGLM + Qwen + MOSS等本地模型
+### 「方案二」 如果需要运行ChatGLM + Qwen + MOSS等本地模型
 ### ===================================================
 version: '3'
 services:
@@ -130,8 +128,10 @@ services:
    devices:
      - /dev/nvidia0:/dev/nvidia0

-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"
+
+    # 启动命令
    command: >
      bash -c "python3 -u main.py"

@@ -139,8 +139,9 @@ services:
    # command: >
    #   bash -c "pip install -r request_llms/requirements_qwen.txt && python3 -u main.py"

+
 ### ===================================================
-### 【方案三】 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
+### 「方案三」 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
 ### ===================================================
 version: '3'
 services:
@@ -164,16 +165,16 @@ services:
    devices:
      - /dev/nvidia0:/dev/nvidia0

-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"

-    # 不使用代理网络拉取最新代码
+    # 启动命令
    command: >
      python3 -u main.py


 ## ===================================================
-## 【方案四】 ChatGPT + Latex
+## 「方案四」 ChatGPT + Latex
 ## ===================================================
 version: '3'
 services:
@@ -190,16 +191,16 @@ services:
      DEFAULT_WORKER_NUM:       '    10                                                                               '
      WEB_PORT:                 '    12303                                                                            '

-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"

-    # 不使用代理网络拉取最新代码
+    # 启动命令
    command: >
      bash -c "python3 -u main.py"


 ## ===================================================
-## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
+## 「方案五」 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
 ## ===================================================
 version: '3'
 services:
@@ -223,9 +224,9 @@ services:
      # (无需填写) ALIYUN_ACCESSKEY:         '    LTAI5q6BrFUzoRXVGUWnekh1                                         '
      # (无需填写) ALIYUN_SECRET:            '    eHmI20AVWIaQZ0CiTD2bGQVsaP9i68                                   '

-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
    network_mode: "host"

-    # 不使用代理网络拉取最新代码
+    # 启动命令
    command: >
      bash -c "python3 -u main.py"
--- a/main.py
+++ b/main.py
@@ -13,9 +13,20 @@ help_menu_description = \
 </br></br>如何语音对话: 请阅读Wiki
 </br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""

+def enable_log(PATH_LOGGING):
+    import logging, uuid
+    admin_log_path = os.path.join(PATH_LOGGING, "admin")
+    os.makedirs(admin_log_path, exist_ok=True)
+    log_dir = os.path.join(admin_log_path, "chat_secrets.log")
+    try:logging.basicConfig(filename=log_dir, level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    except:logging.basicConfig(filename=log_dir, level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    # Disable logging output from the 'httpx' logger
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    print(f"所有对话记录将自动保存在本地目录{log_dir}, 请注意自我隐私保护哦！")
+
 def main():
    import gradio as gr
-    if gr.__version__ not in ['3.32.8']:
+    if gr.__version__ not in ['3.32.9']:
        raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
    from request_llms.bridge_all import predict
    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
@@ -23,25 +34,19 @@ def main():
    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
    CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
    ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
-    DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
-    INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT')
+    NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
+    DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU')

    # 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
    from check_proxy import get_current_version
    from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
    from themes.theme import js_code_for_css_changing, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
-    from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
+    from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
    title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"

-    # 问询记录, python 版本建议3.9+（越新越好）
-    import logging, uuid
-    os.makedirs(PATH_LOGGING, exist_ok=True)
-    try:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    except:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    # Disable logging output from the 'httpx' logger
-    logging.getLogger("httpx").setLevel(logging.WARNING)
-    print(f"所有问询记录将自动保存在本地目录./{PATH_LOGGING}/chat_secrets.log, 请注意自我隐私保护哦！")
+    # 对话、日志记录
+    enable_log(PATH_LOGGING)

    # 一些普通功能模块
    from core_functional import get_core_functions
@@ -74,9 +79,9 @@ def main():
    cancel_handles = []
    customize_btns = {}
    predefined_btns = {}
-    with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
+    with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as app_block:
        gr.HTML(title_html)
-        secret_css, dark_mode, py_pickle_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
+        secret_css, web_cookie_cache = gr.Textbox(visible=False), gr.Textbox(visible=False)
        cookies = gr.State(load_chat_cookies())
        with gr_L1():
            with gr_L2(scale=2, elem_id="gpt-chat"):
@@ -152,9 +157,13 @@ def main():
                with gr.Tab("更换模型", elem_id="interact-panel"):
                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
                    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",)
+                    temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature", elem_id="elem_temperature")
                    max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
-                    system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT)
+                    system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT, elem_id="elem_prompt")
+                    temperature.change(None, inputs=[temperature], outputs=None,
+                        _js="""(temperature)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_temperature_cookie", temperature)""")
+                    system_prompt.change(None, inputs=[system_prompt], outputs=None,
+                        _js="""(system_prompt)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_system_prompt_cookie", system_prompt)""")

                with gr.Tab("界面外观", elem_id="interact-panel"):
                    theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
@@ -194,64 +203,19 @@ def main():
                    with gr.Column(scale=1, min_width=70):
                        basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm")
                        basic_fn_clean   = gr.Button("恢复默认", variant="primary"); basic_fn_clean.style(size="sm")
-                        def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix, clean_up=False):
-                            ret = {}
-                            # 读取之前的自定义按钮
-                            customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
-                            # 更新新的自定义按钮
-                            customize_fn_overwrite_.update({
-                                basic_btn_dropdown_:
-                                    {
-                                        "Title":basic_fn_title,
-                                        "Prefix":basic_fn_prefix,
-                                        "Suffix":basic_fn_suffix,
-                                    }
-                                }
-                            )
-                            if clean_up:
-                                customize_fn_overwrite_ = {}
-                            cookies_.update(customize_fn_overwrite_)    # 更新cookie
-                            visible = (not clean_up) and (basic_fn_title != "")
-                            if basic_btn_dropdown_ in customize_btns:
-                                # 是自定义按钮，不是预定义按钮
-                                ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
-                            else:
-                                # 是预定义按钮
-                                ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
-                            ret.update({cookies: cookies_})
-                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)   # persistent cookie to dict
-                            except: persistent_cookie_ = {}
-                            persistent_cookie_["custom_bnt"] = customize_fn_overwrite_      # dict update new value
-                            persistent_cookie_ = to_cookie_str(persistent_cookie_)          # persistent cookie to dict
-                            ret.update({py_pickle_cookie: persistent_cookie_})             # write persistent cookie
-                            return ret

+                        from shared_utils.cookie_manager import assign_btn__fn_builder
+                        assign_btn = assign_btn__fn_builder(customize_btns, predefined_btns, cookies, web_cookie_cache)
                        # update btn
-                        h = basic_fn_confirm.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
-                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
+                        h = basic_fn_confirm.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
+                                                   [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
+                        h.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")
                        # clean up btn
-                        h2 = basic_fn_clean.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
-                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h2.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
+                        h2 = basic_fn_clean.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
+                                                   [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
+                        h2.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")

-                        def persistent_cookie_reload(persistent_cookie_, cookies_):
-                            ret = {}
-                            for k in customize_btns:
-                                ret.update({customize_btns[k]: gr.update(visible=False, value="")})

-                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)    # persistent cookie to dict
-                            except: return ret
-
-                            customize_fn_overwrite_ = persistent_cookie_.get("custom_bnt", {})
-                            cookies_['customize_fn_overwrite'] = customize_fn_overwrite_
-                            ret.update({cookies: cookies_})
-
-                            for k,v in persistent_cookie_["custom_bnt"].items():
-                                if v['Title'] == "": continue
-                                if k in customize_btns: ret.update({customize_btns[k]: gr.update(visible=True, value=v['Title'])})
-                                else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
-                            return ret

        # 功能区显示开关与功能区的互动
        def fn_area_visibility(a):
@@ -371,11 +335,14 @@ def main():
            audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])


-        demo.load(init_cookie, inputs=[cookies], outputs=[cookies])
-        demo.load(persistent_cookie_reload, inputs = [py_pickle_cookie, cookies],
-            outputs = [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
-        demo.load(None, inputs=[dark_mode], outputs=None, _js="""(dark_mode)=>{apply_cookie_for_checkbox(dark_mode);}""")    # 配置暗色主题或亮色主题
-        demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
+        app_block.load(assign_user_uuid, inputs=[cookies], outputs=[cookies])
+
+        from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
+        load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
+        app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
+            outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
+
+        app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}")""")    # 配置暗色主题或亮色主题

    # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
    def run_delayed_tasks():
@@ -390,28 +357,15 @@ def main():

        threading.Thread(target=auto_updates, name="self-upgrade", daemon=True).start() # 查看自动更新
        threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面
-        threading.Thread(target=warm_up_mods, name="warm-up", daemon=True).start()      # 预热tiktoken模块
+        threading.Thread(target=warm_up_mods, name="warm-up",      daemon=True).start() # 预热tiktoken模块

+    # 运行一些异步任务：自动更新、打开浏览器页面、预热tiktoken模块
    run_delayed_tasks()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
-        quiet=True,
-        server_name="0.0.0.0",
-        ssl_keyfile=None if SSL_KEYFILE == "" else SSL_KEYFILE,
-        ssl_certfile=None if SSL_CERTFILE == "" else SSL_CERTFILE,
-        ssl_verify=False,
-        server_port=PORT,
-        favicon_path=os.path.join(os.path.dirname(__file__), "docs/logo.png"),
-        auth=AUTHENTICATION if len(AUTHENTICATION) != 0 else None,
-        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])

-    # 如果需要在二级路径下运行
-    # CUSTOM_PATH = get_conf('CUSTOM_PATH')
-    # if CUSTOM_PATH != "/":
-    #     from toolbox import run_gradio_in_subpath
-    #     run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
-    # else:
-    #     demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
-    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
+    # 最后，正式开始服务
+    from shared_utils.fastapi_server import start_app
+    start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SSL_CERTFILE)
+

 if __name__ == "__main__":
    main()
--- a/request_llms/bridge_all.py
+++ b/request_llms/bridge_all.py
@@ -8,10 +8,10 @@
    具备多线程调用能力的函数：在函数插件中被调用，灵活而简洁
    2. predict_no_ui_long_connection(...)
 """
-import tiktoken, copy
+import tiktoken, copy, re
 from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
-from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
+from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask, read_one_api_model_name

 from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
 from .bridge_chatgpt import predict as chatgpt_ui
@@ -34,6 +34,9 @@ from .bridge_google_gemini import predict_no_ui_long_connection  as genai_noui
 from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
 from .bridge_zhipu import predict as zhipu_ui

+from .bridge_cohere import predict as cohere_ui
+from .bridge_cohere import predict_no_ui_long_connection as cohere_noui
+
 colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']

 class LazyloadTiktoken(object):
@@ -61,6 +64,11 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
 openai_endpoint = "https://api.openai.com/v1/chat/completions"
 api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
 newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
+gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
+claude_endpoint = "https://api.anthropic.com/v1/messages"
+yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
+cohere_endpoint = 'https://api.cohere.ai/v1/chat'
+
 if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
 # 兼容旧版的配置
@@ -75,7 +83,10 @@ except:
 if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint]
 if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint]
 if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
-
+if gemini_endpoint in API_URL_REDIRECT: gemini_endpoint = API_URL_REDIRECT[gemini_endpoint]
+if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
+if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
+if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[cohere_endpoint]

 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@@ -94,7 +105,7 @@ model_info = {
        "fn_with_ui": chatgpt_ui,
        "fn_without_ui": chatgpt_noui,
        "endpoint": openai_endpoint,
-        "max_token": 4096,
+        "max_token": 16385,
        "tokenizer": tokenizer_gpt35,
        "token_cnt": get_token_num_gpt35,
    },
@@ -117,15 +128,6 @@ model_info = {
        "token_cnt": get_token_num_gpt35,
    },

-    "gpt-3.5-turbo-0125": {
-        "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,
@@ -135,7 +137,16 @@ model_info = {
        "token_cnt": get_token_num_gpt35,
    },

-    "gpt-3.5-turbo-1106": {#16k
+    "gpt-3.5-turbo-1106": { #16k
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 16385,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    "gpt-3.5-turbo-0125": { #16k
        "fn_with_ui": chatgpt_ui,
        "fn_without_ui": chatgpt_noui,
        "endpoint": openai_endpoint,
@@ -291,7 +302,7 @@ model_info = {
    "gemini-pro": {
        "fn_with_ui": genai_ui,
        "fn_without_ui": genai_noui,
-        "endpoint": None,
+        "endpoint": gemini_endpoint,
        "max_token": 1024 * 32,
        "tokenizer": tokenizer_gpt35,
        "token_cnt": get_token_num_gpt35,
@@ -299,13 +310,56 @@ model_info = {
    "gemini-pro-vision": {
        "fn_with_ui": genai_ui,
        "fn_without_ui": genai_noui,
+        "endpoint": gemini_endpoint,
+        "max_token": 1024 * 32,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    # cohere
+    "cohere-command-r-plus": {
+        "fn_with_ui": cohere_ui,
+        "fn_without_ui": cohere_noui,
+        "can_multi_thread": True,
+        "endpoint": cohere_endpoint,
+        "max_token": 1024 * 4,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+}
+# -=-=-=-=-=-=- 月之暗面 -=-=-=-=-=-=-
+from request_llms.bridge_moonshot import predict as moonshot_ui
+from request_llms.bridge_moonshot import predict_no_ui_long_connection as moonshot_no_ui
+model_info.update({
+    "moonshot-v1-8k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
+        "endpoint": None,
+        "max_token": 1024 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "moonshot-v1-32k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
        "endpoint": None,
        "max_token": 1024 * 32,
        "tokenizer": tokenizer_gpt35,
        "token_cnt": get_token_num_gpt35,
    },
-}
-
+    "moonshot-v1-128k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
+        "endpoint": None,
+        "max_token": 1024 * 128,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    }
+})
 # -=-=-=-=-=-=- api2d 对齐支持 -=-=-=-=-=-=-
 for model in AVAIL_LLM_MODELS:
    if model.startswith('api2d-') and (model.replace('api2d-','') in model_info.keys()):
@@ -321,25 +375,67 @@ for model in AVAIL_LLM_MODELS:
        model_info.update({model: mi})

 # -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
-if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" in AVAIL_LLM_MODELS:
+# claude家族
+claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229"]
+if any(item in claude_models for item in AVAIL_LLM_MODELS):
    from .bridge_claude import predict_no_ui_long_connection as claude_noui
    from .bridge_claude import predict as claude_ui
    model_info.update({
-        "claude-1-100k": {
+        "claude-instant-1.2": {
            "fn_with_ui": claude_ui,
            "fn_without_ui": claude_noui,
-            "endpoint": None,
-            "max_token": 8196,
+            "endpoint": claude_endpoint,
+            "max_token": 100000,
            "tokenizer": tokenizer_gpt35,
            "token_cnt": get_token_num_gpt35,
        },
    })
    model_info.update({
-        "claude-2": {
+        "claude-2.0": {
            "fn_with_ui": claude_ui,
            "fn_without_ui": claude_noui,
-            "endpoint": None,
-            "max_token": 8196,
+            "endpoint": claude_endpoint,
+            "max_token": 100000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-2.1": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-haiku-20240307": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-sonnet-20240229": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-opus-20240229": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
            "tokenizer": tokenizer_gpt35,
            "token_cnt": get_token_num_gpt35,
        },
@@ -409,22 +505,6 @@ if "stack-claude" in AVAIL_LLM_MODELS:
            "token_cnt": get_token_num_gpt35,
        }
    })
-if "newbing-free" in AVAIL_LLM_MODELS:
-    try:
-        from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
-        from .bridge_newbingfree import predict as newbingfree_ui
-        model_info.update({
-            "newbing-free": {
-                "fn_with_ui": newbingfree_ui,
-                "fn_without_ui": newbingfree_noui,
-                "endpoint": newbing_endpoint,
-                "max_token": 4096,
-                "tokenizer": tokenizer_gpt35,
-                "token_cnt": get_token_num_gpt35,
-            }
-        })
-    except:
-        print(trimmed_format_exc())
 if "newbing" in AVAIL_LLM_MODELS:   # same with newbing-free
    try:
        from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
@@ -457,6 +537,7 @@ if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
        })
    except:
        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 上海AI-LAB书生大模型 -=-=-=-=-=-=-
 if "internlm" in AVAIL_LLM_MODELS:
    try:
        from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
@@ -489,6 +570,7 @@ if "chatglm_onnx" in AVAIL_LLM_MODELS:
        })
    except:
        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 通义-本地模型 -=-=-=-=-=-=-
 if "qwen-local" in AVAIL_LLM_MODELS:
    try:
        from .bridge_qwen_local import predict_no_ui_long_connection as qwen_local_noui
@@ -497,6 +579,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
            "qwen-local": {
                "fn_with_ui": qwen_local_ui,
                "fn_without_ui": qwen_local_noui,
+                "can_multi_thread": False,
                "endpoint": None,
                "max_token": 4096,
                "tokenizer": tokenizer_gpt35,
@@ -505,6 +588,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
        })
    except:
        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
 if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS:   # zhipuai
    try:
        from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
@@ -513,6 +597,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
            "qwen-turbo": {
                "fn_with_ui": qwen_ui,
                "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 6144,
                "tokenizer": tokenizer_gpt35,
@@ -521,6 +606,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
            "qwen-plus": {
                "fn_with_ui": qwen_ui,
                "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 30720,
                "tokenizer": tokenizer_gpt35,
@@ -529,6 +615,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
            "qwen-max": {
                "fn_with_ui": qwen_ui,
                "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 28672,
                "tokenizer": tokenizer_gpt35,
@@ -537,7 +624,35 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
        })
    except:
        print(trimmed_format_exc())
-if "spark" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+# -=-=-=-=-=-=- 零一万物模型 -=-=-=-=-=-=-
+if "yi-34b-chat-0205" in AVAIL_LLM_MODELS or "yi-34b-chat-200k" in AVAIL_LLM_MODELS:   # zhipuai
+    try:
+        from .bridge_yimodel import predict_no_ui_long_connection as yimodel_noui
+        from .bridge_yimodel import predict as yimodel_ui
+        model_info.update({
+            "yi-34b-chat-0205": {
+                "fn_with_ui": yimodel_ui,
+                "fn_without_ui": yimodel_noui,
+                "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
+                "endpoint": yimodel_endpoint,
+                "max_token": 4000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-34b-chat-200k": {
+                "fn_with_ui": yimodel_ui,
+                "fn_without_ui": yimodel_noui,
+                "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
+                "endpoint": yimodel_endpoint,
+                "max_token": 200000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+        })
+    except:
+        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
+if "spark" in AVAIL_LLM_MODELS:
    try:
        from .bridge_spark import predict_no_ui_long_connection as spark_noui
        from .bridge_spark import predict as spark_ui
@@ -545,6 +660,7 @@ if "spark" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
            "spark": {
                "fn_with_ui": spark_ui,
                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 4096,
                "tokenizer": tokenizer_gpt35,
@@ -561,6 +677,7 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
            "sparkv2": {
                "fn_with_ui": spark_ui,
                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 4096,
                "tokenizer": tokenizer_gpt35,
@@ -577,6 +694,7 @@ if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞
            "sparkv3": {
                "fn_with_ui": spark_ui,
                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 4096,
                "tokenizer": tokenizer_gpt35,
@@ -585,6 +703,7 @@ if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞
            "sparkv3.5": {
                "fn_with_ui": spark_ui,
                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                "endpoint": None,
                "max_token": 4096,
                "tokenizer": tokenizer_gpt35,
@@ -609,6 +728,7 @@ if "llama2" in AVAIL_LLM_MODELS:   # llama2
        })
    except:
        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 智谱 -=-=-=-=-=-=-
 if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容配置
    try:
        model_info.update({
@@ -623,6 +743,7 @@ if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容
        })
    except:
        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
 if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
    try:
        from .bridge_deepseekcoder import predict_no_ui_long_connection as deepseekcoder_noui
@@ -639,26 +760,34 @@ if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
        })
    except:
        print(trimmed_format_exc())
-# if "skylark" in AVAIL_LLM_MODELS:
-#     try:
-#         from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui
-#         from .bridge_skylark2 import predict as skylark_ui
-#         model_info.update({
-#             "skylark": {
-#                 "fn_with_ui": skylark_ui,
-#                 "fn_without_ui": skylark_noui,
-#                 "endpoint": None,
-#                 "max_token": 4096,
-#                 "tokenizer": tokenizer_gpt35,
-#                 "token_cnt": get_token_num_gpt35,
-#             }
-#         })
-#     except:
-#         print(trimmed_format_exc())


-# <-- 用于定义和切换多个azure模型 -->
-AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
+# -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
+for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
+    # 为了更灵活地接入one-api多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["one-api-mixtral-8x7b(max_token=6666)"]
+    # 其中
+    #   "one-api-"          是前缀（必要）
+    #   "mixtral-8x7b"      是模型名（必要）
+    #   "(max_token=6666)"  是配置（非必要）
+    try:
+        _, max_token_tmp = read_one_api_model_name(model)
+    except:
+        print(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        continue
+    model_info.update({
+        model: {
+            "fn_with_ui": chatgpt_ui,
+            "fn_without_ui": chatgpt_noui,
+            "endpoint": openai_endpoint,
+            "max_token": max_token_tmp,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+
+
+# -=-=-=-=-=-=- azure模型对齐支持 -=-=-=-=-=-=-
+AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY") # <-- 用于定义和切换多个azure模型 -->
 if len(AZURE_CFG_ARRAY) > 0:
    for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
        # 可能会覆盖之前的配置，但这是意料之中的
@@ -687,7 +816,7 @@ def LLM_CATCH_EXCEPTION(f):
    """
    装饰器函数，将错误显示出来
    """
-    def decorated(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience):
+    def decorated(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list, console_slience:bool):
        try:
            return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
        except Exception as e:
@@ -697,9 +826,9 @@ def LLM_CATCH_EXCEPTION(f):
    return decorated


-def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list=[], console_slience:bool=False):
    """
-    发送至LLM，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。
+    发送至LLM，等待回复，一次性完成，不显示中间过程。但内部（尽可能地）用stream的方法避免中途网线被掐。
    inputs：
        是本次问询的输入
    sys_prompt:
@@ -717,7 +846,6 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
    model = llm_kwargs['llm_model']
    n_model = 1
    if '&' not in model:
-        assert not model.startswith("tgui"), "TGUI不支持函数插件的实现"

        # 如果只询问1个大语言模型：
        method = model_info[model]["fn_without_ui"]
@@ -752,7 +880,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
                # 观察窗（window）
                chat_string = []
                for i in range(n_model):
-                    chat_string.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {window_mutex[i][0]} </font>" )
+                    color = colors[i%len(colors)]
+                    chat_string.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {window_mutex[i][0]} </font>" )
                res = '<br/><br/>\n\n---\n\n'.join(chat_string)
                # # # # # # # # # # #
                observe_window[0] = res
@@ -769,22 +898,30 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
            time.sleep(1)

        for i, future in enumerate(futures):  # wait and get
-            return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {future.result()} </font>" )
+            color = colors[i%len(colors)]
+            return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {future.result()} </font>" )

        window_mutex[-1] = False # stop mutex thread
        res = '<br/><br/>\n\n---\n\n'.join(return_string_collect)
        return res


-def predict(inputs, llm_kwargs, *args, **kwargs):
+def predict(inputs:str, llm_kwargs:dict, *args, **kwargs):
    """
    发送至LLM，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LLM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
+
+    完整参数列表：
+        predict(
+            inputs:str,                     # 是本次问询的输入
+            llm_kwargs:dict,                # 是LLM的内部调优参数
+            plugin_kwargs:dict,             # 是插件的内部参数
+            chatbot:ChatBotWithCookies,     # 原样传递，负责向用户前端展示对话，兼顾前端状态的功能
+            history:list=[],                # 是之前的对话列表
+            system_prompt:str='',           # 系统静默prompt
+            stream:bool=True,               # 是否流式输出（已弃用）
+            additional_fn:str=None          # 基础功能区按钮的附加功能
+        ):
    """

    inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
--- a/request_llms/bridge_chatglmft.py
+++ b/request_llms/bridge_chatglmft.py
@@ -137,7 +137,8 @@ class GetGLMFTHandle(Process):
 global glmft_handle
 glmft_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_chatgpt.py
+++ b/request_llms/bridge_chatgpt.py
@@ -21,7 +21,9 @@ import random

 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
-from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder
+from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
+from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
+from toolbox import ChatBotWithCookies
 proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')

@@ -68,7 +70,7 @@ def verify_endpoint(endpoint):
        raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
    return endpoint

-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:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=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：
@@ -125,8 +127,9 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
        json_data = chunkjson['choices'][0]
        delta = json_data["delta"]
        if len(delta) == 0: break
-        if "role" in delta: continue
-        if "content" in delta:
+        if (not has_content) and has_role: continue
+        if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
+        if has_content: # has_role = True/False
            result += delta["content"]
            if not console_slience: print(delta["content"], end='')
            if observe_window is not None:
@@ -145,7 +148,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
    return result


-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
    """
    发送至chatGPT，流式获取输出。
    用于基础的对话功能。
@@ -171,7 +175,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)

    raw_input = inputs
-    logging.info(f'[raw_input] {raw_input}')
+    # 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

@@ -252,7 +256,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                    # 前者是API2D的结束条件，后者是OPENAI的结束条件
                    if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
                        # 判定为数据流的结束，gpt_replying_buffer也写完了
-                        logging.info(f'[response] {gpt_replying_buffer}')
+                        # logging.info(f'[response] {gpt_replying_buffer}')
+                        log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
                        break
                    # 处理数据流的主体
                    status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
@@ -264,7 +269,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                        # 一些第三方接口的出现这样的错误，兼容一下吧
                        continue
                    else:
-                        # 一些垃圾第三方接口的出现这样的错误
+                        # 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
+                        if chunkjson['choices'][0]["delta"]["content"] is None: continue # 一些垃圾第三方接口出现这样的错误，兼容一下吧
                        gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]

                    history[-1] = gpt_replying_buffer
@@ -356,6 +362,9 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
    model = llm_kwargs['llm_model']
    if llm_kwargs['llm_model'].startswith('api2d-'):
        model = llm_kwargs['llm_model'][len('api2d-'):]
+    if llm_kwargs['llm_model'].startswith('one-api-'):
+        model = llm_kwargs['llm_model'][len('one-api-'):]
+        model, _ = read_one_api_model_name(model)

    if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
        model = random.choice([
--- a/request_llms/bridge_claude.py
+++ b/request_llms/bridge_claude.py
@@ -9,15 +9,15 @@
    具备多线程调用能力的函数
    2. predict_no_ui_long_connection：支持多线程
 """
-
-import os
-import json
-import time
-import gradio as gr
 import logging
+import os
+import time
 import traceback
+import json
 import requests
-import importlib
+from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path, log_chat
+picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
+Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229"]

 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
@@ -39,6 +39,34 @@ def get_full_error(chunk, stream_response):
            break
    return chunk

+def decode_chunk(chunk):
+    # 提前读取一些信息（用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    is_last_chunk = False
+    need_to_pass = False
+    if chunk_decoded.startswith('data:'):
+        try:
+            chunkjson = json.loads(chunk_decoded[6:])
+        except:
+            need_to_pass = True
+            pass
+    elif chunk_decoded.startswith('event:'):
+        try:
+            event_type = chunk_decoded.split(':')[1].strip()
+            if event_type == 'content_block_stop' or event_type == 'message_stop':
+                is_last_chunk = True
+            elif event_type == 'content_block_start' or event_type == 'message_start':
+                need_to_pass = True
+                pass
+        except:
+            need_to_pass = True
+            pass
+    else:
+        need_to_pass = True
+        pass
+    return need_to_pass, chunkjson, is_last_chunk
+

 def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
    """
@@ -54,50 +82,67 @@ 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
    """
-    from anthropic import Anthropic
    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
-    prompt = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
-    retry = 0
    if len(ANTHROPIC_API_KEY) == 0:
        raise RuntimeError("没有设置ANTHROPIC_API_KEY选项")
+    if inputs == "":     inputs = "空空如也的输入栏"
+    headers, message = generate_payload(inputs, llm_kwargs, history, sys_prompt, image_paths=None)
+    retry = 0
+

    while True:
        try:
            # make a POST request to the API endpoint, stream=False
            from .bridge_all import model_info
-            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
-            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            # with ProxyNetworkActivate()
-            stream = anthropic.completions.create(
-                prompt=prompt,
-                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
-                model=llm_kwargs['llm_model'],
-                stream=True,
-                temperature = llm_kwargs['temperature']
-            )
-            break
-        except Exception as e:
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, json=message,
+                                     proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
+        except requests.exceptions.ReadTimeout as e:
            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.iter_lines()
    result = ''
-    try: 
-        for completion in stream:
-            result += completion.completion
-            if not console_slience: print(completion.completion, 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] += completion.completion
-                # 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。")
-    except Exception as e:
-        traceback.print_exc()
+    while True:
+        try: chunk = next(stream_response)
+        except StopIteration:
+            break
+        except requests.exceptions.ConnectionError:
+            chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+        need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
+        if chunk:
+            try:
+                if need_to_pass:
+                    pass
+                elif is_last_chunk:
+                    # logging.info(f'[response] {result}')
+                    break
+                else:
+                    if chunkjson and chunkjson['type'] == 'content_block_delta':
+                        result += chunkjson['delta']['text']
+                        print(chunkjson['delta']['text'], 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] += chunkjson['delta']['text']
+                            # 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。")
+            except Exception as e:
+                chunk = get_full_error(chunk, stream_response)
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                print(error_msg)
+                raise RuntimeError("Json解析不合常规")

    return result

+def make_media_input(history,inputs,image_paths):
+    for image_path in image_paths:
+        inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
+    return inputs

 def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
    """
@@ -109,7 +154,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
    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
    """
-    from anthropic import Anthropic
+    if inputs == "":     inputs = "空空如也的输入栏"
    if len(ANTHROPIC_API_KEY) == 0:
        chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY"))
        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
@@ -119,13 +164,23 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
        from core_functional import handle_core_functionality
        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)

-    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
+    have_recent_file, image_paths = every_image_file_in_path(chatbot)
+    if len(image_paths) > 20:
+        chatbot.append((inputs, "图片数量超过api上限(20张)"))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")
+        return
+
+    if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and have_recent_file:
+        if inputs == "" or inputs == "空空如也的输入栏":     inputs = "请描述给出的图片"
+        system_prompt += picture_system_prompt  # 由于没有单独的参数保存包含图片的历史，所以只能通过提示词对第几张图片进行定位
+        chatbot.append((make_media_input(history,inputs, image_paths), ""))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+    else:
+        chatbot.append((inputs, ""))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面

    try:
-        prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+        headers, message = generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths)
    except RuntimeError as e:
        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
@@ -138,91 +193,117 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
        try:
            # make a POST request to the API endpoint, stream=True
            from .bridge_all import model_info
-            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
-            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            # with ProxyNetworkActivate()
-            stream = anthropic.completions.create(
-                prompt=prompt,
-                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
-                model=llm_kwargs['llm_model'],
-                stream=True,
-                temperature = llm_kwargs['temperature']
-            )
-            
-            break
-        except:
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, json=message,
+                                     proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
+        except requests.exceptions.ReadTimeout as e:
            retry += 1
-            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
-            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
+            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.iter_lines()
    gpt_replying_buffer = ""

-    for completion in stream:
-        try:
-            gpt_replying_buffer = gpt_replying_buffer + completion.completion
-            history[-1] = gpt_replying_buffer
-            chatbot[-1] = (history[-2], history[-1])
-            yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
+    while True:
+        try: chunk = next(stream_response)
+        except StopIteration:
+            break
+        except requests.exceptions.ConnectionError:
+            chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+        need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
+        if chunk:
+            try:
+                if need_to_pass:
+                    pass
+                elif is_last_chunk:
+                    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
+                    # logging.info(f'[response] {gpt_replying_buffer}')
+                    break
+                else:
+                    if chunkjson and chunkjson['type'] == 'content_block_delta':
+                        gpt_replying_buffer += chunkjson['delta']['text']
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面

-        except Exception as e:
-            from toolbox import regular_txt_to_markdown
-            tb_str = '```\n' + trimmed_format_exc() + '```'
-            chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str}")
-            yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
-            return
+            except Exception as e:
+                chunk = get_full_error(chunk, stream_response)
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                print(error_msg)
+                raise RuntimeError("Json解析不合常规")

+def multiple_picture_types(image_paths):
+    """
+    根据图片类型返回image/jpeg, image/png, image/gif, image/webp，无法判断则返回image/jpeg
+    """
+    for image_path in image_paths:
+        if image_path.endswith('.jpeg') or image_path.endswith('.jpg'):
+            return 'image/jpeg'
+        elif image_path.endswith('.png'):
+            return 'image/png'
+        elif image_path.endswith('.gif'):
+            return 'image/gif'
+        elif image_path.endswith('.webp'):
+            return 'image/webp'
+    return 'image/jpeg'

-
-
-# https://github.com/jtsang4/claude-to-chatgpt/blob/main/claude_to_chatgpt/adapter.py
-def convert_messages_to_prompt(messages):
-    prompt = ""
-    role_map = {
-        "system": "Human",
-        "user": "Human",
-        "assistant": "Assistant",
-    }
-    for message in messages:
-        role = message["role"]
-        content = message["content"]
-        transformed_role = role_map[role]
-        prompt += f"\n\n{transformed_role.capitalize()}: {content}"
-    prompt += "\n\nAssistant: "
-    return prompt
-
-def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
    """
    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
    """
-    from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT

    conversation_cnt = len(history) // 2

-    messages = [{"role": "system", "content": system_prompt}]
+    messages = []
+
    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_i_have_asked["content"] = [{"type": "text", "text": 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
-                if what_gpt_answer["content"] == timeout_bot_msg: continue
+            what_gpt_answer["content"] = [{"type": "text", "text": history[index+1]}]
+            if what_i_have_asked["content"][0]["text"] != "":
+                if what_i_have_asked["content"][0]["text"] == "": continue
+                if what_i_have_asked["content"][0]["text"] == timeout_bot_msg: continue
                messages.append(what_i_have_asked)
                messages.append(what_gpt_answer)
            else:
-                messages[-1]['content'] = what_gpt_answer['content']
+                messages[-1]['content'][0]['text'] = what_gpt_answer['content'][0]['text']

-    what_i_ask_now = {}
-    what_i_ask_now["role"] = "user"
-    what_i_ask_now["content"] = inputs
+    if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and image_paths:
+        what_i_ask_now = {}
+        what_i_ask_now["role"] = "user"
+        what_i_ask_now["content"] = []
+        for image_path in image_paths:
+            what_i_ask_now["content"].append({
+                "type": "image",
+                "source": {
+                    "type": "base64",
+                    "media_type": multiple_picture_types(image_paths),
+                    "data": encode_image(image_path),
+                }
+            })
+        what_i_ask_now["content"].append({"type": "text", "text": inputs})
+    else:
+        what_i_ask_now = {}
+        what_i_ask_now["role"] = "user"
+        what_i_ask_now["content"] = [{"type": "text", "text": inputs}]
    messages.append(what_i_ask_now)
-    prompt = convert_messages_to_prompt(messages)
-
-    return prompt
-
-
+    # 开始整理headers与message
+    headers = {
+        'x-api-key': ANTHROPIC_API_KEY,
+        'anthropic-version': '2023-06-01',
+        'content-type': 'application/json'
+    }
+    payload = {
+        'model': llm_kwargs['llm_model'],
+        'max_tokens': 4096,
+        'messages': messages,
+        'temperature': llm_kwargs['temperature'],
+        'stream': True,
+        'system': system_prompt
+    }
+    return headers, payload
--- a/request_llms/bridge_cohere.py
+++ b/request_llms/bridge_cohere.py
@@ -0,0 +1,328 @@
+# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
+
+"""
+    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_long_connection：支持多线程
+"""
+
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+import random
+
+# config_private.py放自己的秘密如API和代理网址
+# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
+from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
+from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
+from toolbox import ChatBotWithCookies
+proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
+
+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Cohere返回的报错
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+def decode_chunk(chunk):
+    # 提前读取一些信息 （用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    has_choices = False
+    choice_valid = False
+    has_content = False
+    has_role = False
+    try:
+        chunkjson = json.loads(chunk_decoded)
+        has_choices = 'choices' in chunkjson
+        if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
+        if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
+        if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
+        if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
+    except:
+        pass
+    return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
+
+from functools import lru_cache
+@lru_cache(maxsize=32)
+def verify_endpoint(endpoint):
+    """
+        检查endpoint是否可用
+    """
+    if "你亲手写的api名称" in endpoint:
+        raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
+    return endpoint
+
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
+    """
+    发送，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：
+        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
+    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=False
+            from .bridge_all import model_info
+            endpoint = verify_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:
+            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.iter_lines()
+    result = ''
+    json_data = None
+    while True:
+        try: chunk = next(stream_response)
+        except StopIteration:
+            break
+        except requests.exceptions.ConnectionError:
+            chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+        chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
+        if chunkjson['event_type'] == 'stream-start': continue
+        if chunkjson['event_type'] == 'text-generation':
+            result += chunkjson["text"]
+            if not console_slience: print(chunkjson["text"], 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] += chunkjson["text"]
+                # 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。")
+        if chunkjson['event_type'] == 'stream-end': break
+    return result
+
+
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
+    """
+    发送至chatGPT，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
+    """
+    # if is_any_api_key(inputs):
+    #     chatbot._cookies['api_key'] = inputs
+    #     chatbot.append(("输入已识别为Cohere的api_key", what_keys(inputs)))
+    #     yield from update_ui(chatbot=chatbot, history=history, msg="api_key已导入") # 刷新界面
+    #     return
+    # elif not is_any_api_key(chatbot._cookies['api_key']):
+    #     chatbot.append((inputs, "缺少api_key。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。"))
+    #     yield from update_ui(chatbot=chatbot, history=history, msg="缺少api_key") # 刷新界面
+    #     return
+
+    user_input = inputs
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+
+    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
+
+    # check mis-behavior
+    if is_the_upload_folder(user_input):
+        chatbot[-1] = (inputs, f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+        time.sleep(2)
+
+    try:
+        headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+    except RuntimeError as e:
+        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
+        return
+
+    # 检查endpoint是否合法
+    try:
+        from .bridge_all import model_info
+        endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
+    except:
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (inputs, tb_str)
+        yield from update_ui(chatbot=chatbot, history=history, msg="Endpoint不满足要求") # 刷新界面
+        return
+
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
+            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.iter_lines()
+        while True:
+            try:
+                chunk = next(stream_response)
+            except StopIteration:
+                # 非Cohere官方接口的出现这样的报错，Cohere和API2D不会走这里
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                # 其他情况，直接返回报错
+                chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                yield from update_ui(chatbot=chatbot, history=history, msg="非Cohere官方接口返回了错误:" + chunk.decode()) # 刷新界面
+                return
+
+            # 提前读取一些信息 （用于判断异常）
+            chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
+
+            if chunkjson:
+                try:
+                    if chunkjson['event_type'] == 'stream-start':
+                        continue
+                    if chunkjson['event_type'] == 'text-generation':
+                        gpt_replying_buffer = gpt_replying_buffer + chunkjson["text"]
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+                    if chunkjson['event_type'] == 'stream-end':
+                        log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+                        break
+                except Exception as e:
+                    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)
+                    chunk_decoded = chunk.decode()
+                    error_msg = chunk_decoded
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
+                    return
+
+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    Cohere_website = ' 请登录Cohere查看详情 https://platform.Cohere.com/signup'
+    if "reduce the length" in error_msg:
+        if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
+                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
+    elif "does not exist" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
+    elif "Incorrect API key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. Cohere以提供了不正确的API_KEY为由, 拒绝服务. " + Cohere_website)
+    elif "exceeded your current quota" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. Cohere以账户额度不足为由, 拒绝服务." + Cohere_website)
+    elif "account is not active" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "associated with a deactivated account" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "API key has been deactivated" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] API key has been deactivated. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "bad forward key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
+    elif "Not enough point" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
+    else:
+        from toolbox import regular_txt_to_markdown
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+    return chatbot, history
+
+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
+    """
+    # if not is_any_api_key(llm_kwargs['api_key']):
+    #     raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
+
+    api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}"
+    }
+    if API_ORG.startswith('org-'): headers.update({"Cohere-Organization": API_ORG})
+    if llm_kwargs['llm_model'].startswith('azure-'):
+        headers.update({"api-key": api_key})
+        if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
+            azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
+            headers.update({"api-key": azure_api_key_unshared})
+
+    conversation_cnt = len(history) // 2
+
+    messages = [{"role": "SYSTEM", "message": 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["message"] = history[index]
+            what_gpt_answer = {}
+            what_gpt_answer["role"] = "CHATBOT"
+            what_gpt_answer["message"] = history[index+1]
+            if what_i_have_asked["message"] != "":
+                if what_gpt_answer["message"] == "": continue
+                if what_gpt_answer["message"] == timeout_bot_msg: continue
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+            else:
+                messages[-1]['message'] = what_gpt_answer['message']
+
+    model = llm_kwargs['llm_model']
+    if model.startswith('cohere-'): model = model[len('cohere-'):]
+    payload = {
+        "model": model,
+        "message": inputs,
+        "chat_history": 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,
+    }
+
+    return headers,payload
+
+
--- a/request_llms/bridge_google_gemini.py
+++ b/request_llms/bridge_google_gemini.py
@@ -7,6 +7,7 @@ import re
 import os
 import time
 from request_llms.com_google import GoogleChatInit
+from toolbox import ChatBotWithCookies
 from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc

 proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY')
@@ -20,7 +21,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
    if get_conf("GEMINI_API_KEY") == "":
        raise ValueError(f"请配置 GEMINI_API_KEY。")

-    genai = GoogleChatInit()
+    genai = GoogleChatInit(llm_kwargs)
    watch_dog_patience = 5  # 看门狗的耐心, 设置5秒即可
    gpt_replying_buffer = ''
    stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt)
@@ -44,7 +45,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
    return gpt_replying_buffer


-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
    # 检查API_KEY
    if get_conf("GEMINI_API_KEY") == "":
        yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
@@ -70,7 +72,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp

    chatbot.append((inputs, ""))
    yield from update_ui(chatbot=chatbot, history=history)
-    genai = GoogleChatInit()
+    genai = GoogleChatInit(llm_kwargs)
    retry = 0
    while True:
        try:
--- a/request_llms/bridge_jittorllms_llama.py
+++ b/request_llms/bridge_jittorllms_llama.py
@@ -1,10 +1,10 @@

-from transformers import AutoModel, AutoTokenizer
 import time
 import threading
 import importlib
 from toolbox import update_ui, get_conf
 from multiprocessing import Process, Pipe
+from transformers import AutoModel, AutoTokenizer

 load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"

@@ -106,7 +106,8 @@ class GetGLMHandle(Process):
 global llama_glm_handle
 llama_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_jittorllms_pangualpha.py
+++ b/request_llms/bridge_jittorllms_pangualpha.py
@@ -1,10 +1,10 @@

-from transformers import AutoModel, AutoTokenizer
 import time
 import threading
 import importlib
 from toolbox import update_ui, get_conf
 from multiprocessing import Process, Pipe
+from transformers import AutoModel, AutoTokenizer

 load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"

@@ -106,7 +106,8 @@ class GetGLMHandle(Process):
 global pangu_glm_handle
 pangu_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_jittorllms_rwkv.py
+++ b/request_llms/bridge_jittorllms_rwkv.py
@@ -106,7 +106,8 @@ class GetGLMHandle(Process):
 global rwkv_glm_handle
 rwkv_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_moonshot.py
+++ b/request_llms/bridge_moonshot.py
@@ -0,0 +1,197 @@
+# encoding: utf-8
+# @Time   : 2024/3/3
+# @Author : Spike
+# @Descr   :
+import json
+import os
+import time
+import logging
+
+from toolbox import get_conf, update_ui, log_chat
+from toolbox import ChatBotWithCookies
+
+import requests
+
+
+class MoonShotInit:
+
+    def __init__(self):
+        self.llm_model = None
+        self.url = 'https://api.moonshot.cn/v1/chat/completions'
+        self.api_key = get_conf('MOONSHOT_API_KEY')
+
+    def __converter_file(self, user_input: str):
+        what_ask = []
+        for f in user_input.splitlines():
+            if os.path.exists(f):
+                files = []
+                if os.path.isdir(f):
+                    file_list = os.listdir(f)
+                    files.extend([os.path.join(f, file) for file in file_list])
+                else:
+                    files.append(f)
+                for file in files:
+                    if file.split('.')[-1] in ['pdf']:
+                        with open(file, 'r') as fp:
+                            from crazy_functions.crazy_utils import read_and_clean_pdf_text
+                            file_content, _ = read_and_clean_pdf_text(fp)
+                        what_ask.append({"role": "system", "content": file_content})
+        return what_ask
+
+    def __converter_user(self, user_input: str):
+        what_i_ask_now = {"role": "user", "content": user_input}
+        return what_i_ask_now
+
+    def __conversation_history(self, history):
+        conversation_cnt = len(history) // 2
+        messages = []
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = {
+                    "role": "user",
+                    "content": str(history[index])
+                }
+                what_gpt_answer = {
+                    "role": "assistant",
+                    "content": str(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']
+        return messages
+
+    def _analysis_content(self, chuck):
+        chunk_decoded = chuck.decode("utf-8")
+        chunk_json = {}
+        content = ""
+        try:
+            chunk_json = json.loads(chunk_decoded[6:])
+            content = chunk_json['choices'][0]["delta"].get("content", "")
+        except:
+            pass
+        return chunk_decoded, chunk_json, content
+
+    def generate_payload(self, inputs, llm_kwargs, history, system_prompt, stream):
+        self.llm_model = llm_kwargs['llm_model']
+        llm_kwargs.update({'use-key': self.api_key})
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.extend(self.__converter_file(inputs))
+        for i in history[0::2]:    # 历史文件继续上传
+            messages.extend(self.__converter_file(i))
+        messages.extend(self.__conversation_history(history))
+        messages.append(self.__converter_user(inputs))
+        header = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+        }
+        payload = {
+            "model": self.llm_model,
+            "messages": messages,
+            "temperature": llm_kwargs.get('temperature', 0.3),  # 1.0,
+            "top_p": llm_kwargs.get('top_p', 1.0),  # 1.0,
+            "n": llm_kwargs.get('n_choices', 1),
+            "stream": stream
+        }
+        return payload, header
+
+    def generate_messages(self, inputs, llm_kwargs, history, system_prompt, stream):
+        payload, headers = self.generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+        response = requests.post(self.url, headers=headers, json=payload, stream=stream)
+
+        chunk_content = ""
+        gpt_bro_result = ""
+        for chuck in response.iter_lines():
+            chunk_decoded, check_json, content = self._analysis_content(chuck)
+            chunk_content += chunk_decoded
+            if content:
+                gpt_bro_result += content
+                yield content, gpt_bro_result, ''
+            else:
+                error_msg = msg_handle_error(llm_kwargs, chunk_decoded)
+                if error_msg:
+                    yield error_msg, gpt_bro_result, error_msg
+                    break
+
+
+def msg_handle_error(llm_kwargs, chunk_decoded):
+    use_ket = llm_kwargs.get('use-key', '')
+    api_key_encryption = use_ket[:8] + '****' + use_ket[-5:]
+    openai_website = f' 请登录OpenAI查看详情 https://platform.openai.com/signup  api-key: `{api_key_encryption}`'
+    error_msg = ''
+    if "does not exist" in chunk_decoded:
+        error_msg = f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格."
+    elif "Incorrect API key" in chunk_decoded:
+        error_msg = f"[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务." + openai_website
+    elif "exceeded your current quota" in chunk_decoded:
+        error_msg = "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website
+    elif "account is not active" in chunk_decoded:
+        error_msg = "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "associated with a deactivated account" in chunk_decoded:
+        error_msg = "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "API key has been deactivated" in chunk_decoded:
+        error_msg = "[Local Message] API key has been deactivated. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "bad forward key" in chunk_decoded:
+        error_msg = "[Local Message] Bad forward key. API2D账户额度不足."
+    elif "Not enough point" in chunk_decoded:
+        error_msg = "[Local Message] Not enough point. API2D账户点数不足."
+    elif 'error' in str(chunk_decoded).lower():
+        try:
+            error_msg = json.dumps(json.loads(chunk_decoded[:6]), indent=4, ensure_ascii=False)
+        except:
+            error_msg = chunk_decoded
+    return error_msg
+
+
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
+    chatbot.append([inputs, ""])
+
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")  # 刷新界面
+    gpt_bro_init = MoonShotInit()
+    history.extend([inputs, ''])
+    stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, system_prompt, stream)
+    for content, gpt_bro_result, error_bro_meg in stream_response:
+        chatbot[-1] = [inputs, gpt_bro_result]
+        history[-1] = gpt_bro_result
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        if error_bro_meg:
+            chatbot[-1] = [inputs, error_bro_meg]
+            history = history[:-2]
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+            break
+    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_bro_result)
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
+                                  console_slience=False):
+    gpt_bro_init = MoonShotInit()
+    watch_dog_patience = 60  # 看门狗的耐心, 设置10秒即可
+    stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, sys_prompt, True)
+    moonshot_bro_result = ''
+    for content, moonshot_bro_result, error_bro_meg in stream_response:
+        moonshot_bro_result = moonshot_bro_result
+        if error_bro_meg:
+            if len(observe_window) >= 3:
+                observe_window[2] = error_bro_meg
+            return f'{moonshot_bro_result} 对话错误'
+            # 观测窗
+        if len(observe_window) >= 1:
+            observe_window[0] = moonshot_bro_result
+        if len(observe_window) >= 2:
+            if (time.time() - observe_window[1]) > watch_dog_patience:
+                observe_window[2] = "请求超时，程序终止。"
+                raise RuntimeError(f"{moonshot_bro_result} 程序终止。")
+    return moonshot_bro_result
+
+if __name__ == '__main__':
+    moon_ai = MoonShotInit()
+    for g in moon_ai.generate_messages('hello', {'llm_model': 'moonshot-v1-8k'},
+                                       [], '', True):
+        print(g)
--- a/request_llms/bridge_moss.py
+++ b/request_llms/bridge_moss.py
@@ -171,7 +171,8 @@ class GetGLMHandle(Process):
 global moss_handle
 moss_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_qianfan.py
+++ b/request_llms/bridge_qianfan.py
@@ -117,7 +117,8 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
                raise RuntimeError(dec['error_msg'])


-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        ⭐多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_qwen.py
+++ b/request_llms/bridge_qwen.py
@@ -5,7 +5,8 @@ from toolbox import check_packages, report_exception

 model_name = 'Qwen'

-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        ⭐多线程方法
        函数的说明请见 request_llms/bridge_all.py
@@ -47,6 +48,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
    if additional_fn is not None:
        from core_functional import handle_core_functionality
        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+        chatbot[-1] = (inputs, "")
+        yield from update_ui(chatbot=chatbot, history=history)

    # 开始接收回复
    from .com_qwenapi import QwenRequestInstance
--- a/request_llms/bridge_skylark2.py
+++ b/request_llms/bridge_skylark2.py
@@ -9,7 +9,8 @@ def validate_key():
    if YUNQUE_SECRET_KEY == '': return False
    return True

-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        ⭐ 多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_spark.py
+++ b/request_llms/bridge_spark.py
@@ -13,7 +13,8 @@ def validate_key():
        return False
    return True

-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        ⭐多线程方法
        函数的说明请见 request_llms/bridge_all.py
--- a/request_llms/bridge_yimodel.py
+++ b/request_llms/bridge_yimodel.py
@@ -0,0 +1,283 @@
+# 借鉴自同目录下的bridge_chatgpt.py
+
+"""
+    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_long_connection：支持多线程
+"""
+
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+import random
+
+# config_private.py放自己的秘密如API和代理网址
+# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
+from toolbox import get_conf, update_ui, trimmed_format_exc, is_the_upload_folder, read_one_api_model_name
+proxies, TIMEOUT_SECONDS, MAX_RETRY, YIMODEL_API_KEY = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'YIMODEL_API_KEY')
+
+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
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+def decode_chunk(chunk):
+    # 提前读取一些信息（用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    is_last_chunk = False
+    try:
+        chunkjson = json.loads(chunk_decoded[6:])
+        is_last_chunk = chunkjson.get("lastOne", False)
+    except:
+        pass
+    return chunk_decoded, chunkjson, is_last_chunk
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], 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：
+        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
+    if inputs == "":     inputs = "空空如也的输入栏"
+    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    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:
+            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.iter_lines()
+    result = ''
+    is_head_of_the_stream = True
+    while True:
+        try: chunk = next(stream_response)
+        except StopIteration:
+            break
+        except requests.exceptions.ConnectionError:
+            chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+        chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
+        if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r'"role":"assistant"' in chunk_decoded):
+            # 数据流的第一帧不携带content
+            is_head_of_the_stream = False; continue
+        if chunk:
+            try:
+                if is_last_chunk:
+                    # 判定为数据流的结束，gpt_replying_buffer也写完了
+                    logging.info(f'[response] {result}')
+                    break
+                result += chunkjson['choices'][0]["delta"]["content"]
+                if not console_slience: print(chunkjson['choices'][0]["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] += chunkjson['choices'][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。")
+            except Exception as e:
+                chunk = get_full_error(chunk, stream_response)
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                print(error_msg)
+                raise RuntimeError("Json解析不合常规")
+    return result
+
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+    发送至chatGPT，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
+    """
+    if len(YIMODEL_API_KEY) == 0:
+        raise RuntimeError("没有设置YIMODEL_API_KEY选项")
+    if inputs == "":     inputs = "空空如也的输入栏"
+    user_input = inputs
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+
+    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
+
+    # check mis-behavior
+    if is_the_upload_folder(user_input):
+        chatbot[-1] = (inputs, f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+        time.sleep(2)
+
+    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+
+    from .bridge_all import model_info
+    endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
+            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.iter_lines()
+        while True:
+            try:
+                chunk = next(stream_response)
+            except StopIteration:
+                break
+            except requests.exceptions.ConnectionError:
+                chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
+
+            # 提前读取一些信息 （用于判断异常）
+            chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
+
+            if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r'"role":"assistant"' in chunk_decoded):
+                # 数据流的第一帧不携带content
+                is_head_of_the_stream = False; continue
+
+            if chunk:
+                try:
+                    if is_last_chunk:
+                        # 判定为数据流的结束，gpt_replying_buffer也写完了
+                        logging.info(f'[response] {gpt_replying_buffer}')
+                        break
+                    # 处理数据流的主体
+                    status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
+                    gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
+                    # 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
+                    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:
+                    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)
+                    chunk_decoded = chunk.decode()
+                    error_msg = chunk_decoded
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
+                    return
+
+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    if "bad_request" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 已经超过了模型的最大上下文或是模型格式错误,请尝试削减单次输入的文本量。")
+    elif "authentication_error" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. 请确保API key有效。")
+    elif "not_found" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] {llm_kwargs['llm_model']} 无效，请确保使用小写的模型名称。")
+    elif "rate_limit" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 遇到了控制请求速率限制，请一分钟后重试。")
+    elif "system_busy" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 系统繁忙，请一分钟后重试。")
+    else:
+        from toolbox import regular_txt_to_markdown
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+    return chatbot, history
+
+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
+    """
+    api_key = f"Bearer {YIMODEL_API_KEY}"
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": api_key
+    }
+
+    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
+                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
+    messages.append(what_i_ask_now)
+    model = llm_kwargs['llm_model']
+    if llm_kwargs['llm_model'].startswith('one-api-'):
+        model = llm_kwargs['llm_model'][len('one-api-'):]
+        model, _ = read_one_api_model_name(model)
+    tokens = 600 if llm_kwargs['llm_model'] == 'yi-34b-chat-0205' else 4096    #yi-34b-chat-0205只有4k上下文...
+    payload = {
+        "model": model,
+        "messages": messages,
+        "temperature": llm_kwargs['temperature'],  # 1.0,
+        "stream": stream,
+        "max_tokens": tokens
+    }
+    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
--- a/request_llms/bridge_zhipu.py
+++ b/request_llms/bridge_zhipu.py
@@ -1,7 +1,8 @@
 import time
 import os
-from toolbox import update_ui, get_conf, update_ui_lastest_msg
+from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
 from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
+from toolbox import ChatBotWithCookies

 model_name = '智谱AI大模型'
 zhipuai_default_model = 'glm-4'
@@ -16,7 +17,8 @@ def make_media_input(inputs, image_paths):
        inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
    return inputs

-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
    """
        ⭐多线程方法
        函数的说明请见 request_llms/bridge_all.py
@@ -42,7 +44,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
    return response


-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
    """
        ⭐单线程方法
        函数的说明请见 request_llms/bridge_all.py
@@ -90,4 +93,5 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
        chatbot[-1] = [inputs, response]
        yield from update_ui(chatbot=chatbot, history=history)
    history.extend([inputs, response])
+    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
    yield from update_ui(chatbot=chatbot, history=history)
--- a/request_llms/com_google.py
+++ b/request_llms/com_google.py
@@ -114,8 +114,10 @@ def html_local_img(__file, layout="left", max_width=None, max_height=None, md=Tr


 class GoogleChatInit:
-    def __init__(self):
-        self.url_gemini = "https://generativelanguage.googleapis.com/v1beta/models/%m:streamGenerateContent?key=%k"
+    def __init__(self, llm_kwargs):
+        from .bridge_all import model_info
+        endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+        self.url_gemini = endpoint + "/%m:streamGenerateContent?key=%k"

    def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
        headers, payload = self.generate_message_payload(
--- a/request_llms/com_qwenapi.py
+++ b/request_llms/com_qwenapi.py
@@ -48,6 +48,10 @@ class QwenRequestInstance():
        for response in responses:
            if response.status_code == HTTPStatus.OK:
                if response.output.choices[0].finish_reason == 'stop':
+                    try:
+                        self.result_buf += response.output.choices[0].message.content
+                    except:
+                        pass
                    yield self.result_buf
                    break
                elif response.output.choices[0].finish_reason == 'length':
--- a/request_llms/com_zhipuglm.py
+++ b/request_llms/com_zhipuglm.py
@@ -8,7 +8,7 @@ from toolbox import get_conf, encode_image, get_pictures_list
 import logging, os


-def input_encode_handler(inputs, llm_kwargs):        
+def input_encode_handler(inputs:str, llm_kwargs:dict):
    if llm_kwargs["most_recent_uploaded"].get("path"):
        image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
    md_encode = []
@@ -28,7 +28,7 @@ class ZhipuChatInit:
        self.zhipu_bro = ZhipuAI(api_key=ZHIPUAI_API_KEY)
        self.model = ''

-    def __conversation_user(self, user_input: str, llm_kwargs):
+    def __conversation_user(self, user_input: str, llm_kwargs:dict):
        if self.model not in ["glm-4v"]:
            return {"role": "user", "content": user_input}
        else:
@@ -41,7 +41,7 @@ class ZhipuChatInit:
                what_i_have_asked['content'].append(img_d)
            return what_i_have_asked

-    def __conversation_history(self, history, llm_kwargs):
+    def __conversation_history(self, history:list, llm_kwargs:dict):
        messages = []
        conversation_cnt = len(history) // 2
        if conversation_cnt:
@@ -55,22 +55,67 @@ class ZhipuChatInit:
                messages.append(what_gpt_answer)
        return messages

-    def __conversation_message_payload(self, inputs, llm_kwargs, history, system_prompt):
+    @staticmethod
+    def preprocess_param(param, default=0.95, min_val=0.01, max_val=0.99):
+        """预处理参数，保证其在允许范围内，并处理精度问题"""
+        try:
+            param = float(param)
+        except ValueError:
+            return default
+
+        if param <= min_val:
+            return min_val
+        elif param >= max_val:
+            return max_val
+        else:
+            return round(param, 2)  # 可挑选精度，目前是两位小数
+
+    def __conversation_message_payload(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
        messages = []
        if system_prompt:
            messages.append({"role": "system", "content": system_prompt})
        self.model = llm_kwargs['llm_model']
        messages.extend(self.__conversation_history(history, llm_kwargs))  # 处理 history
+        if inputs.strip() == "": # 处理空输入导致报错的问题 https://github.com/binary-husky/gpt_academic/issues/1640 提示 {"error":{"code":"1214","message":"messages[1]:content和tool_calls 字段不能同时为空"}
+            inputs = "."    # 空格、换行、空字符串都会报错，所以用最没有意义的一个点代替
        messages.append(self.__conversation_user(inputs, llm_kwargs))  # 处理用户对话
+        """
+        采样温度，控制输出的随机性，必须为正数
+        取值范围是：(0.0, 1.0)，不能等于 0，默认值为 0.95，
+        值越大，会使输出更随机，更具创造性；
+        值越小，输出会更加稳定或确定
+        建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数
+        """
+        temperature = self.preprocess_param(
+            param=llm_kwargs.get('temperature', 0.95),
+            default=0.95,
+            min_val=0.01,
+            max_val=0.99
+        )
+        """
+        用温度取样的另一种方法，称为核取样
+        取值范围是：(0.0, 1.0) 开区间，
+        不能等于 0 或 1，默认值为 0.7
+        模型考虑具有 top_p 概率质量 tokens 的结果
+        例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens
+        建议您根据应用场景调整 top_p 或 temperature 参数，
+        但不要同时调整两个参数
+        """
+        top_p = self.preprocess_param(
+            param=llm_kwargs.get('top_p', 0.70),
+            default=0.70,
+            min_val=0.01,
+            max_val=0.99
+        )
        response = self.zhipu_bro.chat.completions.create(
            model=self.model, messages=messages, stream=True,
-            temperature=llm_kwargs.get('temperature', 0.95) * 0.95,  # 只能传默认的 temperature 和 top_p
-            top_p=llm_kwargs.get('top_p', 0.7) * 0.7,
-            max_tokens=llm_kwargs.get('max_tokens', 1024 * 4),  # 最大输出模型的一半
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=llm_kwargs.get('max_tokens', 1024 * 4),
        )
        return response

-    def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
+    def generate_chat(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
        self.model = llm_kwargs['llm_model']
        response = self.__conversation_message_payload(inputs, llm_kwargs, history, system_prompt)
        bro_results = ''
--- a/request_llms/local_llm_class.py
+++ b/request_llms/local_llm_class.py
@@ -1,6 +1,7 @@
 import time
 import threading
 from toolbox import update_ui, Singleton
+from toolbox import ChatBotWithCookies
 from multiprocessing import Process, Pipe
 from contextlib import redirect_stdout
 from request_llms.queued_pipe import create_queue_pipe
@@ -214,7 +215,7 @@ class LocalLLMHandle(Process):
 def get_local_llm_predict_fns(LLMSingletonClass, model_name, history_format='classic'):
    load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"

-    def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+    def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[], console_slience:bool=False):
        """
            refer to request_llms/bridge_all.py
        """
@@ -260,7 +261,8 @@ def get_local_llm_predict_fns(LLMSingletonClass, model_name, history_format='cla
                    raise RuntimeError("程序终止。")
        return response

-    def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
+    def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+                history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
        """
            refer to request_llms/bridge_all.py
        """
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-https://public.agent-matrix.com/publish/gradio-3.32.8-py3-none-any.whl
+https://public.agent-matrix.com/publish/gradio-3.32.9-py3-none-any.whl
 gradio-client==0.8
 pypdf2==2.12.1
 zhipuai>=2
@@ -8,6 +8,7 @@ pydantic==2.5.2
 protobuf==3.18
 transformers>=4.27.1
 scipdf_parser>=0.52
+anthropic>=0.18.1
 python-markdown-math
 pymdown-extensions
 websocket-client
@@ -16,7 +17,7 @@ prompt_toolkit
 latex2mathml
 python-docx
 mdtex2html
-anthropic
+dashscope
 pyautogen
 colorama
 Markdown
--- a/shared_utils/cookie_manager.py
+++ b/shared_utils/cookie_manager.py
@@ -0,0 +1,61 @@
+from typing import Callable
+def load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)->Callable:
+    def load_web_cookie_cache(persistent_cookie_, cookies_):
+        import gradio as gr
+        from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
+
+        ret = {}
+        for k in customize_btns:
+            ret.update({customize_btns[k]: gr.update(visible=False, value="")})
+
+        try: persistent_cookie_ = from_cookie_str(persistent_cookie_)    # persistent cookie to dict
+        except: return ret
+
+        customize_fn_overwrite_ = persistent_cookie_.get("custom_bnt", {})
+        cookies_['customize_fn_overwrite'] = customize_fn_overwrite_
+        ret.update({cookies: cookies_})
+
+        for k,v in persistent_cookie_["custom_bnt"].items():
+            if v['Title'] == "": continue
+            if k in customize_btns: ret.update({customize_btns[k]: gr.update(visible=True, value=v['Title'])})
+            else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
+        return ret
+    return load_web_cookie_cache
+
+
+def assign_btn__fn_builder(customize_btns, predefined_btns, cookies, web_cookie_cache)->Callable:
+    def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix, clean_up=False):
+        import gradio as gr
+        from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
+        ret = {}
+        # 读取之前的自定义按钮
+        customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
+        # 更新新的自定义按钮
+        customize_fn_overwrite_.update({
+            basic_btn_dropdown_:
+                {
+                    "Title":basic_fn_title,
+                    "Prefix":basic_fn_prefix,
+                    "Suffix":basic_fn_suffix,
+                }
+            }
+        )
+        if clean_up:
+            customize_fn_overwrite_ = {}
+        cookies_.update(customize_fn_overwrite_)    # 更新cookie
+        visible = (not clean_up) and (basic_fn_title != "")
+        if basic_btn_dropdown_ in customize_btns:
+            # 是自定义按钮，不是预定义按钮
+            ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
+        else:
+            # 是预定义按钮
+            ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
+        ret.update({cookies: cookies_})
+        try: persistent_cookie_ = from_cookie_str(persistent_cookie_)   # persistent cookie to dict
+        except: persistent_cookie_ = {}
+        persistent_cookie_["custom_bnt"] = customize_fn_overwrite_      # dict update new value
+        persistent_cookie_ = to_cookie_str(persistent_cookie_)          # persistent cookie to dict
+        ret.update({web_cookie_cache: persistent_cookie_})             # write persistent cookie
+        return ret
+    return assign_btn
+
--- a/shared_utils/fastapi_server.py
+++ b/shared_utils/fastapi_server.py
@@ -0,0 +1,211 @@
+"""
+Tests:
+
+- custom_path false / no user auth:
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+    -- block __pycache__ access(yes)
+        -- rel (yes)
+        -- abs (yes)
+    -- block user access(fail) http://localhost:45013/file=gpt_log/admin/chat_secrets.log
+        -- fix(commit f6bf05048c08f5cd84593f7fdc01e64dec1f584a)-> block successful
+
+- custom_path yes("/cc/gptac") / no user auth:
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+    -- block __pycache__ access(yes)
+    -- block user access(yes)
+
+- custom_path yes("/cc/gptac/") / no user auth:
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+    -- block user access(yes)
+
+- custom_path yes("/cc/gptac/") / + user auth:
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+    -- block user access(yes)
+    -- block user-wise access (yes)
+
+- custom_path no + user auth:
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+    -- block user access(yes)
+    -- block user-wise access (yes)
+
+queue cocurrent effectiveness
+    -- upload file(yes)
+    -- download file(yes)
+    -- websocket(yes)
+"""
+
+import os, requests, threading, time
+import uvicorn
+
+def _authorize_user(path_or_url, request, gradio_app):
+    from toolbox import get_conf, default_user_name
+    PATH_PRIVATE_UPLOAD, PATH_LOGGING = get_conf('PATH_PRIVATE_UPLOAD', 'PATH_LOGGING')
+    sensitive_path = None
+    path_or_url = os.path.relpath(path_or_url)
+    if path_or_url.startswith(PATH_LOGGING):
+        sensitive_path = PATH_LOGGING
+    if path_or_url.startswith(PATH_PRIVATE_UPLOAD):
+        sensitive_path = PATH_PRIVATE_UPLOAD
+    if sensitive_path:
+        token = request.cookies.get("access-token") or request.cookies.get("access-token-unsecure")
+        user = gradio_app.tokens.get(token)  # get user
+        allowed_users = [user, 'autogen', default_user_name]  # three user path that can be accessed
+        for user_allowed in allowed_users:
+            # exact match
+            if f"{os.sep}".join(path_or_url.split(os.sep)[:2]) == os.path.join(sensitive_path, user_allowed):
+                return True
+        return False # "越权访问!"
+    return True
+
+
+class Server(uvicorn.Server):
+    # A server that runs in a separate thread
+    def install_signal_handlers(self):
+        pass
+
+    def run_in_thread(self):
+        self.thread = threading.Thread(target=self.run, daemon=True)
+        self.thread.start()
+        while not self.started:
+            time.sleep(1e-3)
+
+    def close(self):
+        self.should_exit = True
+        self.thread.join()
+
+
+def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SSL_CERTFILE):
+    import uvicorn
+    import fastapi
+    import gradio as gr
+    from fastapi import FastAPI
+    from gradio.routes import App
+    from toolbox import get_conf
+    CUSTOM_PATH, PATH_LOGGING = get_conf('CUSTOM_PATH', 'PATH_LOGGING')
+
+    # --- --- configurate gradio app block --- ---
+    app_block:gr.Blocks
+    app_block.ssl_verify = False
+    app_block.auth_message = '请登录'
+    app_block.favicon_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "docs/logo.png")
+    app_block.auth = AUTHENTICATION if len(AUTHENTICATION) != 0 else None
+    app_block.blocked_paths = ["config.py", "__pycache__", "config_private.py", "docker-compose.yml", "Dockerfile", f"{PATH_LOGGING}/admin"]
+    app_block.dev_mode = False
+    app_block.config = app_block.get_config_file()
+    app_block.enable_queue = True
+    app_block.queue(concurrency_count=CONCURRENT_COUNT)
+    app_block.validate_queue_settings()
+    app_block.show_api = False
+    app_block.config = app_block.get_config_file()
+    max_threads = 40
+    app_block.max_threads = max(
+        app_block._queue.max_thread_count if app_block.enable_queue else 0, max_threads
+    )
+    app_block.is_colab = False
+    app_block.is_kaggle = False
+    app_block.is_sagemaker = False
+
+    gradio_app = App.create_app(app_block)
+
+    # --- --- replace gradio endpoint to forbid access to sensitive files --- ---
+    if len(AUTHENTICATION) > 0:
+        dependencies = []
+        endpoint = None
+        for route in list(gradio_app.router.routes):
+            if route.path == "/file/{path:path}":
+                gradio_app.router.routes.remove(route)
+            if route.path == "/file={path_or_url:path}":
+                dependencies = route.dependencies
+                endpoint = route.endpoint
+                gradio_app.router.routes.remove(route)
+        @gradio_app.get("/file/{path:path}", dependencies=dependencies)
+        @gradio_app.head("/file={path_or_url:path}", dependencies=dependencies)
+        @gradio_app.get("/file={path_or_url:path}", dependencies=dependencies)
+        async def file(path_or_url: str, request: fastapi.Request):
+            if len(AUTHENTICATION) > 0:
+                if not _authorize_user(path_or_url, request, gradio_app):
+                    return "越权访问!"
+            return await endpoint(path_or_url, request)
+
+    # --- --- app_lifespan --- ---
+    from contextlib import asynccontextmanager
+    @asynccontextmanager
+    async def app_lifespan(app):
+        async def startup_gradio_app():
+            if gradio_app.get_blocks().enable_queue:
+                gradio_app.get_blocks().startup_events()
+        async def shutdown_gradio_app():
+            pass
+        await startup_gradio_app() # startup logic here
+        yield  # The application will serve requests after this point
+        await shutdown_gradio_app() # cleanup/shutdown logic here
+
+    # --- --- FastAPI --- ---
+    fastapi_app = FastAPI(lifespan=app_lifespan)
+    fastapi_app.mount(CUSTOM_PATH, gradio_app)
+
+    # --- --- favicon --- ---
+    if CUSTOM_PATH != '/':
+        from fastapi.responses import FileResponse
+        @fastapi_app.get("/favicon.ico")
+        async def favicon():
+            return FileResponse(app_block.favicon_path)
+
+    # --- --- uvicorn.Config --- ---
+    ssl_keyfile = None if SSL_KEYFILE == "" else SSL_KEYFILE
+    ssl_certfile = None if SSL_CERTFILE == "" else SSL_CERTFILE
+    server_name = "0.0.0.0"
+    config = uvicorn.Config(
+        fastapi_app,
+        host=server_name,
+        port=PORT,
+        reload=False,
+        log_level="warning",
+        ssl_keyfile=ssl_keyfile,
+        ssl_certfile=ssl_certfile,
+    )
+    server = Server(config)
+    url_host_name = "localhost" if server_name == "0.0.0.0" else server_name
+    if ssl_keyfile is not None:
+        if ssl_certfile is None:
+            raise ValueError(
+                "ssl_certfile must be provided if ssl_keyfile is provided."
+            )
+        path_to_local_server = f"https://{url_host_name}:{PORT}/"
+    else:
+        path_to_local_server = f"http://{url_host_name}:{PORT}/"
+    if CUSTOM_PATH != '/':
+        path_to_local_server += CUSTOM_PATH.lstrip('/').rstrip('/') + '/'
+    # --- --- begin  --- ---
+    server.run_in_thread()
+
+    # --- --- after server launch --- ---
+    app_block.server = server
+    app_block.server_name = server_name
+    app_block.local_url = path_to_local_server
+    app_block.protocol = (
+        "https"
+        if app_block.local_url.startswith("https") or app_block.is_colab
+        else "http"
+    )
+
+    if app_block.enable_queue:
+        app_block._queue.set_url(path_to_local_server)
+
+    forbid_proxies = {
+        "http": "",
+        "https": "",
+    }
+    requests.get(f"{app_block.local_url}startup-events", verify=app_block.ssl_verify, proxies=forbid_proxies)
+    app_block.is_running = True
+    app_block.block_thread()
--- a/shared_utils/key_pattern_manager.py
+++ b/shared_utils/key_pattern_manager.py
@@ -28,6 +28,11 @@ def is_api2d_key(key):
    return bool(API_MATCH_API2D)


+def is_cohere_api_key(key):
+    API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{40}$", key)
+    return bool(API_MATCH_AZURE)
+
+
 def is_any_api_key(key):
    if ',' in key:
        keys = key.split(',')
@@ -35,7 +40,7 @@ def is_any_api_key(key):
            if is_any_api_key(k): return True
        return False
    else:
-        return is_openai_api_key(key) or is_api2d_key(key) or is_azure_api_key(key)
+        return is_openai_api_key(key) or is_api2d_key(key) or is_azure_api_key(key) or is_cohere_api_key(key)


 def what_keys(keys):
@@ -62,7 +67,7 @@ def select_api_key(keys, llm_model):
    avail_key_list = []
    key_list = keys.split(',')

-    if llm_model.startswith('gpt-'):
+    if llm_model.startswith('gpt-') or llm_model.startswith('one-api-'):
        for k in key_list:
            if is_openai_api_key(k): avail_key_list.append(k)

@@ -74,8 +79,12 @@ def select_api_key(keys, llm_model):
        for k in key_list:
            if is_azure_api_key(k): avail_key_list.append(k)

+    if llm_model.startswith('cohere-'):
+        for k in key_list:
+            if is_cohere_api_key(k): avail_key_list.append(k)
+
    if len(avail_key_list) == 0:
-        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure,claude,api2d等请求源）。")
+        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（左上角更换模型菜单中可切换openai,azure,claude,cohere等请求源）。")

    api_key = random.choice(avail_key_list) # 随机负载均衡
    return api_key
--- a/shared_utils/map_names.py
+++ b/shared_utils/map_names.py
@@ -0,0 +1,34 @@
+import re
+mapping_dic = {
+    # "qianfan": "qianfan（文心一言大模型）",
+    # "zhipuai": "zhipuai（智谱GLM4超级模型🔥）",
+    # "gpt-4-1106-preview": "gpt-4-1106-preview（新调优版本GPT-4🔥）",
+    # "gpt-4-vision-preview": "gpt-4-vision-preview（识图模型GPT-4V）",
+}
+
+rev_mapping_dic = {}
+for k, v in mapping_dic.items():
+    rev_mapping_dic[v] = k
+
+def map_model_to_friendly_names(m):
+    if m in mapping_dic:
+        return mapping_dic[m]
+    return m
+
+def map_friendly_names_to_model(m):
+    if m in rev_mapping_dic:
+        return rev_mapping_dic[m]
+    return m
+
+def read_one_api_model_name(model: str):
+    """return real model name and max_token.
+    """
+    max_token_pattern = r"\(max_token=(\d+)\)"
+    match = re.search(max_token_pattern, model)
+    if match:
+        max_token_tmp = match.group(1)  # 获取 max_token 的值
+        max_token_tmp = int(max_token_tmp)
+        model = re.sub(max_token_pattern, "", model)  # 从原字符串中删除 "(max_token=...)"
+    else:
+        max_token_tmp = 4096
+    return model, max_token_tmp
--- a/tests/test_llms.py
+++ b/tests/test_llms.py
@@ -11,28 +11,45 @@ def validate_path():


 validate_path()  # validate path so you can run from base directory
-if __name__ == "__main__":
-    # from request_llms.bridge_newbingfree import predict_no_ui_long_connection
-    # from request_llms.bridge_moss import predict_no_ui_long_connection
-    # from request_llms.bridge_jittorllms_pangualpha import predict_no_ui_long_connection
-    # from request_llms.bridge_jittorllms_llama import predict_no_ui_long_connection
-    # from request_llms.bridge_claude import predict_no_ui_long_connection
-    # from request_llms.bridge_internlm import predict_no_ui_long_connection
-    # from request_llms.bridge_deepseekcoder import predict_no_ui_long_connection
-    # from request_llms.bridge_qwen_7B import predict_no_ui_long_connection
-    from request_llms.bridge_qwen_local import predict_no_ui_long_connection

-    # from request_llms.bridge_spark import predict_no_ui_long_connection
-    # from request_llms.bridge_zhipu import predict_no_ui_long_connection
-    # from request_llms.bridge_chatglm3 import predict_no_ui_long_connection
+if "在线模型":
+    if __name__ == "__main__":
+        from request_llms.bridge_cohere import predict_no_ui_long_connection
+        # from request_llms.bridge_spark import predict_no_ui_long_connection
+        # from request_llms.bridge_zhipu import predict_no_ui_long_connection
+        # from request_llms.bridge_chatglm3 import predict_no_ui_long_connection
+        llm_kwargs = {
+            "llm_model": "command-r-plus",
+            "max_length": 4096,
+            "top_p": 1,
+            "temperature": 1,
+        }

-    llm_kwargs = {
-        "max_length": 4096,
-        "top_p": 1,
-        "temperature": 1,
-    }
+        result = predict_no_ui_long_connection(
+            inputs="请问什么是质子？", llm_kwargs=llm_kwargs, history=["你好", "我好！"], sys_prompt="系统"
+        )
+        print("final result:", result)
+        print("final result:", result)
+
+
+if "本地模型":
+    if __name__ == "__main__":
+        # from request_llms.bridge_newbingfree import predict_no_ui_long_connection
+        # from request_llms.bridge_moss import predict_no_ui_long_connection
+        # from request_llms.bridge_jittorllms_pangualpha import predict_no_ui_long_connection
+        # from request_llms.bridge_jittorllms_llama import predict_no_ui_long_connection
+        # from request_llms.bridge_claude import predict_no_ui_long_connection
+        # from request_llms.bridge_internlm import predict_no_ui_long_connection
+        # from request_llms.bridge_deepseekcoder import predict_no_ui_long_connection
+        # from request_llms.bridge_qwen_7B import predict_no_ui_long_connection
+        # from request_llms.bridge_qwen_local import predict_no_ui_long_connection
+        llm_kwargs = {
+            "max_length": 4096,
+            "top_p": 1,
+            "temperature": 1,
+        }
+        result = predict_no_ui_long_connection(
+            inputs="请问什么是质子？", llm_kwargs=llm_kwargs, history=["你好", "我好！"], sys_prompt=""
+        )
+        print("final result:", result)

-    result = predict_no_ui_long_connection(
-        inputs="请问什么是质子？", llm_kwargs=llm_kwargs, history=["你好", "我好！"], sys_prompt=""
-    )
-    print("final result:", result)
--- a/themes/common.js
+++ b/themes/common.js
@@ -2,6 +2,76 @@
 //  第 1 部分: 工具函数
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

+function push_data_to_gradio_component(DAT, ELEM_ID, TYPE) {
+    // type,               // type==="str" / type==="float"
+    if (TYPE == "str") {
+        // convert dat to string: do nothing
+    }
+    else if (TYPE == "no_conversion") {
+        // no nothing
+    }
+    else if (TYPE == "float") {
+        // convert dat to float
+        DAT = parseFloat(DAT);
+    }
+    const myEvent = new CustomEvent('gpt_academic_update_gradio_component', {
+        detail: {
+            data: DAT,
+            elem_id: ELEM_ID,
+        }
+    });
+    window.dispatchEvent(myEvent);
+}
+
+
+async function get_gradio_component(ELEM_ID) {
+    function waitFor(ELEM_ID) {
+        return new Promise((resolve) => {
+            const myEvent = new CustomEvent('gpt_academic_get_gradio_component_value', {
+                detail: {
+                    elem_id: ELEM_ID,
+                    resolve,
+                }
+            });
+            window.dispatchEvent(myEvent);
+        });
+    }
+    result = await waitFor(ELEM_ID);
+    return result;
+}
+
+
+async function get_data_from_gradio_component(ELEM_ID) {
+    let comp = await get_gradio_component(ELEM_ID);
+    return comp.props.value;
+}
+
+
+function update_array(arr, item, mode) {
+    //   // Remove "输入清除键"
+    //   p = updateArray(p, "输入清除键", "remove");
+    //   console.log(p); // Should log: ["基础功能区", "函数插件区"]
+
+    //   // Add "输入清除键"
+    //   p = updateArray(p, "输入清除键", "add");
+    //   console.log(p); // Should log: ["基础功能区", "函数插件区", "输入清除键"]
+
+    const index = arr.indexOf(item);
+    if (mode === "remove") {
+        if (index !== -1) {
+            // Item found, remove it
+            arr.splice(index, 1);
+        }
+    } else if (mode === "add") {
+        if (index === -1) {
+            // Item not found, add it
+            arr.push(item);
+        }
+    }
+    return arr;
+}
+
+
 function gradioApp() {
    // https://github.com/GaiZhenbiao/ChuanhuChatGPT/tree/main/web_assets/javascript
    const elems = document.getElementsByTagName('gradio-app');
@@ -14,6 +84,7 @@ function gradioApp() {
    return elem.shadowRoot ? elem.shadowRoot : elem;
 }

+
 function setCookie(name, value, days) {
    var expires = "";

@@ -26,6 +97,7 @@ function setCookie(name, value, days) {
    document.cookie = name + "=" + value + expires + "; path=/";
 }

+
 function getCookie(name) {
    var decodedCookie = decodeURIComponent(document.cookie);
    var cookies = decodedCookie.split(';');
@@ -41,6 +113,7 @@ function getCookie(name) {
    return null;
 }

+
 let toastCount = 0;
 function toast_push(msg, duration) {
    duration = isNaN(duration) ? 3000 : duration;
@@ -63,6 +136,7 @@ function toast_push(msg, duration) {
    toastCount++;
 }

+
 function toast_up(msg) {
    var m = document.getElementById('toast_up');
    if (m) {
@@ -75,6 +149,7 @@ function toast_up(msg) {
    document.body.appendChild(m);
 }

+
 function toast_down() {
    var m = document.getElementById('toast_up');
    if (m) {
@@ -82,6 +157,7 @@ function toast_down() {
    }
 }

+
 function begin_loading_status() {
    // Create the loader div and add styling
    var loader = document.createElement('div');
@@ -256,6 +332,7 @@ function do_something_but_not_too_frequently(min_interval, func) {
    }
 }

+
 function chatbotContentChanged(attempt = 1, force = false) {
    // https://github.com/GaiZhenbiao/ChuanhuChatGPT/tree/main/web_assets/javascript
    for (var i = 0; i < attempt; i++) {
@@ -272,7 +349,6 @@ function chatbotContentChanged(attempt = 1, force = false) {
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 //  第 3 部分: chatbot动态高度调整
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-
 function chatbotAutoHeight() {
    // 自动调整高度：立即
    function update_height() {
@@ -304,6 +380,7 @@ function chatbotAutoHeight() {
    setInterval(function () { update_height_slow() }, 50); // 每50毫秒执行一次
 }

+
 swapped = false;
 function swap_input_area() {
    // Get the elements to be swapped
@@ -323,6 +400,7 @@ function swap_input_area() {
    else { swapped = true; }
 }

+
 function get_elements(consider_state_panel = false) {
    var chatbot = document.querySelector('#gpt-chatbot > div.wrap.svelte-18telvq');
    if (!chatbot) {
@@ -420,6 +498,7 @@ async function upload_files(files) {
    }
 }

+
 function register_func_paste(input) {
    let paste_files = [];
    if (input) {
@@ -446,6 +525,7 @@ function register_func_paste(input) {
    }
 }

+
 function register_func_drag(elem) {
    if (elem) {
        const dragEvents = ["dragover"];
@@ -482,6 +562,7 @@ function register_func_drag(elem) {
    }
 }

+
 function elem_upload_component_pop_message(elem) {
    if (elem) {
        const dragEvents = ["dragover"];
@@ -511,6 +592,7 @@ function elem_upload_component_pop_message(elem) {
    }
 }

+
 function register_upload_event() {
    locate_upload_elems();
    if (elem_upload_float) {
@@ -533,6 +615,7 @@ function register_upload_event() {
    }
 }

+
 function monitoring_input_box() {
    register_upload_event();

@@ -566,7 +649,6 @@ window.addEventListener("DOMContentLoaded", function () {
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 //  第 5 部分: 音频按钮样式变化
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-
 function audio_fn_init() {
    let audio_component = document.getElementById('elem_audio');
    if (audio_component) {
@@ -603,6 +685,7 @@ function audio_fn_init() {
    }
 }

+
 function minor_ui_adjustment() {
    let cbsc_area = document.getElementById('cbsc');
    cbsc_area.style.paddingTop = '15px';
@@ -695,21 +778,6 @@ function limit_scroll_position() {
 //  第 7 部分: JS初始化函数
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

-function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
-    audio_fn_init();
-    minor_ui_adjustment();
-    chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
-    var chatbotObserver = new MutationObserver(() => {
-        chatbotContentChanged(1);
-    });
-    chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
-    if (LAYOUT === "LEFT-RIGHT") { chatbotAutoHeight(); }
-    if (LAYOUT === "LEFT-RIGHT") { limit_scroll_position(); }
-    // setInterval(function () { uml("mermaid") }, 5000); // 每50毫秒执行一次
-
-}
-
-
 function loadLive2D() {
    try {
        $("<link>").attr({ href: "file=themes/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css" }).appendTo('head');
@@ -731,12 +799,12 @@ function loadLive2D() {
                        live2d_settings['canTakeScreenshot'] = false;
                        live2d_settings['canTurnToHomePage'] = false;
                        live2d_settings['canTurnToAboutPage'] = false;
-                        live2d_settings['showHitokoto'] = false;         // 显示一言
+                        live2d_settings['showHitokoto'] = false;          // 显示一言
                        live2d_settings['showF12Status'] = false;         // 显示加载状态
                        live2d_settings['showF12Message'] = false;        // 显示看板娘消息
-                        live2d_settings['showF12OpenMsg'] = false;         // 显示控制台打开提示
-                        live2d_settings['showCopyMessage'] = false;         // 显示 复制内容 提示
-                        live2d_settings['showWelcomeMessage'] = true;         // 显示进入面页欢迎词
+                        live2d_settings['showF12OpenMsg'] = false;        // 显示控制台打开提示
+                        live2d_settings['showCopyMessage'] = false;       // 显示 复制内容 提示
+                        live2d_settings['showWelcomeMessage'] = true;     // 显示进入面页欢迎词
                        /* 在 initModel 前添加 */
                        initModel("file=themes/waifu_plugin/waifu-tips.json");
                    }
@@ -746,7 +814,8 @@ function loadLive2D() {
    } catch (err) { console.log("[Error] JQuery is not defined.") }
 }

-function get_checkbox_selected_items(elem_id){
+
+function get_checkbox_selected_items(elem_id) {
    display_panel_arr = [];
    document.getElementById(elem_id).querySelector('[data-testid="checkbox-group"]').querySelectorAll('label').forEach(label => {
        // Get the span text
@@ -760,51 +829,52 @@ function get_checkbox_selected_items(elem_id){
    return display_panel_arr;
 }

-function set_checkbox(key, bool, set_twice=false) {
-    set_success = false;
-    elem_ids = ["cbsc", "cbs"]
-    elem_ids.forEach(id => {
-        document.getElementById(id).querySelector('[data-testid="checkbox-group"]').querySelectorAll('label').forEach(label => {
-            // Get the span text
-            const spanText = label.querySelector('span').textContent;
-            if (spanText === key) {
-                if (bool){
-                    label.classList.add('selected');
-                } else {
-                    if (label.classList.contains('selected')) {
-                        label.classList.remove('selected');
-                    }
-                }
-                if (set_twice){
-                    setTimeout(() => {
-                        if (bool){
-                            label.classList.add('selected');
-                        } else {
-                            if (label.classList.contains('selected')) {
-                                label.classList.remove('selected');
-                            }
-                        }
-                    }, 5000);
-                }

-                label.querySelector('input').checked = bool;
-                set_success = true;
-                return
+function gpt_academic_gradio_saveload(
+    save_or_load,       // save_or_load==="save" / save_or_load==="load"
+    elem_id,            // element id
+    cookie_key,         // cookie key
+    save_value = "",      // save value
+    load_type = "str",  // type==="str" / type==="float"
+    load_default = false, // load default value
+    load_default_value = ""
+) {
+    if (save_or_load === "load") {
+        let value = getCookie(cookie_key);
+        if (value) {
+            console.log('加载cookie', elem_id, value)
+            push_data_to_gradio_component(value, elem_id, load_type);
+        }
+        else {
+            if (load_default) {
+                console.log('加载cookie的默认值', elem_id, load_default_value)
+                push_data_to_gradio_component(load_default_value, elem_id, load_type);
            }
-        });
-    });
-
-    if (!set_success){
-        console.log("设置checkbox失败，没有找到对应的key")
+        }
+    }
+    if (save_or_load === "save") {
+        setCookie(cookie_key, save_value, 365);
    }
 }

-function apply_cookie_for_checkbox(dark) {
-    // console.log("apply_cookie_for_checkboxes")
-    let searchString = "输入清除键";
-    let bool_value = "False";

-    //////////////////  darkmode  ///////////////////
+async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout) {
+    // 第一部分，布局初始化
+    audio_fn_init();
+    minor_ui_adjustment();
+    chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
+    var chatbotObserver = new MutationObserver(() => {
+        chatbotContentChanged(1);
+    });
+    chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
+    if (layout === "LEFT-RIGHT") { chatbotAutoHeight(); }
+    if (layout === "LEFT-RIGHT") { limit_scroll_position(); }
+
+    // 第二部分，读取Cookie，初始话界面
+    let searchString = "";
+    let bool_value = "";
+
+    //  darkmode 深色模式
    if (getCookie("js_darkmode_cookie")) {
        dark = getCookie("js_darkmode_cookie")
    }
@@ -819,29 +889,41 @@ function apply_cookie_for_checkbox(dark) {
        }
    }

-    ////////////////////// clearButton ///////////////////////////
+    // SysPrompt 系统静默提示词
+    gpt_academic_gradio_saveload("load", "elem_prompt", "js_system_prompt_cookie", null, "str");
+
+    // Temperature 大模型温度参数
+    gpt_academic_gradio_saveload("load", "elem_temperature", "js_temperature_cookie", null, "float");
+
+    // clearButton 自动清除按钮
    if (getCookie("js_clearbtn_show_cookie")) {
        // have cookie
        bool_value = getCookie("js_clearbtn_show_cookie")
        bool_value = bool_value == "True";
        searchString = "输入清除键";
+
        if (bool_value) {
-            let clearButton = document.getElementById("elem_clear");
-            let clearButton2 = document.getElementById("elem_clear2");
-            clearButton.style.display = "block";
-            clearButton2.style.display = "block";
-            set_checkbox(searchString, true);
+            // make btns appear
+            let clearButton = document.getElementById("elem_clear"); clearButton.style.display = "block";
+            let clearButton2 = document.getElementById("elem_clear2"); clearButton2.style.display = "block";
+            // deal with checkboxes
+            let arr_with_clear_btn = update_array(
+                await get_data_from_gradio_component('cbs'), "输入清除键", "add"
+            )
+            push_data_to_gradio_component(arr_with_clear_btn, "cbs", "no_conversion");
        } else {
-            let clearButton = document.getElementById("elem_clear");
-            let clearButton2 = document.getElementById("elem_clear2");
-            clearButton.style.display = "none";
-            clearButton2.style.display = "none";
-            set_checkbox(searchString, false);
+            // make btns disappear
+            let clearButton = document.getElementById("elem_clear"); clearButton.style.display = "none";
+            let clearButton2 = document.getElementById("elem_clear2"); clearButton2.style.display = "none";
+            // deal with checkboxes
+            let arr_without_clear_btn = update_array(
+                await get_data_from_gradio_component('cbs'), "输入清除键", "remove"
+            )
+            push_data_to_gradio_component(arr_without_clear_btn, "cbs", "no_conversion");
        }
    }

-    ////////////////////// live2d ///////////////////////////
-
+    // live2d 显示
    if (getCookie("js_live2d_show_cookie")) {
        // have cookie
        searchString = "添加Live2D形象";
@@ -849,17 +931,23 @@ function apply_cookie_for_checkbox(dark) {
        bool_value = bool_value == "True";
        if (bool_value) {
            loadLive2D();
-            set_checkbox(searchString, true);
+            let arr_with_live2d = update_array(
+                await get_data_from_gradio_component('cbsc'), "添加Live2D形象", "add"
+            )
+            push_data_to_gradio_component(arr_with_live2d, "cbsc", "no_conversion");
        } else {
-            $('.waifu').hide();
-            set_checkbox(searchString, false);
+            try {
+                $('.waifu').hide();
+                let arr_without_live2d = update_array(
+                    await get_data_from_gradio_component('cbsc'), "添加Live2D形象", "remove"
+                )
+                push_data_to_gradio_component(arr_without_live2d, "cbsc", "no_conversion");
+            } catch (error) {
+            }
        }
    } else {
        // do not have cookie
-        // get conf
-        display_panel_arr = get_checkbox_selected_items("cbsc");
-        searchString = "添加Live2D形象";
-        if (display_panel_arr.includes(searchString)) {
+        if (live2d) {
            loadLive2D();
        } else {
        }
--- a/themes/theme.py
+++ b/themes/theme.py
@@ -1,7 +1,10 @@
 import pickle
 import base64
 import uuid
+import json
 from toolbox import get_conf
+import json
+

 """
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
@@ -45,24 +48,24 @@ adjust_theme, advanced_css, theme_declaration, _ = load_dynamic_theme(get_conf("
 cookie相关工具函数
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 """
-
-def init_cookie(cookies):
+def assign_user_uuid(cookies):
    # 为每一位访问的用户赋予一个独一无二的uuid编码
    cookies.update({"uuid": uuid.uuid4()})
    return cookies


 def to_cookie_str(d):
-    # Pickle the dictionary and encode it as a string
-    pickled_dict = pickle.dumps(d)
-    cookie_value = base64.b64encode(pickled_dict).decode("utf-8")
+    # serialize the dictionary and encode it as a string
+    serialized_dict = json.dumps(d)
+    cookie_value = base64.b64encode(serialized_dict.encode('utf8')).decode("utf-8")
    return cookie_value


 def from_cookie_str(c):
-    # Decode the base64-encoded string and unpickle it into a dictionary
-    pickled_dict = base64.b64decode(c.encode("utf-8"))
-    return pickle.loads(pickled_dict)
+    # Decode the base64-encoded string and unserialize it into a dictionary
+    serialized_dict = base64.b64decode(c.encode("utf-8"))
+    serialized_dict.decode("utf-8")
+    return json.loads(serialized_dict)


 """
@@ -103,8 +106,8 @@ js_code_for_toggle_darkmode = """() => {
 }"""


-js_code_for_persistent_cookie_init = """(py_pickle_cookie, cookie) => {
-    return [getCookie("py_pickle_cookie"), cookie];
+js_code_for_persistent_cookie_init = """(web_cookie_cache, cookie) => {
+    return [getCookie("web_cookie_cache"), cookie];
 }
 """

@@ -175,11 +178,8 @@ setTimeout(() => {
 js_code_show_or_hide_group2 = """
 (display_panel_arr)=>{
 setTimeout(() => {
-    // console.log("display_panel_arr");
-    // get conf
    display_panel_arr = get_checkbox_selected_items("cbsc");

-    ////////////////////// 添加Live2D形象 ///////////////////////////
    let searchString = "添加Live2D形象";
    let ele = "none";
    if (display_panel_arr.includes(searchString)) {
@@ -190,7 +190,6 @@ setTimeout(() => {
        $('.waifu').hide();
    }

-
 }, 50);
 }
 """
--- a/toolbox.py
+++ b/toolbox.py
@@ -7,6 +7,8 @@ import base64
 import gradio
 import shutil
 import glob
+import logging
+import uuid
 from functools import wraps
 from shared_utils.config_loader import get_conf
 from shared_utils.config_loader import set_conf
@@ -25,11 +27,14 @@ from shared_utils.text_mask import apply_gpt_academic_string_mask
 from shared_utils.text_mask import build_gpt_academic_masked_string
 from shared_utils.text_mask import apply_gpt_academic_string_mask_langbased
 from shared_utils.text_mask import build_gpt_academic_masked_string_langbased
+from shared_utils.map_names import map_friendly_names_to_model
+from shared_utils.map_names import map_model_to_friendly_names
+from shared_utils.map_names import read_one_api_model_name
 from shared_utils.handle_upload import html_local_file
 from shared_utils.handle_upload import html_local_img
 from shared_utils.handle_upload import file_manifest_filter_type
 from shared_utils.handle_upload import extract_archive
-
+from typing import List
 pj = os.path.join
 default_user_name = "default_user"

@@ -81,7 +86,9 @@ def ArgsGeneralWrapper(f):
    该装饰器是大多数功能调用的入口。
    函数示意图：https://mermaid.live/edit#pako:eNqNVFtPGkEY_StkntoEDQtLoTw0sWqapjQxVWPabmOm7AiEZZcsQ9QiiW012qixqdeqqIn10geBh6ZR8PJnmAWe-hc6l3VhrWnLEzNzzvnO953ZyYOYoSIQAWOaMR5LQBN7hvoU3UN_g5iu7imAXEyT4wUF3Pd0dT3y9KGYYUJsmK8V0GPGs0-QjkyojZgwk0Fm82C2dVghX08U8EaoOHjOfoEMU0XmADRhOksVWnNLjdpM82qFzB6S5Q_WWsUhuqCc3JtAsVR_OoMnhyZwXgHWwbS1d4gnsLVZJp-P6mfVxveqAgqC70Jz_pQCOGDKM5xFdNNPDdilF6uSU_hOYqu4a3MHYDZLDzq5fodrC3PWcEaFGPUaRiqJWK_W9g9rvRITa4dhy_0nw67SiePMp3oSR6PPn41DGgllkvkizYwsrmtaejTFd8V4yekGmT1zqrt4XGlAy8WTuiPULF01LksZvukSajfQQRAxmYi5S0D81sDcyzapVdn6sYFHkjhhGyel3frVQnvsnbR23lEjlhIlaOJiFPWzU5G4tfNJo8ejwp47-TbvJkKKZvmxA6SKo16oaazJysfG6klr9T0pbTW2ZqzlL_XaT8fYbQLXe4mSmvoCZXMaa7FePW6s7jVqK9bujvse3WFjY5_Z4KfsA4oiPY4T7Drvn1tLJTbG1to1qR79ulgk89-oJbvZzbIwJty6u20LOReWa9BvwserUd9s9MIKc3x5TUWEoAhUyJK5y85w_yG-dFu_R9waoU7K581y8W_qLle35-rG9Nxcrz8QHRsc0K-r9NViYRT36KsFvCCNzDRMqvSVyzOKAnACpZECIvSvCs2UAhS9QHEwh43BST0GItjMIS_I8e-sLwnj9A262cxA_ZVh0OUY1LJiDSJ5MAEiUijYLUtBORR6KElyQPaCSRDpksNSd8AfluSgHPaFC17wjrOlbgbzyyFf4IFPDvoD_sJvnkdK-g
    """
-    def decorated(request: gradio.Request, cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg, *args):
+    def decorated(request: gradio.Request, cookies:dict, max_length:int, llm_model:str,
+                  txt:str, txt2:str, top_p:float, temperature:float, chatbot:list,
+                  history:list, system_prompt:str, plugin_advanced_arg:str, *args):
        txt_passon = txt
        if txt == "" and txt2 != "": txt_passon = txt2
        # 引入一个有cookie的chatbot
@@ -133,7 +140,7 @@ def ArgsGeneralWrapper(f):
    return decorated


-def update_ui(chatbot, history, msg="正常", **kwargs):  # 刷新界面
+def update_ui(chatbot:ChatBotWithCookies, history, msg="正常", **kwargs):  # 刷新界面
    """
    刷新用户界面
    """
@@ -163,7 +170,7 @@ def update_ui(chatbot, history, msg="正常", **kwargs):  # 刷新界面
    yield cookies, chatbot_gr, history, msg


-def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
+def update_ui_lastest_msg(lastmsg:str, chatbot:ChatBotWithCookies, history:list, delay=1):  # 刷新界面
    """
    刷新用户界面
    """
@@ -190,13 +197,12 @@ def CatchException(f):
    """

    @wraps(f)
-    def decorated(main_input, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, *args, **kwargs):
+    def decorated(main_input:str, llm_kwargs:dict, plugin_kwargs:dict,
+                  chatbot_with_cookie:ChatBotWithCookies, history:list, *args, **kwargs):
        try:
            yield from f(main_input, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, *args, **kwargs)
        except Exception as e:
-            from check_proxy import check_proxy
            from toolbox import get_conf
-            proxies = get_conf('proxies')
            tb_str = '```\n' + trimmed_format_exc() + '```'
            if len(chatbot_with_cookie) == 0:
                chatbot_with_cookie.clear()
@@ -249,7 +255,7 @@ def HotReload(f):
 """


-def get_reduce_token_percent(text):
+def get_reduce_token_percent(text:str):
    """
    * 此函数未来将被弃用
    """
@@ -268,7 +274,7 @@ def get_reduce_token_percent(text):


 def write_history_to_file(
-    history, file_basename=None, file_fullname=None, auto_caption=True
+    history:list, file_basename:str=None, file_fullname:str=None, auto_caption:bool=True
 ):
    """
    将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
@@ -302,7 +308,7 @@ def write_history_to_file(
    return res


-def regular_txt_to_markdown(text):
+def regular_txt_to_markdown(text:str):
    """
    将普通文本转换为Markdown格式的文本。
    """
@@ -312,7 +318,7 @@ def regular_txt_to_markdown(text):
    return text


-def report_exception(chatbot, history, a, b):
+def report_exception(chatbot:ChatBotWithCookies, history:list, a:str, b:str):
    """
    向chatbot中添加错误信息
    """
@@ -320,7 +326,7 @@ def report_exception(chatbot, history, a, b):
    history.extend([a, b])


-def find_free_port():
+def find_free_port()->int:
    """
    返回当前系统中可用的未使用端口。
    """
@@ -333,10 +339,9 @@ def find_free_port():
        return s.getsockname()[1]


-def find_recent_files(directory):
+def find_recent_files(directory:str)->List[str]:
    """
-    me: find files that is created with in one minutes under a directory with python, write a function
-    gpt: here it is!
+    Find files that is created with in one minutes under a directory with python, write a function
    """
    import os
    import time
@@ -359,7 +364,7 @@ def find_recent_files(directory):
    return recent_files


-def file_already_in_downloadzone(file, user_path):
+def file_already_in_downloadzone(file:str, user_path:str):
    try:
        parent_path = os.path.abspath(user_path)
        child_path = os.path.abspath(file)
@@ -371,7 +376,7 @@ def file_already_in_downloadzone(file, user_path):
        return False


-def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
+def promote_file_to_downloadzone(file:str, rename_file:str=None, chatbot:ChatBotWithCookies=None):
    # 将文件复制一份到下载区
    import shutil

@@ -406,12 +411,12 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
    return new_path


-def disable_auto_promotion(chatbot):
+def disable_auto_promotion(chatbot:ChatBotWithCookies):
    chatbot._cookies.update({"files_to_promote": []})
    return


-def del_outdated_uploads(outdate_time_seconds, target_path_base=None):
+def del_outdated_uploads(outdate_time_seconds:float, target_path_base:str=None):
    if target_path_base is None:
        user_upload_dir = get_conf("PATH_PRIVATE_UPLOAD")
    else:
@@ -464,7 +469,8 @@ def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False, om


 def on_file_uploaded(
-    request: gradio.Request, files, chatbot, txt, txt2, checkboxes, cookies
+    request: gradio.Request, files:List[str], chatbot:ChatBotWithCookies,
+    txt:str, txt2:str, checkboxes:List[str], cookies:dict
 ):
    """
    当文件被上传时的回调函数
@@ -528,18 +534,14 @@ def on_file_uploaded(
    return chatbot, txt, txt2, cookies


-def on_report_generated(cookies, files, chatbot):
-    # from toolbox import find_recent_files
-    # PATH_LOGGING = get_conf('PATH_LOGGING')
+def on_report_generated(cookies:dict, files:List[str], chatbot:ChatBotWithCookies):
    if "files_to_promote" in cookies:
        report_files = cookies["files_to_promote"]
        cookies.pop("files_to_promote")
    else:
        report_files = []
-    #     report_files = find_recent_files(PATH_LOGGING)
    if len(report_files) == 0:
        return cookies, None, chatbot
-    # files.extend(report_files)
    file_links = ""
    for f in report_files:
        file_links += (
@@ -819,7 +821,7 @@ def is_the_upload_folder(string):
        return False


-def get_user(chatbotwithcookies):
+def get_user(chatbotwithcookies:ChatBotWithCookies):
    return chatbotwithcookies._cookies.get("user_name", default_user_name)


@@ -902,7 +904,7 @@ def get_pictures_list(path):
    return file_manifest


-def have_any_recent_upload_image_files(chatbot):
+def have_any_recent_upload_image_files(chatbot:ChatBotWithCookies):
    _5min = 5 * 60
    if chatbot is None:
        return False, None  # chatbot is None
@@ -919,6 +921,18 @@ def have_any_recent_upload_image_files(chatbot):
    else:
        return False, None  # most_recent_uploaded is too old

+# Claude3 model supports graphic context dialogue, reads all images
+def every_image_file_in_path(chatbot:ChatBotWithCookies):
+    if chatbot is None:
+        return False, []  # chatbot is None
+    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    if not most_recent_uploaded:
+        return False, []  # most_recent_uploaded is None
+    path = most_recent_uploaded["path"]
+    file_manifest = get_pictures_list(path)
+    if len(file_manifest) == 0:
+        return False, []
+    return True, file_manifest

 # Function to encode the image
 def encode_image(image_path):
@@ -939,3 +953,65 @@ def check_packages(packages=[]):
        spam_spec = importlib.util.find_spec(p)
        if spam_spec is None:
            raise ModuleNotFoundError
+
+
+def map_file_to_sha256(file_path):
+    import hashlib
+
+    with open(file_path, 'rb') as file:
+        content = file.read()
+
+    # Calculate the SHA-256 hash of the file contents
+    sha_hash = hashlib.sha256(content).hexdigest()
+
+    return sha_hash
+
+
+def check_repeat_upload(new_pdf_path, pdf_hash):
+    '''
+    检查历史上传的文件是否与新上传的文件相同，如果相同则返回(True, 重复文件路径)，否则返回(False，None)
+    '''
+    from toolbox import get_conf
+    import PyPDF2
+
+    user_upload_dir = os.path.dirname(os.path.dirname(new_pdf_path))
+    file_name = os.path.basename(new_pdf_path)
+
+    file_manifest = [f for f in glob.glob(f'{user_upload_dir}/**/{file_name}', recursive=True)]
+
+    for saved_file in file_manifest:
+        with open(new_pdf_path, 'rb') as file1, open(saved_file, 'rb') as file2:
+            reader1 = PyPDF2.PdfFileReader(file1)
+            reader2 = PyPDF2.PdfFileReader(file2)
+
+            # 比较页数是否相同
+            if reader1.getNumPages() != reader2.getNumPages():
+                continue
+
+            # 比较每一页的内容是否相同
+            for page_num in range(reader1.getNumPages()):
+                page1 = reader1.getPage(page_num).extractText()
+                page2 = reader2.getPage(page_num).extractText()
+                if page1 != page2:
+                    continue
+
+        maybe_project_dir = glob.glob('{}/**/{}'.format(get_log_folder(), pdf_hash + ".tag"), recursive=True)
+
+
+        if len(maybe_project_dir) > 0:
+            return True, os.path.dirname(maybe_project_dir[0])
+
+    # 如果所有页的内容都相同，返回 True
+    return False, None
+
+def log_chat(llm_model: str, input_str: str, output_str: str):
+    try:
+        if output_str and input_str and llm_model:
+            uid = str(uuid.uuid4().hex)
+            logging.info(f"[Model({uid})] {llm_model}")
+            input_str = input_str.rstrip('\n')
+            logging.info(f"[Query({uid})]\n{input_str}")
+            output_str = output_str.rstrip('\n')
+            logging.info(f"[Response({uid})]\n{output_str}\n\n")
+    except:
+        print(trimmed_format_exc())
--- a/4
+++ b/4
@@ -1,5 +1,5 @@
 {
-  "version": 3.72,
+  "version": 3.74,
  "show_feature": true,
-  "new_feature": "支持切换多个智谱ai模型 <-> 用绘图功能增强部分插件 <-> 基础功能区支持自动切换中英提示词 <-> 支持Mermaid绘图库（让大模型绘制脑图） <-> 支持Gemini-pro <-> 支持直接拖拽文件到上传区 <-> 支持将图片粘贴到输入区"
+  "new_feature": "增加多用户文件鉴权验证提高安全性 <-> 优化oneapi接入方法 <-> 接入Cohere和月之暗面模型 <-> 简化挂载二级目录的步骤 <-> 支持Mermaid绘图库（让大模型绘制脑图）"
 }
作者	SHA1	备注	提交日期
Yuki	163f12c533	# fix com_zhipuglm.py illegal temperature problem (#1687 ) * Update com_zhipuglm.py # fix 用户在使用 zhipuai 界面时遇到了关于温度参数的非法参数错误	2024-04-08 12:17:07 +08:00
binary-husky	bdd46c5dd1	Version 3.74: Merge latest updates on dev branch (frontier) (#1621 ) * Update version to 3.74 * Add support for Yi Model API (#1635) * 更新以支持零一万物模型 * 删除newbing * 修改config --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * Refactor function signatures in bridge files * fix qwen api change * rename and ref functions * rename and move some cookie functions * 增加haiku模型，新增endpoint配置说明 (#1626) * haiku added * 新增haiku，新增endpoint配置说明 * Haiku added * 将说明同步至最新Endpoint --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * private_upload目录下进行文件鉴权 (#1596) * private_upload目录下进行文件鉴权 * minor fastapi adjustment * Add logging functionality to enable saving conversation records * waiting to fix username retrieve * support 2rd web path * allow accessing default user dir --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * remove yaml deps * fix favicon * fix abs path auth problem * forget to write a return * add `dashscope` to deps * fix GHSA-v9q9-xj86-953p * 用户名重叠越权访问patch (#1681) * add cohere model api access * cohere + can_multi_thread * fix block user access(fail) * fix fastapi bug * change cohere api endpoint * explain version --------- Co-authored-by: Menghuan1918 <menghuan2003@outlook.com> Co-authored-by: Skyzayre <120616113+Skyzayre@users.noreply.github.com> Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com>	2024-04-08 11:49:30 +08:00
binary-husky	ae51a0e686	fix GHSA-v9q9-xj86-953p	2024-04-05 20:47:11 +08:00
binary-husky	f2582ea137	fix qwen api change	2024-04-03 12:17:41 +08:00
binary-husky	ddd2fd84da	fix checkbox bugs	2024-04-02 19:42:55 +08:00
binary-husky	6c90ff80ea	add prompt and temperature to cookie	2024-04-02 18:02:00 +08:00
binary-husky	cb7c0703be	Update requirements.txt (#1668 )	2024-04-01 11:30:50 +08:00
binary-husky	5181cd441d	change pip install url due to server failure (#1667 )	2024-04-01 11:20:14 +08:00
binary-husky	216d4374e7	fix color list overflow	2024-04-01 00:11:32 +08:00
iluem	8af6c0cab6	Qhaoduoyu patch 1: pickle to json to increase security (#1648 ) * Update theme.py fix bugs * Update theme.py fix bugs * change var names --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com>	2024-03-25 09:54:30 +08:00
binary-husky	67ad041372	fix issue #1640	2024-03-20 18:09:37 +08:00
binary-husky	725c72229c	update docker compose	2024-03-20 17:37:03 +08:00
Menghuan1918	e42ede512b	Update Claude3 api request and fix some bugs (#1641 ) * Update version to 3.74 * Add support for Yi Model API (#1635) * 更新以支持零一万物模型 * 删除newbing * 修改config --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * Update claude requrest to http type * Update for endpoint * Add support for other tpyes of pictures * Update pip packages * Fix console_slience issue while error handling * revert version changes --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com>	2024-03-20 17:22:23 +08:00
binary-husky	84ccc9e64c	fix claude + oneapi error	2024-03-17 14:53:28 +08:00
binary-husky	c172847e19	add python annotations for toolbox functions	2024-03-16 22:54:33 +08:00
binary-husky	d166d25eb4	resolve invalid escape sequence warning to support python3.12	2024-03-11 18:10:05 +08:00
binary-husky	516bbb1331	Update README.md	2024-03-11 17:40:16 +08:00
binary-husky	c3140ce344	merge frontier branch (#1620 ) * Zhipu sdk update 适配最新的智谱SDK，支持GLM4v (#1502) * 适配 google gemini 优化为从用户input中提取文件 * 适配最新的智谱SDK、支持glm-4v * requirements.txt fix * pending history check --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * Update "生成多种Mermaid图表" plugin: Separate out the file reading function (#1520) * Update crazy_functional.py with new functionality deal with PDF * Update crazy_functional.py and Mermaid.py for plugin_kwargs * Update crazy_functional.py with new chart type: mind map * Update SELECT_PROMPT and i_say_show_user messages * Update ArgsReminder message in get_crazy_functions() function * Update with read md file and update PROMPTS * Return the PROMPTS as the test found that the initial version worked best * Update Mermaid chart generation function * version 3.71 * 解决issues #1510 * Remove unnecessary text from sys_prompt in 解析历史输入 function * Remove sys_prompt message in 解析历史输入 function * Update bridge_all.py: supports gpt-4-turbo-preview (#1517) * Update bridge_all.py: supports gpt-4-turbo-preview supports gpt-4-turbo-preview * Update bridge_all.py --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * Update config.py: supports gpt-4-turbo-preview (#1516) * Update config.py: supports gpt-4-turbo-preview supports gpt-4-turbo-preview * Update config.py --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * Refactor 解析历史输入 function to handle file input * Update Mermaid chart generation functionality * rename files and functions --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com> Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * 接入mathpix ocr功能 (#1468) * Update Latex输出PDF结果.py 借助mathpix实现了PDF翻译中文并重新编译PDF * Update config.py add mathpix appid & appkey * Add 'PDF翻译中文并重新编译PDF' feature to plugins. --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * fix zhipuai * check picture * remove glm-4 due to bug * 修改config * 检查MATHPIX_APPID * Remove unnecessary code and update function_plugins dictionary * capture non-standard token overflow * bug fix #1524 * change mermaid style * 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽 (#1530) * 支持mermaid 滚动放大缩小重置,鼠标滚动和拖拽 * 微调未果先stage一下 * update --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> * ver 3.72 * change live2d * save the status of ``clear btn` in cookie * 前端选择保持 * js ui bug fix * reset btn bug fix * update live2d tips * fix missing get_token_num method * fix live2d toggle switch * fix persistent custom btn with cookie * fix zhipuai feedback with core functionality * Refactor button update and clean up functions * tailing space removal * Fix missing MATHPIX_APPID and MATHPIX_APPKEY configuration * Prompt fix、脑图提示词优化 (#1537) * 适配 google gemini 优化为从用户input中提取文件 * 脑图提示词优化 * Fix missing MATHPIX_APPID and MATHPIX_APPKEY configuration --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com> * 优化“PDF翻译中文并重新编译PDF”插件 (#1602) * Add gemini_endpoint to API_URL_REDIRECT (#1560) * Add gemini_endpoint to API_URL_REDIRECT * Update gemini-pro and gemini-pro-vision model_info endpoints * Update to support new claude models (#1606) * Add anthropic library and update claude models * 更新bridge_claude.py文件，添加了对图片输入的支持。修复了一些bug。 * 添加Claude_3_Models变量以限制图片数量 * Refactor code to improve readability and maintainability * minor claude bug fix * more flexible one-api support * reformat config * fix one-api new access bug * dummy * compat non-standard api * version 3.73 --------- Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com> Co-authored-by: Menghuan1918 <menghuan2003@outlook.com> Co-authored-by: hongyi-zhao <hongyi.zhao@gmail.com> Co-authored-by: Hao Ma <893017927@qq.com> Co-authored-by: zeyuan huang <599012428@qq.com>	2024-03-11 17:26:09 +08:00
binary-husky	cd18663800	compat non-standard api - 2	2024-03-10 17:13:54 +08:00
binary-husky	dbf1322836	compat non-standard api	2024-03-10 17:07:59 +08:00
XIao	98dd3ae1c0	Moonshot- 在config.py中增加可用模型 (#1603 ) * 支持月之暗面api * fix文案 * 优化noui的返回值，对话历史文件继续上传到moonshat * fix * config 可用模型配置增加 * add `can_multi_thread` model attr (#1598) --------- Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com> Co-authored-by: binary-husky <qingxu.fu@outlook.com>	2024-03-05 16:07:05 +08:00
binary-husky	3036709496	add `can_multi_thread` model attr (#1598 )	2024-03-05 15:58:18 +08:00
XIao	8e9c07644f	支持月之暗面api，文件对话 (#1597 ) * 支持月之暗面api * fix文案	2024-03-03 23:42:17 +08:00