renew pip url

configuration

README.md

@@ -1,8 +1,20 @@
-> [!IMPORTANT]  
+---
-> 2024.1.18: 更新3.70版本，支持Mermaid绘图库（让大模型绘制脑图）  
+title: GPT-Academic
-> 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！  
+emoji: 😻
-> 2024.1.17: 某些依赖包尚不兼容python 3.12，推荐python 3.11。  
+colorFrom: blue
-> 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。
+colorTo: blue
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+---
+
+# ChatGPT 学术优化
+> **Note**
+> 
+> 2023.11.12: 某些依赖包尚不兼容python 3.12，推荐python 3.11。
+> 
+> 2023.12.26: 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>
 

app.py

@@ -14,23 +14,25 @@ help_menu_description = \
 </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 main():
+    import subprocess, sys
+    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'https://public.agent-matrix.com/publish/gradio-3.32.8-py3-none-any.whl'])
     import gradio as gr
-    if gr.__version__ not in ['3.32.6', '3.32.7', '3.32.8']:
+    if gr.__version__ not in ['3.32.8']:
         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
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
     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 = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME')
+    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')
 
     # 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
+    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_darkmode_init, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
+    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
     title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
 
@@ -65,7 +67,7 @@ def main():
     proxy_info = check_proxy(proxies)
 
     gr_L1 = lambda: gr.Row().style()
-    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id)
+    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id, min_width=400)
     if LAYOUT == "TOP-DOWN":
         gr_L1 = lambda: DummyWith()
         gr_L2 = lambda scale, elem_id: gr.Row()
@@ -76,7 +78,8 @@ def main():
     predefined_btns = {}
     with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
         gr.HTML(title_html)
-        secret_css, dark_mode, persistent_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
+        gr.HTML('''<center><a href="https://huggingface.co/spaces/qingxu98/gpt-academic?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>请您打开此页面后务必点击上方的“复制空间”（Duplicate Space）按钮！<font color="#FF00FF">使用时，先在输入框填入API-KEY然后回车。</font><br/>切忌在“复制空间”（Duplicate Space）之前填入API_KEY或进行提问，否则您的API_KEY将极可能被空间所有者攫取！<br/>支持任意数量的OpenAI的密钥和API2D的密钥共存，例如输入"OpenAI密钥1,API2D密钥2"，然后提交，即可同时使用两种模型接口。</center>''')
+        secret_css, dark_mode, py_pickle_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
         cookies = gr.State(load_chat_cookies())
         with gr_L1():
             with gr_L2(scale=2, elem_id="gpt-chat"):
@@ -86,7 +89,7 @@ def main():
             with gr_L2(scale=1, elem_id="gpt-panel"):
                 with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
                     with gr.Row():
-                        txt = gr.Textbox(show_label=False, placeholder="Input question here.", elem_id='user_input_main').style(container=False)
+                        txt = gr.Textbox(show_label=False, lines=2, placeholder="输入问题或API密钥，输入多个密钥时，用英文逗号间隔。支持多个OpenAI密钥共存。").style(container=False)
                     with gr.Row():
                         submitBtn = gr.Button("提交", elem_id="elem_submit", variant="primary")
                     with gr.Row():
@@ -98,6 +101,7 @@ def main():
                             audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False)
                     with gr.Row():
                         status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
+
                 with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
                     with gr.Row():
                         for k in range(NUM_CUSTOM_BASIC_BTN):
@@ -142,7 +146,6 @@ def main():
                         with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
                             file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
 
-
         with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
             with gr.Row():
                 with gr.Tab("上传文件", elem_id="interact-panel"):
@@ -158,10 +161,11 @@ def main():
 
                 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)
-                    checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"],
+                    checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
-                                                  value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
+                    opt = ["自定义菜单"]
-                    checkboxes_2 = gr.CheckboxGroup(["自定义菜单"],
+                    value=[]
-                                                  value=[], label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
+                    if ADD_WAIFU: opt += ["添加Live2D形象"]; value += ["添加Live2D形象"]
+                    checkboxes_2 = gr.CheckboxGroup(opt, value=value, label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
                     dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
                     dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
                 with gr.Tab("帮助", elem_id="interact-panel"):
@@ -178,7 +182,7 @@ def main():
                         submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm")
                         resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
                         stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
-                        clearBtn2 = gr.Button("清除", variant="secondary", visible=False); clearBtn2.style(size="sm")
+                        clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
 
 
         with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
@@ -192,10 +196,12 @@ def main():
                         basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False)
                     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_load    = gr.Button("加载已保存", variant="primary"); basic_fn_load.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):
+                        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_:
                                     {
@@ -205,20 +211,34 @@ def main():
                                     }
                                 }
                             )
-                            cookies_.update(customize_fn_overwrite_)
+                            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:
-                                ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
+                                # 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:
-                                ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
+                                # 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({persistent_cookie: persistent_cookie_})             # write persistent cookie
+                            ret.update({py_pickle_cookie: persistent_cookie_})             # write persistent cookie
                             return ret
 
-                        def reflesh_btn(persistent_cookie_, cookies_):
+                        # 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);}""")
+                        # 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);}""")
+
+                        def persistent_cookie_reload(persistent_cookie_, cookies_):
                             ret = {}
                             for k in customize_btns:
                                 ret.update({customize_btns[k]: gr.update(visible=False, value="")})
@@ -236,25 +256,16 @@ def main():
                                 else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
                             return ret
 
-                        basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies], [cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h = basic_fn_confirm.click(assign_btn, [persistent_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
-                                                   [persistent_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        # save persistent cookie
-                        h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""")
-
         # 功能区显示开关与功能区的互动
         def fn_area_visibility(a):
             ret = {}
-            ret.update({area_basic_fn: gr.update(visible=("基础功能区" in a))})
-            ret.update({area_crazy_fn: gr.update(visible=("函数插件区" in a))})
             ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))})
             ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))})
-            ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
-            ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
             ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
             if "浮动输入区" in a: ret.update({txt: gr.update(value="")})
             return ret
-        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
+        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, plugin_advanced_arg] )
+        checkboxes.select(None, [checkboxes], None, _js=js_code_show_or_hide)
 
         # 功能区显示开关与功能区的互动
         def fn_area_visibility_2(a):
@@ -262,6 +273,7 @@ def main():
             ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
             return ret
         checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
+        checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
 
         # 整理反复出现的控件句柄组合
         input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
@@ -272,15 +284,17 @@ def main():
         cancel_handles.append(txt2.submit(**predict_args))
         cancel_handles.append(submitBtn.click(**predict_args))
         cancel_handles.append(submitBtn2.click(**predict_args))
-        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
+        resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset)   # 先在前端快速清除chatbot&status
-        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
+        resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset)  # 先在前端快速清除chatbot&status
-        clearBtn.click(lambda: ("",""), None, [txt, txt2])
+        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])    # 再在后端清除history
-        clearBtn2.click(lambda: ("",""), None, [txt, txt2])
+        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])   # 再在后端清除history
+        clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
+        clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
         if AUTO_CLEAR_TXT:
-            submitBtn.click(lambda: ("",""), None, [txt, txt2])
+            submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
-            submitBtn2.click(lambda: ("",""), None, [txt, txt2])
+            submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
-            txt.submit(lambda: ("",""), None, [txt, txt2])
+            txt.submit(None, None, [txt, txt2], _js=js_code_clear)
-            txt2.submit(lambda: ("",""), None, [txt, txt2])
+            txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
@@ -360,10 +374,10 @@ def main():
             audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
 
 
-        demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
+        demo.load(init_cookie, inputs=[cookies], outputs=[cookies])
-        darkmode_js = js_code_for_darkmode_init
+        demo.load(persistent_cookie_reload, inputs = [py_pickle_cookie, cookies],
-        demo.load(None, inputs=None, outputs=[persistent_cookie], _js=js_code_for_persistent_cookie_init)
+            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=darkmode_js)    # 配置暗色主题或亮色主题
+        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);}')
 
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
@@ -382,16 +396,8 @@ def main():
         threading.Thread(target=warm_up_mods, name="warm-up", daemon=True).start()      # 预热tiktoken模块
 
     run_delayed_tasks()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
+    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png", blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
-        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')

config.py

@@ -2,8 +2,8 @@
     以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
     读取优先级：环境变量 > config_private.py > config.py
     --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
-    All the following configurations also support using environment variables to override, 
+    All the following configurations also support using environment variables to override,
-    and the environment variable configuration format can be seen in docker-compose.yml. 
+    and the environment variable configuration format can be seen in docker-compose.yml.
     Configuration reading priority: environment variable > config_private.py > config.py
 """
 
@@ -11,6 +11,10 @@
 API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
 
 
+# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
+
+
 # [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改；如果使用本地或无地域限制的大模型时，此处也不需要修改
 USE_PROXY = False
 if USE_PROXY:
@@ -33,7 +37,7 @@ else:
 # ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
 
 # 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"} 
+# 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"}
 # 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
 API_URL_REDIRECT = {}
 
@@ -45,7 +49,7 @@ DEFAULT_WORKER_NUM = 3
 
 # 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
 # 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
-THEME = "Default"
+THEME = "Chuanhu-Small-and-Beautiful"
 AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
 
 
@@ -66,7 +70,7 @@ LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下
 
 
 # 暗色模式 / 亮色模式
-DARK_MODE = True        
+DARK_MODE = False
 
 
 # 发送请求到OpenAI后，等待多久判定为超时
@@ -80,6 +84,9 @@ WEB_PORT = -1
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
+# OpenAI模型选择是（gpt4现在只对申请成功的人开放）
+LLM_MODEL = "gpt-3.5-turbo" # 可选 "chatglm"
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo", "spark", "azure-gpt-3.5"]
 
 # 插件分类默认选项
 DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
@@ -89,11 +96,11 @@ DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
 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", "api2d-gpt-4",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-3-turbo",
-                    "gemini-pro", "chatglm3", "claude-2", "zhipuai"]
+                    "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", 
+# "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"
 # ]
@@ -136,7 +143,7 @@ AUTO_CLEAR_TXT = False
 
 
 # 加一个live2d装饰
-ADD_WAIFU = False
+ADD_WAIFU = True
 
 
 # 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
@@ -158,7 +165,7 @@ API_ORG = ""
 
 
 # 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
-SLACK_CLAUDE_BOT_ID = ''   
+SLACK_CLAUDE_BOT_ID = ''
 SLACK_CLAUDE_USER_TOKEN = ''
 
 
@@ -195,7 +202,7 @@ XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
 
 # 接入智谱大模型
 ZHIPUAI_API_KEY = ""
-ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4"
+ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
 
 
 # # 火山引擎YUNQUE大模型
@@ -208,6 +215,11 @@ ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4"
 ANTHROPIC_API_KEY = ""
 
 
+# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
+MATHPIX_APPID = ""
+MATHPIX_APPKEY = ""
+
+
 # 自定义API KEY格式
 CUSTOM_API_KEY_PATTERN = ""
 
@@ -224,8 +236,8 @@ HUGGINGFACE_ACCESS_TOKEN = "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"
 # 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
 GROBID_URLS = [
     "https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
-    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space", 
+    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
-    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space", 
+    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
 ]
 
 
@@ -246,7 +258,7 @@ PATH_LOGGING = "gpt_log"
 
 
 # 除了连接OpenAI之外，还有哪些场合允许使用代理，请勿修改
-WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid", 
+WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
                      "Warmup_Modules", "Nougat_Download", "AutoGen"]
 
 
@@ -297,9 +309,8 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   ├── BAIDU_CLOUD_API_KEY
 │   └── BAIDU_CLOUD_SECRET_KEY
 │
-├── "zhipuai" 智谱AI大模型chatglm_turbo
+├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
-│   ├── ZHIPUAI_API_KEY
+│   └── ZHIPUAI_API_KEY
-│   └── ZHIPUAI_MODEL
 │
 ├── "qwen-turbo" 等通义千问大模型
 │   └──  DASHSCOPE_API_KEY
@@ -311,7 +322,7 @@ NUM_CUSTOM_BASIC_BTN = 4
     ├── NEWBING_STYLE
     └── NEWBING_COOKIES
 
-    
+
 本地大模型示意图
 │
 ├── "chatglm3"
@@ -351,6 +362,9 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   └── ALIYUN_SECRET
 │
 └── PDF文档精准解析
-    └── GROBID_URLS
+    ├── GROBID_URLS
+    ├── MATHPIX_APPID
+    └── MATHPIX_APPKEY
+
 
 """

crazy_functional.py

@@ -70,11 +70,11 @@ def get_crazy_functions():
             "Info": "清除所有缓存文件，谨慎操作 | 不需要输入参数",
             "Function": HotReload(清除缓存),
         },
-        "生成多种Mermaid图表(从当前对话或文件(.pdf/.md)中生产图表）": {
+        "生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表）": {
             "Group": "对话",
             "Color": "stop",
             "AsButton": False,
-            "Info" : "基于当前对话或PDF生成多种Mermaid图表,图表类型由模型判断",
+            "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
             "Function": HotReload(生成多种Mermaid图表),
             "AdvancedArgs": True,
             "ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
@@ -532,8 +532,9 @@ def get_crazy_functions():
         print("Load function plugin failed")
 
     try:
-        from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
+        from crazy_functions.Latex输出PDF import Latex英文纠错加PDF对比
-        from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
+        from crazy_functions.Latex输出PDF import Latex翻译中文并重新编译PDF
+        from crazy_functions.Latex输出PDF import PDF翻译中文并重新编译PDF
 
         function_plugins.update(
             {
@@ -550,9 +551,9 @@ def get_crazy_functions():
                     "Color": "stop",
                     "AsButton": False,
                     "AdvancedArgs": True,
-                    "ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
-                    + "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
-                    + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
                     "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
                     "Function": HotReload(Latex翻译中文并重新编译PDF),
                 },
@@ -561,11 +562,22 @@ def get_crazy_functions():
                     "Color": "stop",
                     "AsButton": False,
                     "AdvancedArgs": True,
-                    "ArgsReminder": "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
-                    + "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
-                    + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
                     "Info": "本地Latex论文精细翻译 | 输入参数是路径",
                     "Function": HotReload(Latex翻译中文并重新编译PDF),
+                },
+                "PDF翻译中文并重新编译PDF（上传PDF）[需Latex]": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "Info": "PDF翻译中文，并重新编译PDF | 输入参数为路径",
+                    "Function": HotReload(PDF翻译中文并重新编译PDF)
                 }
             }
         )

crazy_functions/CodeInterpreter.py

@@ -1,232 +0,0 @@
-from collections.abc import Callable, Iterable, Mapping
-from typing import Any
-from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc
-from toolbox import promote_file_to_downloadzone, get_log_folder
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping, try_install_deps
-from multiprocessing import Process, Pipe
-import os
-import time
-
-templete = """
-```python
-import ...  # Put dependencies here, e.g. import numpy as np
-
-class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
-
-    def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
-        # rewrite the function you have just written here 
-        ...
-        return generated_file_path
-```
-"""
-
-def inspect_dependency(chatbot, history):
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    return True
-
-def get_code_block(reply):
-    import re
-    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
-    matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
-        return matches[0].strip('python') #  code block
-    for match in matches:
-        if 'class TerminalFunction' in match:
-            return match.strip('python') #  code block
-    raise RuntimeError("GPT is not generating proper code.")
-
-def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
-    # 输入
-    prompt_compose = [
-        f'Your job:\n'
-        f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
-        f"2. You should write this function to perform following task: " + txt + "\n",
-        f"3. Wrap the output python function with markdown codeblock."
-    ]
-    i_say = "".join(prompt_compose)
-    demo = []
-
-    # 第一步
-    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=i_say, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo, 
-        sys_prompt= r"You are a programmer."
-    )
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-
-    # 第二步
-    prompt_compose = [
-        "If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
-        templete
-    ]
-    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
-    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=inputs_show_user, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-        sys_prompt= r"You are a programmer."
-    )
-    code_to_return = gpt_say
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
-    # # 第三步
-    # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
-    # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
-    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=inputs_show_user, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-    #     sys_prompt= r"You are a programmer."
-    # )
-    # # # 第三步  
-    # i_say = "Show me how to use `pip` to install packages to run the code above. "
-    # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
-    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=i_say, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-    #     sys_prompt= r"You are a programmer."
-    # )
-    installation_advance = ""
-    
-    return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
-
-def make_module(code):
-    module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
-    with open(f'{get_log_folder()}/{module_file}.py', 'w', encoding='utf8') as f:
-        f.write(code)
-
-    def get_class_name(class_string):
-        import re
-        # Use regex to extract the class name
-        class_name = re.search(r'class (\w+)\(', class_string).group(1)
-        return class_name
-
-    class_name = get_class_name(code)
-    return f"{get_log_folder().replace('/', '.')}.{module_file}->{class_name}"
-
-def init_module_instance(module):
-    import importlib
-    module_, class_ = module.split('->')
-    init_f = getattr(importlib.import_module(module_), class_)
-    return init_f()
-
-def for_immediate_show_off_when_possible(file_type, fp, chatbot):
-    if file_type in ['png', 'jpg']:
-        image_path = os.path.abspath(fp)
-        chatbot.append(['这是一张图片, 展示如下:',  
-            f'本地文件地址: <br/>`{image_path}`<br/>'+
-            f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
-        ])
-    return chatbot
-
-def subprocess_worker(instance, file_path, return_dict):
-    return_dict['result'] = instance.run(file_path)
-
-def have_any_recent_upload_files(chatbot):
-    _5min = 5 * 60
-    if not chatbot: 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
-    if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
-    else: return False  # most_recent_uploaded is too old
-
-def get_recent_file_prompt_support(chatbot):
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
-    path = most_recent_uploaded['path']
-    return path
-
-@CatchException
-def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，暂时没有用武之地
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    user_request    当前用户的请求信息（IP地址等）
-    """
-    raise NotImplementedError
-
-    # 清空历史，以免输入溢出
-    history = []; clear_file_downloadzone(chatbot)
-
-    # 基本信息：功能、贡献者
-    chatbot.append([
-        "函数插件功能？",
-        "CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 插件初始化中 ..."
-    ])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    if have_any_recent_upload_files(chatbot):
-        file_path = get_recent_file_prompt_support(chatbot)
-    else:
-        chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 读取文件
-    if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
-    recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
-    file_path = recently_uploaded_files[-1]
-    file_type = file_path.split('.')[-1]
-
-    # 粗心检查
-    if is_the_upload_folder(txt):
-        chatbot.append([
-            "...",
-            f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
-        ])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    # 开始干正事
-    for j in range(5):  # 最多重试5次
-        try:
-            code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
-                yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
-            code = get_code_block(code)
-            res = make_module(code)
-            instance = init_module_instance(res)
-            break
-        except Exception as e:
-            chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 代码生成结束, 开始执行
-    try:
-        import multiprocessing
-        manager = multiprocessing.Manager()
-        return_dict = manager.dict()
-
-        p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
-        # only has 10 seconds to run
-        p.start(); p.join(timeout=10)
-        if p.is_alive(): p.terminate(); p.join()
-        p.close()
-        res = return_dict['result']
-        # res = instance.run(file_path)
-    except Exception as e:
-        chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-        # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 顺利完成，收尾
-    res = str(res)
-    if os.path.exists(res):
-        chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
-        new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
-        chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    else:
-        chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新   
-
-"""
-测试：
-    裁剪图像，保留下半部分
-    交换图像的蓝色通道和红色通道
-    将图像转为灰度图像
-    将csv文件转excel表格
-"""

crazy_functions/Latex输出PDF.py

@@ -0,0 +1,484 @@
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
+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
+
+pj = os.path.join
+ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
+def switch_prompt(pfg, mode, more_requirement):
+    """
+    Generate prompts and system prompts based on the mode for proofreading or translating.
+    Args:
+    - pfg: Proofreader or Translator instance.
+    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
+
+    Returns:
+    - inputs_array: A list of strings containing prompts for users to respond to.
+    - sys_prompt_array: A list of strings containing prompts for system prompts.
+    """
+    n_split = len(pfg.sp_file_contents)
+    if mode == 'proofread_en':
+        inputs_array = [r"Below is a section from an academic paper, proofread this section." +
+                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
+                        r"Answer me only with the revised text:" +
+                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
+    elif mode == 'translate_zh':
+        inputs_array = [
+            r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
+            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
+            r"Answer me only with the translated text:" +
+            f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
+    else:
+        assert False, "未知指令"
+    return inputs_array, sys_prompt_array
+
+
+def desend_to_extracted_folder_if_exist(project_folder):
+    """ 
+    Descend into the extracted folder if it exists, otherwise return the original folder.
+
+    Args:
+    - project_folder: A string specifying the folder path.
+
+    Returns:
+    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
+    """
+    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
+    if len(maybe_dir) == 0: return project_folder
+    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
+    return project_folder
+
+
+def move_project(project_folder, arxiv_id=None):
+    """ 
+    Create a new work folder and copy the project folder to it.
+
+    Args:
+    - project_folder: A string specifying the folder path of the project.
+
+    Returns:
+    - A string specifying the path to the new work folder.
+    """
+    import shutil, time
+    time.sleep(2)  # avoid time string conflict
+    if arxiv_id is not None:
+        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
+    else:
+        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
+    try:
+        shutil.rmtree(new_workfolder)
+    except:
+        pass
+
+    # align subfolder if there is a folder wrapper
+    items = glob.glob(pj(project_folder, '*'))
+    items = [item for item in items if os.path.basename(item) != '__MACOSX']
+    if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
+        if os.path.isdir(items[0]): project_folder = items[0]
+
+    shutil.copytree(src=project_folder, dst=new_workfolder)
+    return new_workfolder
+
+
+def arxiv_download(chatbot, history, txt, allow_cache=True):
+    def check_cached_translation_pdf(arxiv_id):
+        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
+        if not os.path.exists(translation_dir):
+            os.makedirs(translation_dir)
+        target_file = pj(translation_dir, 'translate_zh.pdf')
+        if os.path.exists(target_file):
+            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
+            target_file_compare = pj(translation_dir, 'comparison.pdf')
+            if os.path.exists(target_file_compare):
+                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
+            return target_file
+        return False
+
+    def is_float(s):
+        try:
+            float(s)
+            return True
+        except ValueError:
+            return False
+
+    if ('.' in txt) and ('/' not in txt) and is_float(txt):  # is arxiv ID
+        txt = 'https://arxiv.org/abs/' + txt.strip()
+    if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]):  # is arxiv ID
+        txt = 'https://arxiv.org/abs/' + txt[:10]
+
+    if not txt.startswith('https://arxiv.org'): 
+        return txt, None    # 是本地文件，跳过下载
+    
+    # <-------------- inspect format ------------->
+    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
+    yield from update_ui(chatbot=chatbot, history=history)
+    time.sleep(1)  # 刷新界面
+
+    url_ = txt  # https://arxiv.org/abs/1707.06690
+    if not txt.startswith('https://arxiv.org/abs/'):
+        msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
+        yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history)  # 刷新界面
+        return msg, None
+    # <-------------- set format ------------->
+    arxiv_id = url_.split('/abs/')[-1]
+    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
+    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
+    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
+
+    url_tar = url_.replace('/abs/', '/e-print/')
+    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
+    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
+    os.makedirs(translation_dir, exist_ok=True)
+
+    # <-------------- download arxiv source file ------------->
+    dst = pj(translation_dir, arxiv_id + '.tar')
+    if os.path.exists(dst):
+        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
+    else:
+        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
+        proxies = get_conf('proxies')
+        r = requests.get(url_tar, proxies=proxies)
+        with open(dst, 'wb+') as f:
+            f.write(r.content)
+    # <-------------- extract file ------------->
+    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
+    from toolbox import extract_archive
+    extract_archive(file_path=dst, dest_dir=extract_dst)
+    return extract_dst, arxiv_id
+
+
+def pdf2tex_project(pdf_file_path):
+    # Mathpix API credentials
+    app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+    headers = {"app_id": app_id, "app_key": app_key}
+
+    # Step 1: Send PDF file for processing
+    options = {
+        "conversion_formats": {"tex.zip": True},
+        "math_inline_delimiters": ["$", "$"],
+        "rm_spaces": True
+    }
+
+    response = requests.post(url="https://api.mathpix.com/v3/pdf",
+                             headers=headers,
+                             data={"options_json": json.dumps(options)},
+                             files={"file": open(pdf_file_path, "rb")})
+
+    if response.ok:
+        pdf_id = response.json()["pdf_id"]
+        print(f"PDF processing initiated. PDF ID: {pdf_id}")
+
+        # Step 2: Check processing status
+        while True:
+            conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
+            conversion_data = conversion_response.json()
+
+            if conversion_data["status"] == "completed":
+                print("PDF processing completed.")
+                break
+            elif conversion_data["status"] == "error":
+                print("Error occurred during processing.")
+            else:
+                print(f"Processing status: {conversion_data['status']}")
+                time.sleep(5)  # wait for a few seconds before checking again
+
+        # Step 3: Save results to local files
+        output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+
+        url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
+        response = requests.get(url, headers=headers)
+        file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
+        output_name = f"{file_name_wo_dot}.tex.zip"
+        output_path = os.path.join(output_dir, output_name)
+        with open(output_path, "wb") as output_file:
+            output_file.write(response.content)
+        print(f"tex.zip file saved at: {output_path}")
+
+        import zipfile
+        unzip_dir = os.path.join(output_dir, file_name_wo_dot)
+        with zipfile.ZipFile(output_path, 'r') as zip_ref:
+            zip_ref.extractall(unzip_dir)
+
+        return unzip_dir
+
+    else:
+        print(f"Error sending PDF for processing. Status code: {response.status_code}")
+        return None
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
+
+
+@CatchException
+def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    # <-------------- information about this plugin ------------->
+    chatbot.append(["函数插件功能？",
+                    "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+    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, arxiv_id=None)
+
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
+        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                       chatbot, history, system_prompt, mode='proofread_en',
+                                       switch_prompt=_switch_prompt_)
+
+    # <-------------- compile PDF ------------->
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                   main_file_modified='merge_proofread_en',
+                                   work_folder_original=project_folder, work_folder_modified=project_folder,
+                                   work_folder=project_folder)
+
+    # <-------------- 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, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <-------------- we are done ------------->
+    return success
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
+
+@CatchException
+def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    # <-------------- information about this plugin ------------->
+    chatbot.append([
+        "函数插件功能？",
+        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    try:
+        txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
+    except tarfile.ReadError as e:
+        yield from update_ui_lastest_msg(
+            "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。", 
+            chatbot=chatbot, history=history)
+        return
+
+    if txt.endswith('.pdf'):
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+    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, arxiv_id)
+
+    # <-------------- 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 ------------->
+    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
+
+
+#  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=   
+
+@CatchException
+def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # <-------------- information about this plugin ------------->
+    chatbot.append([
+        "函数插件功能？",
+        "将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', 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.pdf文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    if len(file_manifest) != 1:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+    if len(app_id) == 0 or len(app_key) == 0:
+        report_exception(chatbot, history, a="缺失 MATHPIX_APPID 和 MATHPIX_APPKEY。", b=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- convert pdf into tex ------------->
+    project_folder = pdf2tex_project(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
+
+    # <-------------- 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)
+
+    # <-------------- 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 ------------->
+    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

crazy_functions/Latex输出PDF结果.py

@@ -1,313 +0,0 @@
-from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
-from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
-from functools import partial
-import glob, os, requests, time, tarfile
-pj = os.path.join
-ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
-
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
-# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
-def switch_prompt(pfg, mode, more_requirement):
-    """
-    Generate prompts and system prompts based on the mode for proofreading or translating.
-    Args:
-    - pfg: Proofreader or Translator instance.
-    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
-
-    Returns:
-    - inputs_array: A list of strings containing prompts for users to respond to.
-    - sys_prompt_array: A list of strings containing prompts for system prompts.
-    """
-    n_split = len(pfg.sp_file_contents)
-    if mode == 'proofread_en':
-        inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
-                        r"Answer me only with the revised text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
-    elif mode == 'translate_zh':
-        inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
-                        r"Answer me only with the translated text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
-    else:
-        assert False, "未知指令"
-    return inputs_array, sys_prompt_array
-
-def desend_to_extracted_folder_if_exist(project_folder):
-    """ 
-    Descend into the extracted folder if it exists, otherwise return the original folder.
-
-    Args:
-    - project_folder: A string specifying the folder path.
-
-    Returns:
-    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
-    """
-    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
-    if len(maybe_dir) == 0: return project_folder
-    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
-    return project_folder
-
-def move_project(project_folder, arxiv_id=None):
-    """ 
-    Create a new work folder and copy the project folder to it.
-
-    Args:
-    - project_folder: A string specifying the folder path of the project.
-
-    Returns:
-    - A string specifying the path to the new work folder.
-    """
-    import shutil, time
-    time.sleep(2)   # avoid time string conflict
-    if arxiv_id is not None:
-        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
-    else:
-        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
-    try:
-        shutil.rmtree(new_workfolder)
-    except:
-        pass
-
-    # align subfolder if there is a folder wrapper
-    items = glob.glob(pj(project_folder,'*'))
-    items = [item for item in items if os.path.basename(item)!='__MACOSX']
-    if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
-        if os.path.isdir(items[0]): project_folder = items[0]
-
-    shutil.copytree(src=project_folder, dst=new_workfolder)
-    return new_workfolder
-
-def arxiv_download(chatbot, history, txt, allow_cache=True):
-    def check_cached_translation_pdf(arxiv_id):
-        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
-        if not os.path.exists(translation_dir):
-            os.makedirs(translation_dir)
-        target_file = pj(translation_dir, 'translate_zh.pdf')
-        if os.path.exists(target_file):
-            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
-            target_file_compare = pj(translation_dir, 'comparison.pdf')
-            if os.path.exists(target_file_compare):
-                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
-            return target_file
-        return False
-    def is_float(s):
-        try:
-            float(s)
-            return True
-        except ValueError:
-            return False
-    if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
-        txt = 'https://arxiv.org/abs/' + txt.strip()
-    if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
-        txt = 'https://arxiv.org/abs/' + txt[:10]
-    if not txt.startswith('https://arxiv.org'): 
-        return txt, None    # 是本地文件，跳过下载
-    
-    # <-------------- inspect format ------------->
-    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...']) 
-    yield from update_ui(chatbot=chatbot, history=history)
-    time.sleep(1) # 刷新界面
-
-    url_ = txt   # https://arxiv.org/abs/1707.06690
-    if not txt.startswith('https://arxiv.org/abs/'): 
-        msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
-        yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
-        return msg, None
-    # <-------------- set format ------------->
-    arxiv_id = url_.split('/abs/')[-1]
-    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
-    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
-    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
-
-    url_tar = url_.replace('/abs/', '/e-print/')
-    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
-    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
-    os.makedirs(translation_dir, exist_ok=True)
-    
-    # <-------------- download arxiv source file ------------->
-    dst = pj(translation_dir, arxiv_id+'.tar')
-    if os.path.exists(dst):
-        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
-    else:
-        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
-        proxies = get_conf('proxies')
-        r = requests.get(url_tar, proxies=proxies)
-        with open(dst, 'wb+') as f:
-            f.write(r.content)
-    # <-------------- extract file ------------->
-    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
-    from toolbox import extract_archive
-    extract_archive(file_path=dst, dest_dir=extract_dst)
-    return extract_dst, arxiv_id
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
-
-
-@CatchException
-def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    # <-------------- information about this plugin ------------->
-    chatbot.append([ "函数插件功能？",
-        "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
-    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, arxiv_id=None)
-
-
-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
-        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
-
-
-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en', 
-                             work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
-    
-
-    # <-------------- 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, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-    # <-------------- we are done ------------->
-    return success
-
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
-
-@CatchException
-def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    # <-------------- information about this plugin ------------->
-    chatbot.append([
-        "函数插件功能？",
-        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    no_cache = more_req.startswith("--no-cache")
-    if no_cache: more_req.lstrip("--no-cache")
-    allow_cache = not no_cache
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    try:
-        txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
-    except tarfile.ReadError as e:
-        yield from update_ui_lastest_msg(
-            "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。", 
-            chatbot=chatbot, history=history)
-        return
-
-    if txt.endswith('.pdf'):
-        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无法处理: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
-    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, arxiv_id)
-
-
-    # <-------------- 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 ------------->
-    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

crazy_functions/crazy_utils.py

@@ -12,7 +12,7 @@ def input_clipping(inputs, history, max_token_limit):
     mode = 'input-and-history'
     # 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
     input_token_num = get_token_num(inputs)
-    if input_token_num < max_token_limit//2: 
+    if input_token_num < max_token_limit//2:
         mode = 'only-history'
         max_token_limit = max_token_limit - input_token_num
 
@@ -21,7 +21,7 @@ def input_clipping(inputs, history, max_token_limit):
     n_token = get_token_num('\n'.join(everything))
     everything_token = [get_token_num(e) for e in everything]
     delta = max(everything_token) // 16 # 截断时的颗粒度
-        
+
     while n_token > max_token_limit:
         where = np.argmax(everything_token)
         encoded = enc.encode(everything[where], disallowed_special=())
@@ -38,9 +38,9 @@ def input_clipping(inputs, history, max_token_limit):
     return inputs, history
 
 def request_gpt_model_in_new_thread_with_ui_alive(
-        inputs, inputs_show_user, llm_kwargs, 
+        inputs, inputs_show_user, llm_kwargs,
         chatbot, history, sys_prompt, refresh_interval=0.2,
-        handle_token_exceed=True, 
+        handle_token_exceed=True,
         retry_times_at_unknown_error=2,
         ):
     """
@@ -77,7 +77,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
         exceeded_cnt = 0
         while True:
             # watchdog error
-            if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience: 
+            if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
@@ -140,12 +140,12 @@ def can_multi_process(llm):
     if llm.startswith('api2d-'): return True
     if llm.startswith('azure-'): return True
     if llm.startswith('spark'): return True
-    if llm.startswith('zhipuai'): return True
+    if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
     return False
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-        inputs_array, inputs_show_user_array, llm_kwargs, 
+        inputs_array, inputs_show_user_array, llm_kwargs,
-        chatbot, history_array, sys_prompt_array, 
+        chatbot, history_array, sys_prompt_array,
         refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
         handle_token_exceed=True, show_user_at_complete=False,
         retry_times_at_unknown_error=2,
@@ -189,7 +189,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
     if not can_multi_process(llm_kwargs['llm_model']):
         max_workers = 1
-        
+
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
@@ -214,7 +214,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             try:
                 # 【第一种情况】：顺利完成
                 gpt_say = predict_no_ui_long_connection(
-                    inputs=inputs, llm_kwargs=llm_kwargs, history=history, 
+                    inputs=inputs, llm_kwargs=llm_kwargs, history=history,
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
                 )
                 mutable[index][2] = "已成功"
@@ -246,7 +246,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 print(tb_str)
                 gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
-                if retry_op > 0: 
+                if retry_op > 0:
                     retry_op -= 1
                     wait = random.randint(5, 20)
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
@@ -287,8 +287,8 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
-        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n' 
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
-                            if not done else f'`{mutable[thread_index][2]}`\n\n' 
+                            if not done else f'`{mutable[thread_index][2]}`\n\n'
                             for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
         # 在前端打印些好玩的东西
         chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
@@ -302,7 +302,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     for inputs_show_user, f in zip(inputs_show_user_array, futures):
         gpt_res = f.result()
         gpt_response_collection.extend([inputs_show_user, gpt_res])
-    
+
     # 是否在结束时，在界面上显示结果
     if show_user_at_complete:
         for inputs_show_user, f in zip(inputs_show_user_array, futures):
@@ -352,7 +352,7 @@ def read_and_clean_pdf_text(fp):
             if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
             fsize_statiscs[wtf['size']] += len(wtf['text'])
         return max(fsize_statiscs, key=fsize_statiscs.get)
-        
+
     def ffsize_same(a,b):
         """
         提取字体大小是否近似相等
@@ -388,7 +388,7 @@ def read_and_clean_pdf_text(fp):
             if index == 0:
                 page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
                     '- ', '') for t in text_areas['blocks'] if 'lines' in t]
-                
+
         ############################## <第 2 步，获取正文主字体> ##################################
         try:
             fsize_statiscs = {}
@@ -404,7 +404,7 @@ def read_and_clean_pdf_text(fp):
         mega_sec = []
         sec = []
         for index, line in enumerate(meta_line):
-            if index == 0: 
+            if index == 0:
                 sec.append(line[fc])
                 continue
             if REMOVE_FOOT_NOTE:
@@ -501,12 +501,12 @@ def get_files_from_everything(txt, type): # type='.md'
     """
     这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
     下面是对每个参数和返回值的说明：
-    参数 
+    参数
-    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。 
+    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
     - type: 字符串，表示要搜索的文件类型。默认是.md。
-    返回值 
+    返回值
-    - success: 布尔值，表示函数是否成功执行。 
+    - success: 布尔值，表示函数是否成功执行。
-    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。 
+    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
     - project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
     该函数详细注释已添加，请确认是否满足您的需要。
     """
@@ -570,7 +570,7 @@ class nougat_interface():
     def NOUGAT_parse_pdf(self, fp, chatbot, history):
         from toolbox import update_ui_lastest_msg
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...", 
+        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
                                          chatbot=chatbot, history=history, delay=0)
         self.threadLock.acquire()
         import glob, threading, os
@@ -578,7 +578,7 @@ class nougat_interface():
         dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
         os.makedirs(dst)
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）", 
+        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
                                          chatbot=chatbot, history=history, delay=0)
         self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd(), timeout=3600)
         res = glob.glob(os.path.join(dst,'*.mmd'))

crazy_functions/pdf_fns/parse_word.py

@@ -0,0 +1,85 @@
+from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
+import os
+import re
+def extract_text_from_files(txt, chatbot, history):
+    """
+    查找pdf/md/word并获取文本内容并返回状态以及文本
+
+    输入参数 Args:
+        chatbot: chatbot inputs and outputs （用户界面对话窗口句柄，用于数据流可视化）
+        history (list): List of chat history （历史，对话历史列表）
+
+    输出 Returns:
+        文件是否存在(bool)
+        final_result(list):文本内容
+        page_one(list):第一页内容/摘要
+        file_manifest(list):文件路径
+        excption(string):需要用户手动处理的信息,如没出错则保持为空
+    """
+
+    final_result = []
+    page_one = []
+    file_manifest = []
+    excption = ""
+
+    if txt == "": 
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+    
+    #查找输入区内容中的文件
+    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
+    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
+    file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
+    file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
+
+    if file_doc:
+        excption = "word"
+        return False, final_result, page_one, file_manifest, excption
+    
+    file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
+    if file_num == 0:
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+    
+    if file_pdf:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            import fitz
+        except:
+            excption = "pdf"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(pdf_manifest):
+            file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
+            file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+            pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
+            final_result.append(file_content)
+            page_one.append(pdf_one)
+            file_manifest.append(os.path.relpath(fp, folder_pdf))
+
+    if file_md:
+        for index, fp in enumerate(md_manifest):
+            with open(fp, 'r', encoding='utf-8', errors='replace') as f:
+                file_content = f.read()
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE)  #接下来提取md中的一级/二级标题作为摘要
+            if len(headers) > 0: 
+                page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
+            else:
+                page_one.append("")
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_md))
+
+    if file_word:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            from docx import Document
+        except:
+            excption = "word_pip"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(word_manifest):
+            doc = Document(fp)
+            file_content = '\n'.join([p.text for p in doc.paragraphs])
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            page_one.append(file_content[:200])
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_word))
+            
+    return True, final_result, page_one, file_manifest, excption

crazy_functions/生成多种Mermaid图表.py

@@ -1,6 +1,5 @@
 from toolbox import CatchException, update_ui, report_exception
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import read_and_clean_pdf_text
 import datetime
 
 #以下是每类图表的PROMPT
@@ -162,7 +161,7 @@ mindmap
 ```
 """
 
-def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
+def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
     ############################## <第 0 步，切割输入> ##################################
     # 借用PDF切割中的函数对文本进行切割
     TOKEN_LIMIT_PER_FRAGMENT = 2500
@@ -170,8 +169,6 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
     from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
     txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
     ############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
-    i_say_show_user = f'首先你从历史记录或文件中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
-    chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
     results = []
     MAX_WORD_TOTAL = 4096
     n_txt = len(txt)
@@ -179,7 +176,7 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
     if n_txt >= 20: print('文章极长，不能达到预期效果')
     for i in range(n_txt):
         NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
-        i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i]}"
+        i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
         i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
                                                                            llm_kwargs, chatbot, 
@@ -232,34 +229,10 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
         inputs=i_say,
         inputs_show_user=i_say_show_user,
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
-        sys_prompt="你精通使用mermaid语法来绘制图表,首先确保语法正确,其次避免在mermaid语法中使用不允许的字符,此外也应当分考虑图表的可读性。"
+        sys_prompt=""
     )
     history.append(gpt_say)
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-
-def 输入区文件处理(txt):
-    if txt == "": return False, txt
-    success = True
-    import glob
-    from .crazy_utils import get_files_from_everything
-    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
-    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
-    if len(pdf_manifest) == 0 and len(md_manifest) == 0:
-        return False, txt   #如输入区内容不是文件则直接返回输入区内容
-    
-    final_result = ""
-    if file_pdf:
-        for index, fp in enumerate(pdf_manifest):
-            file_content, page_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
-            file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-            final_result += "\n" + file_content
-    if file_md:
-        for index, fp in enumerate(md_manifest):
-            with open(fp, 'r', encoding='utf-8', errors='replace') as f:
-                file_content = f.read()
-            file_content = file_content.encode('utf-8', 'ignore').decode()
-            final_result += "\n" + file_content
-    return True, final_result
     
 @CatchException
 def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
@@ -277,26 +250,47 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？", 
-        "根据当前聊天历史或文件中(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
+        "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
         \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 尝试导入依赖，如果缺少依赖，则给出安装建议
-    try:
-        import fitz
-    except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
-            b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
     
     if os.path.exists(txt):     #如输入区无内容则直接解析历史记录
-        file_exist, txt = 输入区文件处理(txt)
+        from crazy_functions.pdf_fns.parse_word import extract_text_from_files
+        file_exist, final_result, page_one, file_manifest, excption = extract_text_from_files(txt, chatbot, history)
     else:
         file_exist = False
+        excption = ""
+        file_manifest = []
 
-    if file_exist : history = []    #如输入区内容为文件则清空历史记录
+    if excption != "":
-    history.append(txt)     #将解析后的txt传递加入到历史中
+        if excption == "word":
-    
+            report_exception(chatbot, history, 
-    yield from 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs)  
+                a = f"解析项目: {txt}", 
+                b = f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。")
+            
+        elif excption == "pdf":
+            report_exception(chatbot, history, 
+                a = f"解析项目: {txt}", 
+                b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
+        
+        elif excption == "word_pip":
+                report_exception(chatbot, history,
+                    a=f"解析项目: {txt}",
+                    b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
+
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    else:
+        if not file_exist:
+            history.append(txt)     #如输入区不是文件则将输入区内容加入历史记录
+            i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
+            chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+            yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+        else:
+            file_num = len(file_manifest)
+            for i in range(file_num):     #依次处理文件
+                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。"   # 用户提示
+                chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+                history = []    #如输入区内容为文件则清空历史记录
+                history.append(final_result[i])
+                yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)

crazy_functions/解析JupyterNotebook.py

@@ -12,6 +12,12 @@ class PaperFileGroup():
         self.sp_file_index = []
         self.sp_file_tag = []
 
+        # count_token
+        from request_llms.bridge_all import model_info
+        enc = model_info["gpt-3.5-turbo"]['tokenizer']
+        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
+        self.get_token_num = get_token_num
+
     def run_file_split(self, max_token_limit=1900):
         """
         将长文本分离开来
@@ -54,7 +60,7 @@ def parseNotebook(filename, enable_markdown=1):
         Code += f"This is {idx+1}th code block: \n"
         Code += code+"\n"
 
-    return Code 
+    return Code
 
 
 def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):

crazy_functions/辅助回答.py

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

docs/GithubAction+NoLocal+Latex

@@ -10,6 +10,9 @@ ENV PATH "$PATH:/usr/local/texlive/2024/bin/x86_64-linux"
 ENV PATH "$PATH:/usr/local/texlive/2025/bin/x86_64-linux"
 ENV PATH "$PATH:/usr/local/texlive/2026/bin/x86_64-linux"
 
+# 删除文档文件以节约空间
+RUN rm -rf /usr/local/texlive/2023/texmf-dist/doc
+
 # 指定路径
 WORKDIR /gpt
 

docs/translate_english.json

@@ -1668,7 +1668,7 @@
     "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
     "Langchain知识库": "LangchainKnowledgeBase",
     "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
-    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex输出PDF": "OutputPDFFromLatex",
     "Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF",
     "sprint亮靛": "SprintIndigo",
     "寻找Latex主文件": "FindLatexMainFile",
@@ -3004,5 +3004,7 @@
     "1. 上传图片": "TranslatedText",
     "保存状态": "TranslatedText",
     "GPT-Academic对话存档": "TranslatedText",
-    "Arxiv论文精细翻译": "TranslatedText"
+    "Arxiv论文精细翻译": "TranslatedText",
+    "from crazy_functions.AdvancedFunctionTemplate import 测试图表渲染": "from crazy_functions.AdvancedFunctionTemplate import test_chart_rendering",
+    "测试图表渲染": "test_chart_rendering"
 }

docs/translate_japanese.json

@@ -1492,7 +1492,7 @@
     "交互功能模板函数": "InteractiveFunctionTemplateFunction",
     "交互功能函数模板": "InteractiveFunctionFunctionTemplate",
     "Latex英文纠错加PDF对比": "LatexEnglishErrorCorrectionWithPDFComparison",
-    "Latex输出PDF结果": "LatexOutputPDFResult",
+    "Latex输出PDF": "LatexOutputPDFResult",
     "Latex翻译中文并重新编译PDF": "TranslateChineseAndRecompilePDF",
     "语音助手": "VoiceAssistant",
     "微调数据集生成": "FineTuneDatasetGeneration",

docs/translate_std.json

@@ -16,7 +16,7 @@
     "批量Markdown翻译": "BatchTranslateMarkdown",
     "连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion",
     "Langchain知识库": "LangchainKnowledgeBase",
-    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex输出PDF": "OutputPDFFromLatex",
     "把字符太少的块清除为回车": "ClearBlocksWithTooFewCharactersToNewline",
     "Latex精细分解与转化": "DecomposeAndConvertLatex",
     "解析一个C项目的头文件": "ParseCProjectHeaderFiles",
@@ -97,5 +97,12 @@
     "多智能体": "MultiAgent",
     "图片生成_DALLE2": "ImageGeneration_DALLE2",
     "图片生成_DALLE3": "ImageGeneration_DALLE3",
-    "图片修改_DALLE2": "ImageModification_DALLE2"
+    "图片修改_DALLE2": "ImageModification_DALLE2",
-}
+    "生成多种Mermaid图表": "GenerateMultipleMermaidCharts",
+    "知识库文件注入": "InjectKnowledgeBaseFiles",
+    "PDF翻译中文并重新编译PDF": "TranslatePDFToChineseAndRecompilePDF",
+    "随机小游戏": "RandomMiniGame",
+    "互动小游戏": "InteractiveMiniGame",
+    "解析历史输入": "ParseHistoricalInput",
+    "高阶功能模板函数示意图": "HighOrderFunctionTemplateDiagram"
+}

docs/translate_traditionalchinese.json

@@ -1468,7 +1468,7 @@
     "交互功能模板函数": "InteractiveFunctionTemplateFunctions",
     "交互功能函数模板": "InteractiveFunctionFunctionTemplates",
     "Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison",
-    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex输出PDF": "OutputPDFFromLatex",
     "Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
     "语音助手": "VoiceAssistant",
     "微调数据集生成": "FineTuneDatasetGeneration",

docs/waifu_plugin/autoload.js

@@ -1,30 +0,0 @@
-try {
-    $("<link>").attr({href: "file=docs/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css"}).appendTo('head');
-    $('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
-    $.ajax({url: "file=docs/waifu_plugin/waifu-tips.js", dataType:"script", cache: true, success: function() {
-        $.ajax({url: "file=docs/waifu_plugin/live2d.js", dataType:"script", cache: true, success: function() {
-            /* 可直接修改部分参数 */
-            live2d_settings['hitokotoAPI'] = "hitokoto.cn";  // 一言 API
-            live2d_settings['modelId'] = 5;                  // 默认模型 ID
-            live2d_settings['modelTexturesId'] = 1;          // 默认材质 ID
-            live2d_settings['modelStorage'] = false;         // 不储存模型 ID
-            live2d_settings['waifuSize']            = '210x187';
-            live2d_settings['waifuTipsSize']        = '187x52';
-            live2d_settings['canSwitchModel']       = true;
-            live2d_settings['canSwitchTextures']    = true;
-            live2d_settings['canSwitchHitokoto']    = false;
-            live2d_settings['canTakeScreenshot']    = false;
-            live2d_settings['canTurnToHomePage']    = false;
-            live2d_settings['canTurnToAboutPage']   = false;
-            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
-
-            /* 在 initModel 前添加 */
-            initModel("file=docs/waifu_plugin/waifu-tips.json");
-        }});
-    }});
-} catch(err) { console.log("[Error] JQuery is not defined.") }

request_llms/bridge_all.py

@@ -31,6 +31,9 @@ from .bridge_qianfan import predict as qianfan_ui
 from .bridge_google_gemini import predict as genai_ui
 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
+
 colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
 
 class LazyloadTiktoken(object):
@@ -44,13 +47,13 @@ class LazyloadTiktoken(object):
         tmp = tiktoken.encoding_for_model(model)
         print('加载tokenizer完毕')
         return tmp
-    
+
     def encode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.encode(*args, **kwargs)
-    
+
     def decode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.decode(*args, **kwargs)
 
 # Endpoint 重定向
@@ -63,7 +66,7 @@ azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/compl
 # 兼容旧版的配置
 try:
     API_URL = get_conf("API_URL")
-    if API_URL != "https://api.openai.com/v1/chat/completions": 
+    if API_URL != "https://api.openai.com/v1/chat/completions":
         openai_endpoint = API_URL
         print("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置")
 except:
@@ -95,7 +98,7 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-    
+
     "gpt-3.5-turbo-16k": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -185,7 +188,7 @@ model_info = {
         "tokenizer": tokenizer_gpt4,
         "token_cnt": get_token_num_gpt4,
     },
-    
+
     "gpt-4-vision-preview": {
         "fn_with_ui": chatgpt_vision_ui,
         "fn_without_ui": chatgpt_vision_noui,
@@ -215,16 +218,25 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
+    # 智谱AI
-    "api2d-gpt-3.5-turbo": {
+    "glm-4": {
-        "fn_with_ui": chatgpt_ui,
+        "fn_with_ui": zhipu_ui,
-        "fn_without_ui": chatgpt_noui,
+        "fn_without_ui": zhipu_noui,
-        "endpoint": api2d_endpoint,
+        "endpoint": None,
-        "max_token": 4096,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "glm-3-turbo": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 4,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
 
+    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
     "api2d-gpt-4": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -548,7 +560,7 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
         })
     except:
         print(trimmed_format_exc())
-if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
         from .bridge_spark import predict as spark_ui
@@ -560,6 +572,14 @@ if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
+            },
+            "sparkv3.5": {
+                "fn_with_ui": spark_ui,
+                "fn_without_ui": spark_noui,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
             }
         })
     except:
@@ -580,19 +600,17 @@ if "llama2" in AVAIL_LLM_MODELS:   # llama2
         })
     except:
         print(trimmed_format_exc())
-if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai
+if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容配置
     try:
-        from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
-        from .bridge_zhipu import predict as zhipu_ui
         model_info.update({
             "zhipuai": {
                 "fn_with_ui": zhipu_ui,
                 "fn_without_ui": zhipu_noui,
                 "endpoint": None,
-                "max_token": 4096,
+                "max_token": 10124 * 8,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
-            }
+            },
         })
     except:
         print(trimmed_format_exc())
@@ -635,7 +653,7 @@ AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
 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
-        if not azure_model_name.startswith('azure'): 
+        if not azure_model_name.startswith('azure'):
             raise ValueError("AZURE_CFG_ARRAY中配置的模型必须以azure开头")
         endpoint_ = azure_cfg_dict["AZURE_ENDPOINT"] + \
             f'openai/deployments/{azure_cfg_dict["AZURE_ENGINE"]}/chat/completions?api-version=2023-05-15'
@@ -701,7 +719,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
         executor = ThreadPoolExecutor(max_workers=4)
         models = model.split('&')
         n_model = len(models)
-        
+
         window_len = len(observe_window)
         assert window_len==3
         window_mutex = [["", time.time(), ""] for _ in range(n_model)] + [True]
@@ -720,7 +738,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
                 time.sleep(0.25)
                 if not window_mutex[-1]: break
                 # 看门狗（watchdog）
-                for i in range(n_model): 
+                for i in range(n_model):
                     window_mutex[i][1] = observe_window[1]
                 # 观察窗（window）
                 chat_string = []

request_llms/bridge_chatgpt.py

@@ -113,6 +113,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
             error_msg = get_full_error(chunk, stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
+            elif """type":"upstream_error","param":"307""" in error_msg:
+                raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
             else:
                 raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
         if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成

request_llms/bridge_google_gemini.py

@@ -57,6 +57,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     if "vision" in llm_kwargs["llm_model"]:
         have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
+        if not have_recent_file:
+            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
+            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
+            return
         def make_media_input(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>'

request_llms/bridge_qianfan.py

@@ -146,21 +146,17 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     yield from update_ui(chatbot=chatbot, history=history)
     # 开始接收回复
     try:
+        response = f"[Local Message] 等待{model_name}响应中 ..."
         for response in generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
             chatbot[-1] = (inputs, response)
             yield from update_ui(chatbot=chatbot, history=history)
+        history.extend([inputs, response])
+        yield from update_ui(chatbot=chatbot, history=history)
     except ConnectionAbortedError as e:
         from .bridge_all import model_info
         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'], 
+        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.)")
         yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
         return
-    
-    # 总结输出
-    response = f"[Local Message] {model_name}响应异常 ..."
-    if response == f"[Local Message] 等待{model_name}响应中 ...":
-        response = f"[Local Message] {model_name}响应异常 ..."
-    history.extend([inputs, response])
-    yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_qwen.py

@@ -51,6 +51,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     # 开始接收回复
     from .com_qwenapi import QwenRequestInstance
     sri = QwenRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_skylark2.py

@@ -56,6 +56,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     # 开始接收回复
     from .com_skylark2api import YUNQUERequestInstance
     sri = YUNQUERequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_spark.py

@@ -9,7 +9,7 @@ model_name = '星火认知大模型'
 
 def validate_key():
     XFYUN_APPID = get_conf('XFYUN_APPID')
-    if XFYUN_APPID == '00000000' or XFYUN_APPID == '': 
+    if XFYUN_APPID == '00000000' or XFYUN_APPID == '':
         return False
     return True
 
@@ -49,9 +49,10 @@ 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)
 
-    # 开始接收回复    
+    # 开始接收回复
     from .com_sparkapi import SparkRequestInstance
     sri = SparkRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt, use_image_api=True):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_zhipu.py

@@ -1,15 +1,21 @@
-
 import time
+import os
 from toolbox import update_ui, get_conf, update_ui_lastest_msg
-from toolbox import check_packages, report_exception
+from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
 
 model_name = '智谱AI大模型'
+zhipuai_default_model = 'glm-4'
 
 def validate_key():
     ZHIPUAI_API_KEY = get_conf("ZHIPUAI_API_KEY")
     if ZHIPUAI_API_KEY == '': return False
     return True
 
+def make_media_input(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_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
     """
         ⭐多线程方法
@@ -18,34 +24,40 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     watch_dog_patience = 5
     response = ""
 
+    if llm_kwargs["llm_model"] == "zhipuai":
+        llm_kwargs["llm_model"] = zhipuai_default_model
+
     if validate_key() is False:
         raise RuntimeError('请配置ZHIPUAI_API_KEY')
 
-    from .com_zhipuapi import ZhipuRequestInstance
+    # 开始接收回复
-    sri = ZhipuRequestInstance()
+    from .com_zhipuglm import ZhipuChatInit
-    for response in sri.generate(inputs, llm_kwargs, history, sys_prompt):
+    zhipu_bro_init = ZhipuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
         if len(observe_window) >= 1:
             observe_window[0] = response
         if len(observe_window) >= 2:
-            if (time.time()-observe_window[1]) > watch_dog_patience: raise RuntimeError("程序终止。")
+            if (time.time() - observe_window[1]) > watch_dog_patience:
+                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, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
     """
         ⭐单线程方法
         函数的说明请见 request_llms/bridge_all.py
     """
-    chatbot.append((inputs, ""))
+    chatbot.append([inputs, ""])
     yield from update_ui(chatbot=chatbot, history=history)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         check_packages(["zhipuai"])
     except:
-        yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install zhipuai==1.0.7```。",
+        yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
-                                         chatbot=chatbot, history=history, delay=0)
+            chatbot=chatbot, history=history, delay=0)
         return
-    
+
     if validate_key() is False:
         yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
         return
@@ -53,16 +65,29 @@ 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, ""]
-    # 开始接收回复    
-    from .com_zhipuapi import ZhipuRequestInstance
-    sri = ZhipuRequestInstance()
-    for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
-        chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)
 
-    # 总结输出
+    if llm_kwargs["llm_model"] == "zhipuai":
-    if response == f"[Local Message] 等待{model_name}响应中 ...":
+        llm_kwargs["llm_model"] = zhipuai_default_model
-        response = f"[Local Message] {model_name}响应异常 ..."
+
+    if llm_kwargs["llm_model"] in ["glm-4v"]:
+        have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
+        if not have_recent_file:
+            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
+            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
+            return
+        if have_recent_file:
+            inputs = make_media_input(inputs, image_paths)
+            chatbot[-1] = [inputs, ""]
+            yield from update_ui(chatbot=chatbot, history=history)
+
+
+    # 开始接收回复
+    from .com_zhipuglm import ZhipuChatInit
+    zhipu_bro_init = ZhipuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
+        chatbot[-1] = [inputs, response]
+        yield from update_ui(chatbot=chatbot, history=history)
     history.extend([inputs, response])
     yield from update_ui(chatbot=chatbot, history=history)

request_llms/com_google.py

@@ -7,7 +7,7 @@ import os
 import re
 import requests
 from typing import List, Dict, Tuple
-from toolbox import get_conf, encode_image, get_pictures_list
+from toolbox import get_conf, encode_image, get_pictures_list, to_markdown_tabs
 
 proxies, TIMEOUT_SECONDS = get_conf("proxies", "TIMEOUT_SECONDS")
 
@@ -112,34 +112,6 @@ def html_local_img(__file, layout="left", max_width=None, max_height=None, md=Tr
     return a
 
 
-def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
-    """
-    Args:
-        head: 表头：[]
-        tabs: 表值：[[列1], [列2], [列3], [列4]]
-        alignment: :--- 左对齐， :---: 居中对齐， ---: 右对齐
-        column: True to keep data in columns, False to keep data in rows (default).
-    Returns:
-        A string representation of the markdown table.
-    """
-    if column:
-        transposed_tabs = list(map(list, zip(*tabs)))
-    else:
-        transposed_tabs = tabs
-    # Find the maximum length among the columns
-    max_len = max(len(column) for column in transposed_tabs)
-
-    tab_format = "| %s "
-    tabs_list = "".join([tab_format % i for i in head]) + "|\n"
-    tabs_list += "".join([tab_format % alignment for i in head]) + "|\n"
-
-    for i in range(max_len):
-        row_data = [tab[i] if i < len(tab) else "" for tab in transposed_tabs]
-        row_data = file_manifest_filter_html(row_data, filter_=None)
-        tabs_list += "".join([tab_format % i for i in row_data]) + "|\n"
-
-    return tabs_list
-
 
 class GoogleChatInit:
     def __init__(self):

request_llms/com_sparkapi.py

@@ -65,6 +65,7 @@ class SparkRequestInstance():
         self.gpt_url = "ws://spark-api.xf-yun.com/v1.1/chat"
         self.gpt_url_v2 = "ws://spark-api.xf-yun.com/v2.1/chat"
         self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
+        self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
         self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
 
         self.time_to_yield_event = threading.Event()
@@ -91,6 +92,8 @@ class SparkRequestInstance():
             gpt_url = self.gpt_url_v2
         elif llm_kwargs['llm_model'] == 'sparkv3':
             gpt_url = self.gpt_url_v3
+        elif llm_kwargs['llm_model'] == 'sparkv3.5':
+            gpt_url = self.gpt_url_v35
         else:
             gpt_url = self.gpt_url
         file_manifest = []
@@ -190,6 +193,7 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
         "spark": "general",
         "sparkv2": "generalv2",
         "sparkv3": "generalv3",
+        "sparkv3.5": "generalv3.5",
     }
     domains_select = domains[llm_kwargs['llm_model']]
     if file_manifest: domains_select = 'image'

request_llms/com_zhipuapi.py

@@ -1,70 +0,0 @@
-from toolbox import get_conf
-import threading
-import logging
-
-timeout_bot_msg = '[Local Message] Request timeout. Network error.'
-
-class ZhipuRequestInstance():
-    def __init__(self):
-
-        self.time_to_yield_event = threading.Event()
-        self.time_to_exit_event = threading.Event()
-
-        self.result_buf = ""
-
-    def generate(self, inputs, llm_kwargs, history, system_prompt):
-        # import _thread as thread
-        import zhipuai
-        ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
-        zhipuai.api_key = ZHIPUAI_API_KEY
-        self.result_buf = ""
-        response = zhipuai.model_api.sse_invoke(
-            model=ZHIPUAI_MODEL,
-            prompt=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
-            top_p=llm_kwargs['top_p']*0.7,              # 智谱的API抽风，手动*0.7给做个线性变换
-            temperature=llm_kwargs['temperature']*0.95, # 智谱的API抽风，手动*0.7给做个线性变换
-        )
-        for event in response.events():
-            if event.event == "add":
-                # if self.result_buf == "" and event.data.startswith(" "):
-                #     event.data = event.data.lstrip(" ") # 每次智谱为啥都要带个空格开头呢？
-                self.result_buf += event.data
-                yield self.result_buf
-            elif event.event == "error" or event.event == "interrupted":
-                raise RuntimeError("Unknown error:" + event.data)
-            elif event.event == "finish":
-                yield self.result_buf
-                break
-            else:
-                raise RuntimeError("Unknown error:" + str(event))
-        if self.result_buf == "":
-            yield "智谱没有返回任何数据, 请检查ZHIPUAI_API_KEY和ZHIPUAI_MODEL是否填写正确."
-        logging.info(f'[raw_input] {inputs}')
-        logging.info(f'[response] {self.result_buf}')
-        return self.result_buf
-
-def generate_message_payload(inputs, llm_kwargs, history, system_prompt):
-    conversation_cnt = len(history) // 2
-    messages = [{"role": "user", "content": system_prompt}, {"role": "assistant", "content": "Certainly!"}]
-    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)
-    return messages

request_llms/com_zhipuglm.py

@@ -0,0 +1,84 @@
+# encoding: utf-8
+# @Time   : 2024/1/22
+# @Author : Kilig947 & binary husky
+# @Descr   : 兼容最新的智谱Ai
+from toolbox import get_conf
+from zhipuai import ZhipuAI
+from toolbox import get_conf, encode_image, get_pictures_list
+import logging, os
+
+
+def input_encode_handler(inputs, llm_kwargs):        
+    if llm_kwargs["most_recent_uploaded"].get("path"):
+        image_paths = get_pictures_list(llm_kwargs["most_recent_uploaded"]["path"])
+    md_encode = []
+    for md_path in image_paths:
+        type_ = os.path.splitext(md_path)[1].replace(".", "")
+        type_ = "jpeg" if type_ == "jpg" else type_
+        md_encode.append({"data": encode_image(md_path), "type": type_})
+    return inputs, md_encode
+
+
+class ZhipuChatInit:
+
+    def __init__(self):
+        ZHIPUAI_API_KEY, ZHIPUAI_MODEL = get_conf("ZHIPUAI_API_KEY", "ZHIPUAI_MODEL")
+        if len(ZHIPUAI_MODEL) > 0:
+            logging.error('ZHIPUAI_MODEL 配置项选项已经弃用，请在LLM_MODEL中配置')
+        self.zhipu_bro = ZhipuAI(api_key=ZHIPUAI_API_KEY)
+        self.model = ''
+
+    def __conversation_user(self, user_input: str, llm_kwargs):
+        if self.model not in ["glm-4v"]:
+            return {"role": "user", "content": user_input}
+        else:
+            input_, encode_img = input_encode_handler(user_input, llm_kwargs=llm_kwargs)
+            what_i_have_asked = {"role": "user", "content": []}
+            what_i_have_asked['content'].append({"type": 'text', "text": user_input})
+            if encode_img:
+                img_d = {"type": "image_url",
+                         "image_url": {'url': encode_img}}
+                what_i_have_asked['content'].append(img_d)
+            return what_i_have_asked
+
+    def __conversation_history(self, history, llm_kwargs):
+        messages = []
+        conversation_cnt = len(history) // 2
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
+                what_gpt_answer = {
+                    "role": "assistant",
+                    "content": history[index + 1]
+                }
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+        return messages
+
+    def __conversation_message_payload(self, inputs, llm_kwargs, history, system_prompt):
+        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
+        messages.append(self.__conversation_user(inputs, llm_kwargs))  # 处理用户对话
+        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
+        )
+        return response
+
+    def generate_chat(self, inputs, llm_kwargs, history, system_prompt):
+        self.model = llm_kwargs['llm_model']
+        response = self.__conversation_message_payload(inputs, llm_kwargs, history, system_prompt)
+        bro_results = ''
+        for chunk in response:
+            bro_results += chunk.choices[0].delta.content
+            yield chunk.choices[0].delta.content, bro_results
+
+
+if __name__ == '__main__':
+    zhipu = ZhipuChatInit()
+    zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')

requirements.txt

@@ -1,10 +1,10 @@
-https://public.gpt-academic.top/publish/gradio-3.32.7-py3-none-any.whl
+https://public.agent-matrix.com/publish/gradio-3.32.8-py3-none-any.whl
 gradio-client==0.8
 pypdf2==2.12.1
-zhipuai<2
+zhipuai>=2
 tiktoken>=0.3.3
 requests[socks]
-pydantic==1.10.11
+pydantic==2.5.2
 protobuf==3.18
 transformers>=4.27.1
 scipdf_parser>=0.52

shared_utils/handle_upload.py

@@ -0,0 +1,137 @@
+import importlib
+import time
+import inspect
+import re
+import os
+import base64
+import gradio
+import shutil
+import glob
+from shared_utils.config_loader import get_conf
+
+def html_local_file(file):
+    base_path = os.path.dirname(__file__)  # 项目目录
+    if os.path.exists(str(file)):
+        file = f'file={file.replace(base_path, ".")}'
+    return file
+
+
+def html_local_img(__file, layout="left", max_width=None, max_height=None, md=True):
+    style = ""
+    if max_width is not None:
+        style += f"max-width: {max_width};"
+    if max_height is not None:
+        style += f"max-height: {max_height};"
+    __file = html_local_file(__file)
+    a = f'<div align="{layout}"><img src="{__file}" style="{style}"></div>'
+    if md:
+        a = f"![{__file}]({__file})"
+    return a
+
+
+def file_manifest_filter_type(file_list, filter_: list = None):
+    new_list = []
+    if not filter_:
+        filter_ = ["png", "jpg", "jpeg"]
+    for file in file_list:
+        if str(os.path.basename(file)).split(".")[-1] in filter_:
+            new_list.append(html_local_img(file, md=False))
+        else:
+            new_list.append(file)
+    return new_list
+
+
+def zip_extract_member_new(self, member, targetpath, pwd):
+    # 修复中文乱码的问题
+    """Extract the ZipInfo object 'member' to a physical
+        file on the path targetpath.
+    """
+    import zipfile
+    if not isinstance(member, zipfile.ZipInfo):
+        member = self.getinfo(member)
+
+    # build the destination pathname, replacing
+    # forward slashes to platform specific separators.
+    arcname = member.filename.replace('/', os.path.sep)
+    arcname = arcname.encode('cp437', errors='replace').decode('gbk', errors='replace')
+
+    if os.path.altsep:
+        arcname = arcname.replace(os.path.altsep, os.path.sep)
+    # interpret absolute pathname as relative, remove drive letter or
+    # UNC path, redundant separators, "." and ".." components.
+    arcname = os.path.splitdrive(arcname)[1]
+    invalid_path_parts = ('', os.path.curdir, os.path.pardir)
+    arcname = os.path.sep.join(x for x in arcname.split(os.path.sep)
+                                if x not in invalid_path_parts)
+    if os.path.sep == '\\':
+        # filter illegal characters on Windows
+        arcname = self._sanitize_windows_name(arcname, os.path.sep)
+
+    targetpath = os.path.join(targetpath, arcname)
+    targetpath = os.path.normpath(targetpath)
+
+    # Create all upper directories if necessary.
+    upperdirs = os.path.dirname(targetpath)
+    if upperdirs and not os.path.exists(upperdirs):
+        os.makedirs(upperdirs)
+
+    if member.is_dir():
+        if not os.path.isdir(targetpath):
+            os.mkdir(targetpath)
+        return targetpath
+
+    with self.open(member, pwd=pwd) as source, \
+            open(targetpath, "wb") as target:
+        shutil.copyfileobj(source, target)
+
+    return targetpath
+
+
+def extract_archive(file_path, dest_dir):
+    import zipfile
+    import tarfile
+    import os
+
+    # Get the file extension of the input file
+    file_extension = os.path.splitext(file_path)[1]
+
+    # Extract the archive based on its extension
+    if file_extension == ".zip":
+        with zipfile.ZipFile(file_path, "r") as zipobj:
+            zipobj._extract_member = lambda a,b,c: zip_extract_member_new(zipobj, a,b,c)    # 修复中文乱码的问题
+            zipobj.extractall(path=dest_dir)
+            print("Successfully extracted zip archive to {}".format(dest_dir))
+
+    elif file_extension in [".tar", ".gz", ".bz2"]:
+        with tarfile.open(file_path, "r:*") as tarobj:
+            tarobj.extractall(path=dest_dir)
+            print("Successfully extracted tar archive to {}".format(dest_dir))
+
+    # 第三方库，需要预先pip install rarfile
+    # 此外，Windows上还需要安装winrar软件，配置其Path环境变量，如"C:\Program Files\WinRAR"才可以
+    elif file_extension == ".rar":
+        try:
+            import rarfile
+
+            with rarfile.RarFile(file_path) as rf:
+                rf.extractall(path=dest_dir)
+                print("Successfully extracted rar archive to {}".format(dest_dir))
+        except:
+            print("Rar format requires additional dependencies to install")
+            return "\n\n解压失败! 需要安装pip install rarfile来解压rar文件。建议：使用zip压缩格式。"
+
+    # 第三方库，需要预先pip install py7zr
+    elif file_extension == ".7z":
+        try:
+            import py7zr
+
+            with py7zr.SevenZipFile(file_path, mode="r") as f:
+                f.extractall(path=dest_dir)
+                print("Successfully extracted 7z archive to {}".format(dest_dir))
+        except:
+            print("7z format requires additional dependencies to install")
+            return "\n\n解压失败! 需要安装pip install py7zr来解压7z文件"
+    else:
+        return ""
+    return ""
+

tests/test_plugins.py

@@ -20,10 +20,10 @@ if __name__ == "__main__":
 
     # plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
 
-    # plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2307.07522")
+    # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2307.07522")
 
     plugin_test(
-        plugin="crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF",
+        plugin="crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF",
         main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
     )
 
@@ -66,7 +66,7 @@ if __name__ == "__main__":
 
     # plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="远程云服务器部署？")
 
-    # plugin_test(plugin='crazy_functions.Latex输出PDF结果->Latex翻译中文并重新编译PDF', main_input="2210.03629")
+    # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2210.03629")
 
     # advanced_arg = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、人设进行描写。要求：100字以内，用第二人称。' --system_prompt=''" }
     # plugin_test(plugin='crazy_functions.chatglm微调工具->微调数据集生成', main_input='build/dev.json', advanced_arg=advanced_arg)

themes/base64.mjs

@@ -1,296 +1 @@
-/**
+// we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
- *  base64.ts
- *
- *  Licensed under the BSD 3-Clause License.
- *    http://opensource.org/licenses/BSD-3-Clause
- *
- *  References:
- *    http://en.wikipedia.org/wiki/Base64
- *
- * @author Dan Kogai (https://github.com/dankogai)
- */
-const version = '3.7.2';
-/**
- * @deprecated use lowercase `version`.
- */
-const VERSION = version;
-const _hasatob = typeof atob === 'function';
-const _hasbtoa = typeof btoa === 'function';
-const _hasBuffer = typeof Buffer === 'function';
-const _TD = typeof TextDecoder === 'function' ? new TextDecoder() : undefined;
-const _TE = typeof TextEncoder === 'function' ? new TextEncoder() : undefined;
-const b64ch = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=';
-const b64chs = Array.prototype.slice.call(b64ch);
-const b64tab = ((a) => {
-    let tab = {};
-    a.forEach((c, i) => tab[c] = i);
-    return tab;
-})(b64chs);
-const b64re = /^(?:[A-Za-z\d+\/]{4})*?(?:[A-Za-z\d+\/]{2}(?:==)?|[A-Za-z\d+\/]{3}=?)?$/;
-const _fromCC = String.fromCharCode.bind(String);
-const _U8Afrom = typeof Uint8Array.from === 'function'
-    ? Uint8Array.from.bind(Uint8Array)
-    : (it, fn = (x) => x) => new Uint8Array(Array.prototype.slice.call(it, 0).map(fn));
-const _mkUriSafe = (src) => src
-    .replace(/=/g, '').replace(/[+\/]/g, (m0) => m0 == '+' ? '-' : '_');
-const _tidyB64 = (s) => s.replace(/[^A-Za-z0-9\+\/]/g, '');
-/**
- * polyfill version of `btoa`
- */
-const btoaPolyfill = (bin) => {
-    // console.log('polyfilled');
-    let u32, c0, c1, c2, asc = '';
-    const pad = bin.length % 3;
-    for (let i = 0; i < bin.length;) {
-        if ((c0 = bin.charCodeAt(i++)) > 255 ||
-            (c1 = bin.charCodeAt(i++)) > 255 ||
-            (c2 = bin.charCodeAt(i++)) > 255)
-            throw new TypeError('invalid character found');
-        u32 = (c0 << 16) | (c1 << 8) | c2;
-        asc += b64chs[u32 >> 18 & 63]
-            + b64chs[u32 >> 12 & 63]
-            + b64chs[u32 >> 6 & 63]
-            + b64chs[u32 & 63];
-    }
-    return pad ? asc.slice(0, pad - 3) + "===".substring(pad) : asc;
-};
-/**
- * does what `window.btoa` of web browsers do.
- * @param {String} bin binary string
- * @returns {string} Base64-encoded string
- */
-const _btoa = _hasbtoa ? (bin) => btoa(bin)
-    : _hasBuffer ? (bin) => Buffer.from(bin, 'binary').toString('base64')
-        : btoaPolyfill;
-const _fromUint8Array = _hasBuffer
-    ? (u8a) => Buffer.from(u8a).toString('base64')
-    : (u8a) => {
-        // cf. https://stackoverflow.com/questions/12710001/how-to-convert-uint8-array-to-base64-encoded-string/12713326#12713326
-        const maxargs = 0x1000;
-        let strs = [];
-        for (let i = 0, l = u8a.length; i < l; i += maxargs) {
-            strs.push(_fromCC.apply(null, u8a.subarray(i, i + maxargs)));
-        }
-        return _btoa(strs.join(''));
-    };
-/**
- * converts a Uint8Array to a Base64 string.
- * @param {boolean} [urlsafe] URL-and-filename-safe a la RFC4648 §5
- * @returns {string} Base64 string
- */
-const fromUint8Array = (u8a, urlsafe = false) => urlsafe ? _mkUriSafe(_fromUint8Array(u8a)) : _fromUint8Array(u8a);
-// This trick is found broken https://github.com/dankogai/js-base64/issues/130
-// const utob = (src: string) => unescape(encodeURIComponent(src));
-// reverting good old fationed regexp
-const cb_utob = (c) => {
-    if (c.length < 2) {
-        var cc = c.charCodeAt(0);
-        return cc < 0x80 ? c
-            : cc < 0x800 ? (_fromCC(0xc0 | (cc >>> 6))
-                + _fromCC(0x80 | (cc & 0x3f)))
-                : (_fromCC(0xe0 | ((cc >>> 12) & 0x0f))
-                    + _fromCC(0x80 | ((cc >>> 6) & 0x3f))
-                    + _fromCC(0x80 | (cc & 0x3f)));
-    }
-    else {
-        var cc = 0x10000
-            + (c.charCodeAt(0) - 0xD800) * 0x400
-            + (c.charCodeAt(1) - 0xDC00);
-        return (_fromCC(0xf0 | ((cc >>> 18) & 0x07))
-            + _fromCC(0x80 | ((cc >>> 12) & 0x3f))
-            + _fromCC(0x80 | ((cc >>> 6) & 0x3f))
-            + _fromCC(0x80 | (cc & 0x3f)));
-    }
-};
-const re_utob = /[\uD800-\uDBFF][\uDC00-\uDFFFF]|[^\x00-\x7F]/g;
-/**
- * @deprecated should have been internal use only.
- * @param {string} src UTF-8 string
- * @returns {string} UTF-16 string
- */
-const utob = (u) => u.replace(re_utob, cb_utob);
-//
-const _encode = _hasBuffer
-    ? (s) => Buffer.from(s, 'utf8').toString('base64')
-    : _TE
-        ? (s) => _fromUint8Array(_TE.encode(s))
-        : (s) => _btoa(utob(s));
-/**
- * converts a UTF-8-encoded string to a Base64 string.
- * @param {boolean} [urlsafe] if `true` make the result URL-safe
- * @returns {string} Base64 string
- */
-const encode = (src, urlsafe = false) => urlsafe
-    ? _mkUriSafe(_encode(src))
-    : _encode(src);
-/**
- * converts a UTF-8-encoded string to URL-safe Base64 RFC4648 §5.
- * @returns {string} Base64 string
- */
-const encodeURI = (src) => encode(src, true);
-// This trick is found broken https://github.com/dankogai/js-base64/issues/130
-// const btou = (src: string) => decodeURIComponent(escape(src));
-// reverting good old fationed regexp
-const re_btou = /[\xC0-\xDF][\x80-\xBF]|[\xE0-\xEF][\x80-\xBF]{2}|[\xF0-\xF7][\x80-\xBF]{3}/g;
-const cb_btou = (cccc) => {
-    switch (cccc.length) {
-        case 4:
-            var cp = ((0x07 & cccc.charCodeAt(0)) << 18)
-                | ((0x3f & cccc.charCodeAt(1)) << 12)
-                | ((0x3f & cccc.charCodeAt(2)) << 6)
-                | (0x3f & cccc.charCodeAt(3)), offset = cp - 0x10000;
-            return (_fromCC((offset >>> 10) + 0xD800)
-                + _fromCC((offset & 0x3FF) + 0xDC00));
-        case 3:
-            return _fromCC(((0x0f & cccc.charCodeAt(0)) << 12)
-                | ((0x3f & cccc.charCodeAt(1)) << 6)
-                | (0x3f & cccc.charCodeAt(2)));
-        default:
-            return _fromCC(((0x1f & cccc.charCodeAt(0)) << 6)
-                | (0x3f & cccc.charCodeAt(1)));
-    }
-};
-/**
- * @deprecated should have been internal use only.
- * @param {string} src UTF-16 string
- * @returns {string} UTF-8 string
- */
-const btou = (b) => b.replace(re_btou, cb_btou);
-/**
- * polyfill version of `atob`
- */
-const atobPolyfill = (asc) => {
-    // console.log('polyfilled');
-    asc = asc.replace(/\s+/g, '');
-    if (!b64re.test(asc))
-        throw new TypeError('malformed base64.');
-    asc += '=='.slice(2 - (asc.length & 3));
-    let u24, bin = '', r1, r2;
-    for (let i = 0; i < asc.length;) {
-        u24 = b64tab[asc.charAt(i++)] << 18
-            | b64tab[asc.charAt(i++)] << 12
-            | (r1 = b64tab[asc.charAt(i++)]) << 6
-            | (r2 = b64tab[asc.charAt(i++)]);
-        bin += r1 === 64 ? _fromCC(u24 >> 16 & 255)
-            : r2 === 64 ? _fromCC(u24 >> 16 & 255, u24 >> 8 & 255)
-                : _fromCC(u24 >> 16 & 255, u24 >> 8 & 255, u24 & 255);
-    }
-    return bin;
-};
-/**
- * does what `window.atob` of web browsers do.
- * @param {String} asc Base64-encoded string
- * @returns {string} binary string
- */
-const _atob = _hasatob ? (asc) => atob(_tidyB64(asc))
-    : _hasBuffer ? (asc) => Buffer.from(asc, 'base64').toString('binary')
-        : atobPolyfill;
-//
-const _toUint8Array = _hasBuffer
-    ? (a) => _U8Afrom(Buffer.from(a, 'base64'))
-    : (a) => _U8Afrom(_atob(a), c => c.charCodeAt(0));
-/**
- * converts a Base64 string to a Uint8Array.
- */
-const toUint8Array = (a) => _toUint8Array(_unURI(a));
-//
-const _decode = _hasBuffer
-    ? (a) => Buffer.from(a, 'base64').toString('utf8')
-    : _TD
-        ? (a) => _TD.decode(_toUint8Array(a))
-        : (a) => btou(_atob(a));
-const _unURI = (a) => _tidyB64(a.replace(/[-_]/g, (m0) => m0 == '-' ? '+' : '/'));
-/**
- * converts a Base64 string to a UTF-8 string.
- * @param {String} src Base64 string.  Both normal and URL-safe are supported
- * @returns {string} UTF-8 string
- */
-const decode = (src) => _decode(_unURI(src));
-/**
- * check if a value is a valid Base64 string
- * @param {String} src a value to check
-  */
-const isValid = (src) => {
-    if (typeof src !== 'string')
-        return false;
-    const s = src.replace(/\s+/g, '').replace(/={0,2}$/, '');
-    return !/[^\s0-9a-zA-Z\+/]/.test(s) || !/[^\s0-9a-zA-Z\-_]/.test(s);
-};
-//
-const _noEnum = (v) => {
-    return {
-        value: v, enumerable: false, writable: true, configurable: true
-    };
-};
-/**
- * extend String.prototype with relevant methods
- */
-const extendString = function () {
-    const _add = (name, body) => Object.defineProperty(String.prototype, name, _noEnum(body));
-    _add('fromBase64', function () { return decode(this); });
-    _add('toBase64', function (urlsafe) { return encode(this, urlsafe); });
-    _add('toBase64URI', function () { return encode(this, true); });
-    _add('toBase64URL', function () { return encode(this, true); });
-    _add('toUint8Array', function () { return toUint8Array(this); });
-};
-/**
- * extend Uint8Array.prototype with relevant methods
- */
-const extendUint8Array = function () {
-    const _add = (name, body) => Object.defineProperty(Uint8Array.prototype, name, _noEnum(body));
-    _add('toBase64', function (urlsafe) { return fromUint8Array(this, urlsafe); });
-    _add('toBase64URI', function () { return fromUint8Array(this, true); });
-    _add('toBase64URL', function () { return fromUint8Array(this, true); });
-};
-/**
- * extend Builtin prototypes with relevant methods
- */
-const extendBuiltins = () => {
-    extendString();
-    extendUint8Array();
-};
-const gBase64 = {
-    version: version,
-    VERSION: VERSION,
-    atob: _atob,
-    atobPolyfill: atobPolyfill,
-    btoa: _btoa,
-    btoaPolyfill: btoaPolyfill,
-    fromBase64: decode,
-    toBase64: encode,
-    encode: encode,
-    encodeURI: encodeURI,
-    encodeURL: encodeURI,
-    utob: utob,
-    btou: btou,
-    decode: decode,
-    isValid: isValid,
-    fromUint8Array: fromUint8Array,
-    toUint8Array: toUint8Array,
-    extendString: extendString,
-    extendUint8Array: extendUint8Array,
-    extendBuiltins: extendBuiltins,
-};
-// makecjs:CUT //
-export { version };
-export { VERSION };
-export { _atob as atob };
-export { atobPolyfill };
-export { _btoa as btoa };
-export { btoaPolyfill };
-export { decode as fromBase64 };
-export { encode as toBase64 };
-export { utob };
-export { encode };
-export { encodeURI };
-export { encodeURI as encodeURL };
-export { btou };
-export { decode };
-export { isValid };
-export { fromUint8Array };
-export { toUint8Array };
-export { extendString };
-export { extendUint8Array };
-export { extendBuiltins };
-// and finally,
-export { gBase64 as Base64 };

themes/common.css

@@ -59,6 +59,7 @@
 
 /* Scrollbar Width */
 ::-webkit-scrollbar {
+    height: 12px;
     width: 12px;
 }
 

themes/common.js

@@ -234,7 +234,7 @@ let timeoutID = null;
 let lastInvocationTime = 0;
 let lastArgs = null;
 function do_something_but_not_too_frequently(min_interval, func) {
-    return function(...args) {
+    return function (...args) {
         lastArgs = args;
         const now = Date.now();
         if (!lastInvocationTime || (now - lastInvocationTime) >= min_interval) {
@@ -263,13 +263,8 @@ function chatbotContentChanged(attempt = 1, force = false) {
             gradioApp().querySelectorAll('#gpt-chatbot .message-wrap .message.bot').forEach(addCopyButton);
         }, i === 0 ? 0 : 200);
     }
+    // we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
 
-    const run_mermaid_render = do_something_but_not_too_frequently(1000, function () {
-        const blocks = document.querySelectorAll(`pre.mermaid, diagram-div`);
-        if (blocks.length == 0) { return; }
-        uml("mermaid");
-    });
-    run_mermaid_render();
 }
 
 
@@ -672,9 +667,9 @@ function limit_scroll_position() {
     let scrollableDiv = document.querySelector('#gpt-chatbot > div.wrap');
     scrollableDiv.addEventListener('wheel', function (e) {
         let preventScroll = false;
-        if (e.deltaX != 0) { prevented_offset = 0; return;}
+        if (e.deltaX != 0) { prevented_offset = 0; return; }
-        if (this.scrollHeight == this.clientHeight) { prevented_offset = 0; return;}
+        if (this.scrollHeight == this.clientHeight) { prevented_offset = 0; return; }
-        if (e.deltaY < 0) { prevented_offset = 0; return;}
+        if (e.deltaY < 0) { prevented_offset = 0; return; }
         if (e.deltaY > 0 && this.scrollHeight - this.clientHeight - this.scrollTop <= 1) { preventScroll = true; }
 
         if (preventScroll) {
@@ -713,3 +708,161 @@ function GptAcademicJavaScriptInit(LAYOUT = "LEFT-RIGHT") {
     // 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');
+        $('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
+        $.ajax({
+            url: "file=themes/waifu_plugin/waifu-tips.js", dataType: "script", cache: true, success: function () {
+                $.ajax({
+                    url: "file=themes/waifu_plugin/live2d.js", dataType: "script", cache: true, success: function () {
+                        /* 可直接修改部分参数 */
+                        live2d_settings['hitokotoAPI'] = "hitokoto.cn";  // 一言 API
+                        live2d_settings['modelId'] = 3;                  // 默认模型 ID
+                        live2d_settings['modelTexturesId'] = 44;          // 默认材质 ID
+                        live2d_settings['modelStorage'] = false;         // 不储存模型 ID
+                        live2d_settings['waifuSize'] = '210x187';
+                        live2d_settings['waifuTipsSize'] = '187x52';
+                        live2d_settings['canSwitchModel'] = true;
+                        live2d_settings['canSwitchTextures'] = true;
+                        live2d_settings['canSwitchHitokoto'] = false;
+                        live2d_settings['canTakeScreenshot'] = false;
+                        live2d_settings['canTurnToHomePage'] = false;
+                        live2d_settings['canTurnToAboutPage'] = false;
+                        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
+                        /* 在 initModel 前添加 */
+                        initModel("file=themes/waifu_plugin/waifu-tips.json");
+                    }
+                });
+            }
+        });
+    } catch (err) { console.log("[Error] JQuery is not defined.") }
+}
+
+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
+        const spanText = label.querySelector('span').textContent;
+        // Get the input value
+        const checked = label.querySelector('input').checked;
+        if (checked) {
+            display_panel_arr.push(spanText)
+        }
+    });
+    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 apply_cookie_for_checkbox(dark) {
+    // console.log("apply_cookie_for_checkboxes")
+    let searchString = "输入清除键";
+    let bool_value = "False";
+
+    //////////////////  darkmode  ///////////////////
+    if (getCookie("js_darkmode_cookie")) {
+        dark = getCookie("js_darkmode_cookie")
+    }
+    dark = dark == "True";
+    if (document.querySelectorAll('.dark').length) {
+        if (!dark) {
+            document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
+        }
+    } else {
+        if (dark) {
+            document.querySelector('body').classList.add('dark');
+        }
+    }
+
+    ////////////////////// clearButton ///////////////////////////
+    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);
+        } 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);
+        }
+    }
+
+    ////////////////////// live2d ///////////////////////////
+
+    if (getCookie("js_live2d_show_cookie")) {
+        // have cookie
+        searchString = "添加Live2D形象";
+        bool_value = getCookie("js_live2d_show_cookie");
+        bool_value = bool_value == "True";
+        if (bool_value) {
+            loadLive2D();
+            set_checkbox(searchString, true);
+        } else {
+            $('.waifu').hide();
+            set_checkbox(searchString, false);
+        }
+    } 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)) {
+            loadLive2D();
+        } else {
+        }
+    }
+
+}

themes/common.py

@@ -5,17 +5,14 @@ def get_common_html_javascript_code():
     js = "\n"
     for jsf in [
         "file=themes/common.js",
-        "file=themes/mermaid.min.js",
-        "file=themes/mermaid_loader.js",
     ]:
         js += f"""<script src="{jsf}"></script>\n"""
 
     # 添加Live2D
     if ADD_WAIFU:
         for jsf in [
-            "file=docs/waifu_plugin/jquery.min.js",
+            "file=themes/waifu_plugin/jquery.min.js",
-            "file=docs/waifu_plugin/jquery-ui.min.js",
+            "file=themes/waifu_plugin/jquery-ui.min.js",
-            "file=docs/waifu_plugin/autoload.js",
         ]:
             js += f"""<script src="{jsf}"></script>\n"""
     return js

themes/mermaid_editor.js

@@ -1,55 +1 @@
-import { deflate, inflate } from '/file=themes/pako.esm.mjs';
+// we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
-import { toUint8Array, fromUint8Array, toBase64, fromBase64 } from '/file=themes/base64.mjs';
-
-const base64Serde = {
-    serialize: (state) => {
-        return toBase64(state, true);
-    },
-    deserialize: (state) => {
-        return fromBase64(state);
-    }
-};
-
-const pakoSerde = {
-    serialize: (state) => {
-        const data = new TextEncoder().encode(state);
-        const compressed = deflate(data, { level: 9 });
-        return fromUint8Array(compressed, true);
-    },
-    deserialize: (state) => {
-        const data = toUint8Array(state);
-        return inflate(data, { to: 'string' });
-    }
-};
-
-const serdes = {
-    base64: base64Serde,
-    pako: pakoSerde
-};
-
-export const serializeState = (state, serde = 'pako') => {
-    if (!(serde in serdes)) {
-        throw new Error(`Unknown serde type: ${serde}`);
-    }
-    const json = JSON.stringify(state);
-    const serialized = serdes[serde].serialize(json);
-    return `${serde}:${serialized}`;
-};
-
-const deserializeState = (state) => {
-    let type, serialized;
-    if (state.includes(':')) {
-        let tempType;
-        [tempType, serialized] = state.split(':');
-        if (tempType in serdes) {
-            type = tempType;
-        } else {
-            throw new Error(`Unknown serde type: ${tempType}`);
-        }
-    } else {
-        type = 'base64';
-        serialized = state;
-    }
-    const json = serdes[type].deserialize(serialized);
-    return JSON.parse(json);
-};

themes/mermaid_loader.js

@@ -1,197 +1 @@
-const uml = async className => {
+// we have moved mermaid-related code to gradio-fix repository: binary-husky/gradio-fix@32150d0
-
-    // Custom element to encapsulate Mermaid content.
-    class MermaidDiv extends HTMLElement {
-
-        /**
-        * Creates a special Mermaid div shadow DOM.
-        * Works around issues of shared IDs.
-        * @return {void}
-        */
-        constructor() {
-            super()
-
-            // Create the Shadow DOM and attach style
-            const shadow = this.attachShadow({ mode: "open" })
-            const style = document.createElement("style")
-            style.textContent = `
-        :host {
-          display: block;
-          line-height: initial;
-          font-size: 16px;
-        }
-        div.diagram {
-          margin: 0;
-          overflow: visible;
-        }`
-            shadow.appendChild(style)
-        }
-    }
-
-    if (typeof customElements.get("diagram-div") === "undefined") {
-        customElements.define("diagram-div", MermaidDiv)
-    }
-
-    const getFromCode = parent => {
-        // Handles <pre><code> text extraction.
-        let text = ""
-        for (let j = 0; j < parent.childNodes.length; j++) {
-            const subEl = parent.childNodes[j]
-            if (subEl.tagName.toLowerCase() === "code") {
-                for (let k = 0; k < subEl.childNodes.length; k++) {
-                    const child = subEl.childNodes[k]
-                    const whitespace = /^\s*$/
-                    if (child.nodeName === "#text" && !(whitespace.test(child.nodeValue))) {
-                        text = child.nodeValue
-                        break
-                    }
-                }
-            }
-        }
-        return text
-    }
-
-    function createOrUpdateHyperlink(parentElement, linkText, linkHref) {
-        // Search for an existing anchor element within the parentElement
-        let existingAnchor = parentElement.querySelector("a");
-
-        // Check if an anchor element already exists
-        if (existingAnchor) {
-            // Update the hyperlink reference if it's different from the current one
-            if (existingAnchor.href !== linkHref) {
-                existingAnchor.href = linkHref;
-            }
-            // Update the target attribute to ensure it opens in a new tab
-            existingAnchor.target = '_blank';
-
-            // If the text must be dynamic, uncomment and use the following line:
-            // existingAnchor.textContent = linkText;
-        } else {
-            // If no anchor exists, create one and append it to the parentElement
-            let anchorElement = document.createElement("a");
-            anchorElement.href = linkHref; // Set hyperlink reference
-            anchorElement.textContent = linkText; // Set text displayed
-            anchorElement.target = '_blank'; // Ensure it opens in a new tab
-            parentElement.appendChild(anchorElement); // Append the new anchor element to the parent
-        }
-    }
-
-    function removeLastLine(str) {
-        // 将字符串按换行符分割成数组
-        var lines = str.split('\n');
-        lines.pop();
-        // 将数组重新连接成字符串，并按换行符连接
-        var result = lines.join('\n');
-        return result;
-    }
-
-    // 给出配置 Provide a default config in case one is not specified
-    const defaultConfig = {
-        startOnLoad: false,
-        theme: "default",
-        flowchart: {
-            htmlLabels: false
-        },
-        er: {
-            useMaxWidth: false
-        },
-        sequence: {
-            useMaxWidth: false,
-            noteFontWeight: "14px",
-            actorFontSize: "14px",
-            messageFontSize: "16px"
-        }
-    }
-    if (document.body.classList.contains("dark")) {
-        defaultConfig.theme = "dark"
-    }
-    
-    const Module = await import('/file=themes/mermaid_editor.js');
-
-    function do_render(block, code, codeContent, cnt) {
-        var rendered_content = mermaid.render(`_diagram_${cnt}`, code);
-        ////////////////////////////// 记录有哪些代码已经被渲染了 ///////////////////////////////////
-        let codeFinishRenderElement = block.querySelector("code_finish_render"); // 如果block下已存在code_already_rendered元素，则获取它
-        if (codeFinishRenderElement) {                                             // 如果block下已存在code_already_rendered元素
-            codeFinishRenderElement.style.display = "none";
-        } else {
-            // 如果不存在code_finish_render元素，则将code元素中的内容添加到新创建的code_finish_render元素中
-            let codeFinishRenderElementNew = document.createElement("code_finish_render"); // 创建一个新的code_already_rendered元素
-            codeFinishRenderElementNew.style.display = "none";
-            codeFinishRenderElementNew.textContent = "";
-            block.appendChild(codeFinishRenderElementNew); // 将新创建的code_already_rendered元素添加到block中
-            codeFinishRenderElement = codeFinishRenderElementNew;
-        }
-
-        ////////////////////////////// 创建一个用于渲染的容器 ///////////////////////////////////
-        let mermaidRender = block.querySelector(".mermaid_render"); // 尝试获取已存在的<div class='mermaid_render'>
-        if (!mermaidRender) {
-            mermaidRender = document.createElement("div");  // 不存在，创建新的<div class='mermaid_render'>
-            mermaidRender.classList.add("mermaid_render");
-            block.appendChild(mermaidRender);               // 将新创建的元素附加到block
-        }
-        mermaidRender.innerHTML = rendered_content
-        codeFinishRenderElement.textContent = code  // 标记已经渲染的部分
-
-        ////////////////////////////// 创建一个“点击这里编辑脑图” ///////////////////////////////
-        let pako_encode = Module.serializeState({
-            "code": codeContent,
-            "mermaid": "{\n  \"theme\": \"default\"\n}",
-            "autoSync": true,
-            "updateDiagram": false
-        });
-        createOrUpdateHyperlink(block, "点击这里编辑脑图", "https://mermaid.live/edit#" + pako_encode)
-    }
-
-    // 加载配置 Load up the config
-    mermaid.mermaidAPI.globalReset() // 全局复位
-    const config = (typeof mermaidConfig === "undefined") ? defaultConfig : mermaidConfig
-    mermaid.initialize(config)
-    // 查找需要渲染的元素 Find all of our Mermaid sources and render them.
-    const blocks = document.querySelectorAll(`pre.mermaid`);
-
-    for (let i = 0; i < blocks.length; i++) {
-        var block = blocks[i]
-        ////////////////////////////// 如果代码没有发生变化，就不渲染了 ///////////////////////////////////
-        var code = getFromCode(block);
-        let code_elem = block.querySelector("code");
-        let codeContent = code_elem.textContent; // 获取code元素中的文本内容
-
-        // 判断codeContent是否包含'<gpt_academic_hide_mermaid_code>'，如果是，则使code_elem隐藏
-        if (codeContent.indexOf('<gpt_academic_hide_mermaid_code>') !== -1) {
-            code_elem.style.display = "none";
-        }
-
-        // 如果block下已存在code_already_rendered元素，则获取它
-        let codePendingRenderElement = block.querySelector("code_pending_render");
-        if (codePendingRenderElement) {                               // 如果block下已存在code_pending_render元素
-            codePendingRenderElement.style.display = "none";
-            if (codePendingRenderElement.textContent !== codeContent) {
-                codePendingRenderElement.textContent = codeContent; // 如果现有的code_pending_render元素中的内容与code元素中的内容不同，更新code_pending_render元素中的内容
-            }
-            else {
-                continue; // 如果相同，就不处理了
-            }
-        } else { // 如果不存在code_pending_render元素，则将code元素中的内容添加到新创建的code_pending_render元素中
-            let codePendingRenderElementNew = document.createElement("code_pending_render"); // 创建一个新的code_already_rendered元素
-            codePendingRenderElementNew.style.display = "none";
-            codePendingRenderElementNew.textContent = codeContent;
-            block.appendChild(codePendingRenderElementNew); // 将新创建的code_pending_render元素添加到block中
-            codePendingRenderElement = codePendingRenderElementNew;
-        }
-
-        ////////////////////////////// 在这里才真正开始渲染 ///////////////////////////////////
-        try {
-            do_render(block, code, codeContent, i);
-            // console.log("渲染", codeContent);
-        } catch (err) {
-            try {
-                var lines = code.split('\n'); if (lines.length < 2) { continue; }
-                do_render(block, removeLastLine(code), codeContent, i);
-                // console.log("渲染", codeContent);
-            } catch (err) {
-                console.log("以下代码不能渲染", code, removeLastLine(code), err);
-            }
-        }
-    }
-}

themes/theme.py

@@ -46,8 +46,7 @@ cookie相关工具函数
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 """
 
-
+def init_cookie(cookies):
-def init_cookie(cookies, chatbot):
     # 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
@@ -91,31 +90,107 @@ js_code_for_css_changing = """(css) => {
 }
 """
 
-js_code_for_darkmode_init = """(dark) => {
-    dark = dark == "True";
-    if (document.querySelectorAll('.dark').length) {
-        if (!dark){
-            document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
-        }
-    } else {
-        if (dark){
-            document.querySelector('body').classList.add('dark');
-        }
-    }
-}
-"""
 
 js_code_for_toggle_darkmode = """() => {
     if (document.querySelectorAll('.dark').length) {
+        setCookie("js_darkmode_cookie", "False", 365);
         document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
     } else {
+        setCookie("js_darkmode_cookie", "True", 365);
         document.querySelector('body').classList.add('dark');
     }
     document.querySelectorAll('code_pending_render').forEach(code => {code.remove();})
 }"""
 
 
-js_code_for_persistent_cookie_init = """(persistent_cookie) => {
+js_code_for_persistent_cookie_init = """(py_pickle_cookie, cookie) => {
-    return getCookie("persistent_cookie");
+    return [getCookie("py_pickle_cookie"), cookie];
+}
+"""
+
+
+js_code_reset = """
+(a,b,c)=>{
+    return [[], [], "已重置"];
+}
+"""
+
+
+js_code_clear = """
+(a,b)=>{
+    return ["", ""];
+}
+"""
+
+
+js_code_show_or_hide = """
+(display_panel_arr)=>{
+setTimeout(() => {
+    // get conf
+    display_panel_arr = get_checkbox_selected_items("cbs");
+
+    ////////////////////// 输入清除键 ///////////////////////////
+    let searchString = "输入清除键";
+    let ele = "none";
+    if (display_panel_arr.includes(searchString)) {
+        let clearButton = document.getElementById("elem_clear");
+        let clearButton2 = document.getElementById("elem_clear2");
+        clearButton.style.display = "block";
+        clearButton2.style.display = "block";
+        setCookie("js_clearbtn_show_cookie", "True", 365);
+    } else {
+        let clearButton = document.getElementById("elem_clear");
+        let clearButton2 = document.getElementById("elem_clear2");
+        clearButton.style.display = "none";
+        clearButton2.style.display = "none";
+        setCookie("js_clearbtn_show_cookie", "False", 365);
+    }
+
+    ////////////////////// 基础功能区 ///////////////////////////
+    searchString = "基础功能区";
+    if (display_panel_arr.includes(searchString)) {
+        ele = document.getElementById("basic-panel");
+        ele.style.display = "block";
+    } else {
+        ele = document.getElementById("basic-panel");
+        ele.style.display = "none";
+    }
+
+    ////////////////////// 函数插件区 ///////////////////////////
+    searchString = "函数插件区";
+    if (display_panel_arr.includes(searchString)) {
+        ele = document.getElementById("plugin-panel");
+        ele.style.display = "block";
+    } else {
+        ele = document.getElementById("plugin-panel");
+        ele.style.display = "none";
+    }
+
+}, 50);
+}
+"""
+
+
+
+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)) {
+        setCookie("js_live2d_show_cookie", "True", 365);
+        loadLive2D();
+    } else {
+        setCookie("js_live2d_show_cookie", "False", 365);
+        $('.waifu').hide();
+    }
+
+
+}, 50);
 }
 """

themes/waifu_plugin/waifu-tips.js

@@ -92,7 +92,7 @@ String.prototype.render = function(context) {
 };
 
 var re = /x/;
-console.log(re);
+// console.log(re);
 
 function empty(obj) {return typeof obj=="undefined"||obj==null||obj==""?true:false}
 function getRandText(text) {return Array.isArray(text) ? text[Math.floor(Math.random() * text.length + 1)-1] : text}
@@ -120,7 +120,7 @@ function hideMessage(timeout) {
 
 function initModel(waifuPath, type) {
     /* console welcome message */
-    eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{}));
+    // eval(function(p,a,c,k,e,r){e=function(c){return(c<a?'':e(parseInt(c/a)))+((c=c%a)>35?String.fromCharCode(c+29):c.toString(36))};if(!''.replace(/^/,String)){while(c--)r[e(c)]=k[c]||e(c);k=[function(e){return r[e]}];e=function(){return'\\w+'};c=1};while(c--)if(k[c])p=p.replace(new RegExp('\\b'+e(c)+'\\b','g'),k[c]);return p}('8.d(" ");8.d("\\U,.\\y\\5.\\1\\1\\1\\1/\\1,\\u\\2 \\H\\n\\1\\1\\1\\1\\1\\b \', !-\\r\\j-i\\1/\\1/\\g\\n\\1\\1\\1 \\1 \\a\\4\\f\'\\1\\1\\1 L/\\a\\4\\5\\2\\n\\1\\1 \\1 /\\1 \\a,\\1 /|\\1 ,\\1 ,\\1\\1\\1 \',\\n\\1\\1\\1\\q \\1/ /-\\j/\\1\\h\\E \\9 \\5!\\1 i\\n\\1\\1\\1 \\3 \\6 7\\q\\4\\c\\1 \\3\'\\s-\\c\\2!\\t|\\1 |\\n\\1\\1\\1\\1 !,/7 \'0\'\\1\\1 \\X\\w| \\1 |\\1\\1\\1\\n\\1\\1\\1\\1 |.\\x\\"\\1\\l\\1\\1 ,,,, / |./ \\1 |\\n\\1\\1\\1\\1 \\3\'| i\\z.\\2,,A\\l,.\\B / \\1.i \\1|\\n\\1\\1\\1\\1\\1 \\3\'| | / C\\D/\\3\'\\5,\\1\\9.\\1|\\n\\1\\1\\1\\1\\1\\1 | |/i \\m|/\\1 i\\1,.\\6 |\\F\\1|\\n\\1\\1\\1\\1\\1\\1.|/ /\\1\\h\\G \\1 \\6!\\1\\1\\b\\1|\\n\\1\\1\\1 \\1 \\1 k\\5>\\2\\9 \\1 o,.\\6\\2 \\1 /\\2!\\n\\1\\1\\1\\1\\1\\1 !\'\\m//\\4\\I\\g\', \\b \\4\'7\'\\J\'\\n\\1\\1\\1\\1\\1\\1 \\3\'\\K|M,p,\\O\\3|\\P\\n\\1\\1\\1\\1\\1 \\1\\1\\1\\c-,/\\1|p./\\n\\1\\1\\1\\1\\1 \\1\\1\\1\'\\f\'\\1\\1!o,.:\\Q \\R\\S\\T v"+e.V+" / W "+e.N);8.d(" ");',60,60,'|u3000|uff64|uff9a|uff40|u30fd|uff8d||console|uff8a|uff0f|uff3c|uff84|log|live2d_settings|uff70|u00b4|uff49||u2010||u3000_|u3008||_|___|uff72|u2500|uff67|u30cf|u30fc||u30bd|u4ece|u30d8|uff1e|__|u30a4|k_|uff17_|u3000L_|u3000i|uff1a|u3009|uff34|uff70r|u30fdL__||___i|l2dVerDate|u30f3|u30ce|nLive2D|u770b|u677f|u5a18|u304f__|l2dVersion|FGHRSH|u00b40i'.split('|'),0,{}));
 
     /* 判断 JQuery */
     if (typeof($.ajax) != 'function') typeof(jQuery.ajax) == 'function' ? window.$ = jQuery : console.log('[Error] JQuery is not defined.');

themes/waifu_plugin/waifu-tips.json

@@ -44,8 +44,8 @@
         { "selector": ".container a[href^='http']", "text": ["要看看 <span style=\"color:#0099cc;\">{text}</span> 么？"] },
         { "selector": ".fui-home", "text": ["点击前往首页，想回到上一页可以使用浏览器的后退功能哦"] },
         { "selector": ".fui-chat", "text": ["一言一语，一颦一笑。一字一句，一颗赛艇。"] },
-        { "selector": ".fui-eye", "text": ["嗯··· 要切换 看板娘 吗？"] },
+        { "selector": ".fui-eye", "text": ["嗯··· 要切换 Live2D形象 吗？"] },
-        { "selector": ".fui-user", "text": ["喜欢换装 Play 吗？"] },
+        { "selector": ".fui-user", "text": ["喜欢换装吗？"] },
         { "selector": ".fui-photo", "text": ["要拍张纪念照片吗？"] },
         { "selector": ".fui-info-circle", "text": ["这里有关于我的信息呢"] },
         { "selector": ".fui-cross", "text": ["你不喜欢我了吗..."] },
@@ -77,14 +77,28 @@
             "看什么看(*^▽^*)",
             "焦虑时，吃顿大餐心情就好啦^_^",
             "你这个年纪，怎么睡得着觉的你^_^",
-            "修改ADD_WAIFU=False，我就不再打扰你了~",
+            "打开“界面外观”菜单，可选择关闭Live2D形象",
-            "经常去github看看我们的更新吧，也许有好玩的新功能呢。",
+            "经常去Github看看我们的更新吧，也许有好玩的新功能呢。",
             "试试本地大模型吧，有的也很强大的哦。",
             "很多强大的函数插件隐藏在下拉菜单中呢。",
-            "红色的插件，使用之前需要把文件上传进去哦。",
+            "插件使用之前，需要把文件上传进去哦。",
-            "想添加功能按钮吗？读读readme很容易就学会啦。",
+            "上传文件时，可以把文件直接拖进对话中的哦。",
+            "上传文件时，可以文件或图片粘贴到输入区哦。",
+            "想添加基础功能按钮吗？打开“界面外观”菜单进行自定义吧！",
             "敏感或机密的信息，不可以问AI的哦！",
-            "LLM究竟是划时代的创新，还是扼杀创造力的毒药呢？"
+            "LLM究竟是划时代的创新，还是扼杀创造力的毒药呢？",
+            "休息一下，起来走动走动吧！",
+            "今天的阳光也很不错哦，不妨外出晒晒。",
+            "笑一笑，生活更美好！",
+            "遇到难题，深呼吸就能解决一半。",
+            "偶尔换换环境，灵感也许就来了。",
+            "小憩片刻，醒来便是满血复活。",
+            "技术改变生活，让我们共同进步。",
+            "保持好奇心，探索未知的世界。",
+            "遇到困难，记得还有朋友和AI陪在你身边。",
+            "劳逸结合，方能长久。",
+            "偶尔给自己放个假，放松心情。",
+            "不要害怕失败，勇敢尝试才能成功。"
         ] }
     ],
     "click": [

toolbox.py

@@ -25,6 +25,10 @@ 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.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
 
 pj = os.path.join
 default_user_name = "default_user"
@@ -329,54 +333,6 @@ def find_free_port():
         return s.getsockname()[1]
 
 
-def extract_archive(file_path, dest_dir):
-    import zipfile
-    import tarfile
-    import os
-
-    # Get the file extension of the input file
-    file_extension = os.path.splitext(file_path)[1]
-
-    # Extract the archive based on its extension
-    if file_extension == ".zip":
-        with zipfile.ZipFile(file_path, "r") as zipobj:
-            zipobj.extractall(path=dest_dir)
-            print("Successfully extracted zip archive to {}".format(dest_dir))
-
-    elif file_extension in [".tar", ".gz", ".bz2"]:
-        with tarfile.open(file_path, "r:*") as tarobj:
-            tarobj.extractall(path=dest_dir)
-            print("Successfully extracted tar archive to {}".format(dest_dir))
-
-    # 第三方库，需要预先pip install rarfile
-    # 此外，Windows上还需要安装winrar软件，配置其Path环境变量，如"C:\Program Files\WinRAR"才可以
-    elif file_extension == ".rar":
-        try:
-            import rarfile
-
-            with rarfile.RarFile(file_path) as rf:
-                rf.extractall(path=dest_dir)
-                print("Successfully extracted rar archive to {}".format(dest_dir))
-        except:
-            print("Rar format requires additional dependencies to install")
-            return "\n\n解压失败! 需要安装pip install rarfile来解压rar文件。建议：使用zip压缩格式。"
-
-    # 第三方库，需要预先pip install py7zr
-    elif file_extension == ".7z":
-        try:
-            import py7zr
-
-            with py7zr.SevenZipFile(file_path, mode="r") as f:
-                f.extractall(path=dest_dir)
-                print("Successfully extracted 7z archive to {}".format(dest_dir))
-        except:
-            print("7z format requires additional dependencies to install")
-            return "\n\n解压失败! 需要安装pip install py7zr来解压7z文件"
-    else:
-        return ""
-    return ""
-
-
 def find_recent_files(directory):
     """
     me: find files that is created with in one minutes under a directory with python, write a function
@@ -474,39 +430,8 @@ def del_outdated_uploads(outdate_time_seconds, target_path_base=None):
     return
 
 
-def html_local_file(file):
-    base_path = os.path.dirname(__file__)  # 项目目录
-    if os.path.exists(str(file)):
-        file = f'file={file.replace(base_path, ".")}'
-    return file
 
-
+def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False, omit_path=None):
-def html_local_img(__file, layout="left", max_width=None, max_height=None, md=True):
-    style = ""
-    if max_width is not None:
-        style += f"max-width: {max_width};"
-    if max_height is not None:
-        style += f"max-height: {max_height};"
-    __file = html_local_file(__file)
-    a = f'<div align="{layout}"><img src="{__file}" style="{style}"></div>'
-    if md:
-        a = f"![{__file}]({__file})"
-    return a
-
-
-def file_manifest_filter_type(file_list, filter_: list = None):
-    new_list = []
-    if not filter_:
-        filter_ = ["png", "jpg", "jpeg"]
-    for file in file_list:
-        if str(os.path.basename(file)).split(".")[-1] in filter_:
-            new_list.append(html_local_img(file, md=False))
-        else:
-            new_list.append(file)
-    return new_list
-
-
-def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
     """
     Args:
         head: 表头：[]
@@ -530,6 +455,9 @@ def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False):
     for i in range(max_len):
         row_data = [tab[i] if i < len(tab) else "" for tab in transposed_tabs]
         row_data = file_manifest_filter_type(row_data, filter_=None)
+        # for dat in row_data:
+        #     if (omit_path is not None) and os.path.exists(dat):
+        #         dat = os.path.relpath(dat, omit_path)
         tabs_list += "".join([tab_format % i for i in row_data]) + "|\n"
 
     return tabs_list
@@ -565,15 +493,21 @@ def on_file_uploaded(
         )
 
     # 整理文件集合 输出消息
-    moved_files = [fp for fp in glob.glob(f"{target_path_base}/**/*", recursive=True)]
+    files = glob.glob(f"{target_path_base}/**/*", recursive=True)
-    moved_files_str = to_markdown_tabs(head=["文件"], tabs=[moved_files])
+    moved_files = [fp for fp in files]
+    max_file_to_show = 10
+    if len(moved_files) > max_file_to_show:
+        moved_files = moved_files[:max_file_to_show//2] + [f'... ( 📌省略{len(moved_files) - max_file_to_show}个文件的显示 ) ...'] + \
+                      moved_files[-max_file_to_show//2:]
+    moved_files_str = to_markdown_tabs(head=["文件"], tabs=[moved_files], omit_path=target_path_base)
     chatbot.append(
         [
             "我上传了文件，请查收",
-            f"[Local Message] 收到以下文件: \n\n{moved_files_str}"
+            f"[Local Message] 收到以下文件 （上传到路径：{target_path_base}）: " +
-            + f"\n\n调用路径参数已自动修正到: \n\n{txt}"
+            f"\n\n{moved_files_str}" +
-            + f"\n\n现在您点击任意函数插件时，以上文件将被作为输入参数"
+            f"\n\n调用路径参数已自动修正到: \n\n{txt}" +
-            + upload_msg,
+            f"\n\n现在您点击任意函数插件时，以上文件将被作为输入参数" +
+            upload_msg,
         ]
     )
 

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.71,
+  "version": 3.72,
   "show_feature": true,
-  "new_feature": "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": "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"
 }