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>

config.py

@@ -45,7 +45,7 @@ AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-p
 #   "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-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
+#   "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"
 # ]
@@ -157,7 +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 = "/"
 
 

main.py

@@ -13,6 +13,17 @@ 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 ['3.32.9']:
@@ -31,18 +42,11 @@ def main():
     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}"
 
-    # 对话记录, python 版本建议3.9+（越新越好）
+    # 对话、日志记录
-    import logging, uuid
+    enable_log(PATH_LOGGING)
-    os.makedirs(PATH_LOGGING, exist_ok=True)
-    chat_secrets_log = os.path.join(PATH_LOGGING, "chat_secrets.log")
-    try:logging.basicConfig(filename=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=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"所有对话记录将自动保存在本地目录 {chat_secrets_log}, 请注意自我隐私保护哦！")
 
     # 一些普通功能模块
     from core_functional import get_core_functions
@@ -75,9 +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, py_pickle_cookie = gr.Textbox(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"):
@@ -199,64 +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],
+                        h = basic_fn_confirm.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
-                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
+                                                   [web_cookie_cache, 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.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)],
+                        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)],
-                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
+                                                   [web_cookie_cache, 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.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):
@@ -376,11 +335,14 @@ def main():
             audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
 
 
-        demo.load(init_cookie, inputs=[cookies], outputs=[cookies])
+        app_block.load(assign_user_uuid, 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)
+        from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
-        demo.load(None, inputs=[], outputs=None, _js=f"""()=>init_frontend_with_cookies("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}")""")    # 配置暗色主题或亮色主题
+        load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
-        demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
+        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():
@@ -397,17 +359,13 @@ def main():
         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
 
+    # 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,
+    # 最后，正式开始服务
-        server_name="0.0.0.0",
+    from shared_utils.fastapi_server import start_app
-        ssl_keyfile=None if SSL_KEYFILE == "" else SSL_KEYFILE,
+    start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SSL_CERTFILE)
-        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","__pycache__","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin", chat_secrets_log])
 
 if __name__ == "__main__":
     main()

request_llms/bridge_all.py

@@ -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):
@@ -64,6 +67,7 @@ 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'
@@ -82,6 +86,7 @@ if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[new
 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")
@@ -310,6 +315,18 @@ model_info = {
         "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
@@ -359,7 +376,7 @@ for model in AVAIL_LLM_MODELS:
 
 # -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
 # claude家族
-claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-sonnet-20240229","claude-3-opus-20240229"]
+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
@@ -393,6 +410,16 @@ if any(item in claude_models for item in AVAIL_LLM_MODELS):
             "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,
@@ -789,7 +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:
@@ -799,9 +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:
@@ -819,7 +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"]
@@ -880,15 +906,22 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
         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
+    完整参数列表：
-    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）
+        predict(
-    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
+            inputs:str,                     # 是本次问询的输入
-    additional_fn代表点击的哪个按钮，按钮见functional.py
+            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")

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

request_llms/bridge_chatgpt.py

@@ -23,6 +23,7 @@ import random
 # 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')
 
@@ -69,7 +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：
@@ -147,7 +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。

request_llms/bridge_claude.py

@@ -13,11 +13,11 @@ import logging
 import os
 import time
 import traceback
-from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path
 import json
 import requests
+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-sonnet-20240229", "claude-3-opus-20240229"]
+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
@@ -116,7 +116,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                 if need_to_pass:
                     pass
                 elif is_last_chunk:
-                    logging.info(f'[response] {result}')
+                    # logging.info(f'[response] {result}')
                     break
                 else:
                     if chunkjson and chunkjson['type'] == 'content_block_delta':
@@ -216,7 +216,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 if need_to_pass:
                     pass
                 elif is_last_chunk:
-                    logging.info(f'[response] {gpt_replying_buffer}')
+                    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':

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
+
+

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')
@@ -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)

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

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

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

request_llms/bridge_moonshot.py

@@ -8,6 +8,7 @@ import time
 import logging
 
 from toolbox import get_conf, update_ui, log_chat
+from toolbox import ChatBotWithCookies
 
 import requests
 
@@ -146,7 +147,8 @@ def msg_handle_error(llm_kwargs, chunk_decoded):
     return error_msg
 
 
-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):
     chatbot.append([inputs, ""])
 
     if additional_fn is not None:

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

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

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

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

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

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)

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
         """

requirements.txt

@@ -17,6 +17,7 @@ prompt_toolkit
 latex2mathml
 python-docx
 mdtex2html
+dashscope
 pyautogen
 colorama
 Markdown

shared_utils/cookie_manager.py

@@ -1 +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
 

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()

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):
@@ -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

tests/test_llms.py

@@ -11,7 +11,29 @@ def validate_path():
 
 
 validate_path()  # validate path so you can run from base directory
-if __name__ == "__main__":
+
+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,
+        }
+
+        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
@@ -20,19 +42,14 @@ if __name__ == "__main__":
         # 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_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
-
         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)
+

themes/common.js

@@ -2,15 +2,15 @@
 //  第 1 部分: 工具函数
 // -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 
-function push_data_to_gradio_component(DAT, ELEM_ID, TYPE){
+function push_data_to_gradio_component(DAT, ELEM_ID, TYPE) {
     // type,               // type==="str" / type==="float"
-    if (TYPE=="str"){
+    if (TYPE == "str") {
         // convert dat to string: do nothing
     }
-    else if (TYPE=="no_conversion"){
+    else if (TYPE == "no_conversion") {
         // no nothing
     }
-    else if (TYPE=="float"){
+    else if (TYPE == "float") {
         // convert dat to float
         DAT = parseFloat(DAT);
     }
@@ -24,7 +24,7 @@ function push_data_to_gradio_component(DAT, ELEM_ID, TYPE){
 }
 
 
-async function get_gradio_component(ELEM_ID){
+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', {
@@ -41,14 +41,13 @@ async function get_gradio_component(ELEM_ID){
 }
 
 
-async function get_data_from_gradio_component(ELEM_ID){
+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) {
-    //   let p = ["基础功能区", "输入清除键", "函数插件区"];
 
+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"]
@@ -85,6 +84,7 @@ function gradioApp() {
     return elem.shadowRoot ? elem.shadowRoot : elem;
 }
 
+
 function setCookie(name, value, days) {
     var expires = "";
 
@@ -97,6 +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(';');
@@ -112,6 +113,7 @@ function getCookie(name) {
     return null;
 }
 
+
 let toastCount = 0;
 function toast_push(msg, duration) {
     duration = isNaN(duration) ? 3000 : duration;
@@ -134,6 +136,7 @@ function toast_push(msg, duration) {
     toastCount++;
 }
 
+
 function toast_up(msg) {
     var m = document.getElementById('toast_up');
     if (m) {
@@ -146,6 +149,7 @@ function toast_up(msg) {
     document.body.appendChild(m);
 }
 
+
 function toast_down() {
     var m = document.getElementById('toast_up');
     if (m) {
@@ -153,6 +157,7 @@ function toast_down() {
     }
 }
 
+
 function begin_loading_status() {
     // Create the loader div and add styling
     var loader = document.createElement('div');
@@ -327,6 +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++) {
@@ -343,7 +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() {
@@ -375,6 +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
@@ -394,6 +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) {
@@ -491,6 +498,7 @@ async function upload_files(files) {
     }
 }
 
+
 function register_func_paste(input) {
     let paste_files = [];
     if (input) {
@@ -517,6 +525,7 @@ function register_func_paste(input) {
     }
 }
 
+
 function register_func_drag(elem) {
     if (elem) {
         const dragEvents = ["dragover"];
@@ -553,6 +562,7 @@ function register_func_drag(elem) {
     }
 }
 
+
 function elem_upload_component_pop_message(elem) {
     if (elem) {
         const dragEvents = ["dragover"];
@@ -582,6 +592,7 @@ function elem_upload_component_pop_message(elem) {
     }
 }
 
+
 function register_upload_event() {
     locate_upload_elems();
     if (elem_upload_float) {
@@ -604,6 +615,7 @@ function register_upload_event() {
     }
 }
 
+
 function monitoring_input_box() {
     register_upload_event();
 
@@ -637,7 +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) {
@@ -674,6 +685,7 @@ function audio_fn_init() {
     }
 }
 
+
 function minor_ui_adjustment() {
     let cbsc_area = document.getElementById('cbsc');
     cbsc_area.style.paddingTop = '15px';
@@ -766,21 +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');
@@ -817,7 +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
@@ -831,62 +829,24 @@ 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
-            }
-        });
-    });
-
-    if (!set_success){
-        console.log("设置checkbox失败，没有找到对应的key")
-    }
-}
 
 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
+    save_value = "",      // save value
     load_type = "str",  // type==="str" / type==="float"
-        load_default=false, // load default value
+    load_default = false, // load default value
-        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{
+        else {
-            if (load_default){
+            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);
             }
@@ -897,11 +857,24 @@ function gpt_academic_gradio_saveload(
     }
 }
 
-async function init_frontend_with_cookies(dark, prompt, live2d) {
-    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")
     }
@@ -916,12 +889,13 @@ async function init_frontend_with_cookies(dark, prompt, live2d) {
         }
     }
 
-    ////////////////////// SysPrompt ///////////////////////////
+    // SysPrompt 系统静默提示词
     gpt_academic_gradio_saveload("load", "elem_prompt", "js_system_prompt_cookie", null, "str");
-    ////////////////////// Temperature ///////////////////////////
+
+    // Temperature 大模型温度参数
     gpt_academic_gradio_saveload("load", "elem_temperature", "js_temperature_cookie", null, "float");
 
-    ////////////////////// clearButton ///////////////////////////
+    // clearButton 自动清除按钮
     if (getCookie("js_clearbtn_show_cookie")) {
         // have cookie
         bool_value = getCookie("js_clearbtn_show_cookie")
@@ -949,7 +923,7 @@ async function init_frontend_with_cookies(dark, prompt, live2d) {
         }
     }
 
-    ////////////////////// live2d ///////////////////////////
+    // live2d 显示
     if (getCookie("js_live2d_show_cookie")) {
         // have cookie
         searchString = "添加Live2D形象";

themes/theme.py

@@ -48,7 +48,7 @@ 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
@@ -106,8 +106,8 @@ js_code_for_toggle_darkmode = """() => {
 }"""
 
 
-js_code_for_persistent_cookie_init = """(py_pickle_cookie, cookie) => {
+js_code_for_persistent_cookie_init = """(web_cookie_cache, cookie) => {
-    return [getCookie("py_pickle_cookie"), cookie];
+    return [getCookie("web_cookie_cache"), cookie];
 }
 """
 

toolbox.py

@@ -535,17 +535,13 @@ def on_file_uploaded(
 
 
 def on_report_generated(cookies:dict, files:List[str], chatbot:ChatBotWithCookies):
-    # from toolbox import find_recent_files
-    # PATH_LOGGING = get_conf('PATH_LOGGING')
     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 += (
@@ -1009,6 +1005,7 @@ def check_repeat_upload(new_pdf_path, pdf_hash):
     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}")
@@ -1016,3 +1013,5 @@ def log_chat(llm_model: str, input_str: str, output_str: str):
             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())

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.73,
+  "version": 3.74,
   "show_feature": true,
-  "new_feature": "优化oneapi接入方法 <-> 接入月之暗面模型 <-> 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）"
+  "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）"
 }