Merge branch 'master' into huggingface

README.md

@@ -1,3 +1,15 @@
+---
+title: ChatImprovement
+emoji: 😻
+colorFrom: blue
+colorTo: blue
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+---
+
+# ChatGPT 学术优化
 > **Note**
 >
 > 2023.5.27 对Gradio依赖进行了调整，Fork并解决了官方Gradio的若干Bugs。请及时**更新代码**并重新更新pip依赖。安装依赖时，请严格选择`requirements.txt`中**指定的版本**： 

app.py

@@ -1,13 +1,15 @@
 import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
 
 def main():
+    import subprocess, sys
+    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'gradio-stable-fork'])
     import gradio as gr
-    if gr.__version__ not in ['3.28.3','3.32.2']: assert False, "需要特殊依赖，请务必用 pip install -r requirements.txt 指令安装依赖，详情信息见requirements.txt"
+    if gr.__version__ not in ['3.28.3','3.32.3']: assert False, "请用 pip install -r requirements.txt 安装依赖"
     from request_llm.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS = \
+        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS')
 
     # 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
@@ -54,6 +56,7 @@ def main():
     cancel_handles = []
     with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
         gr.HTML(title_html)
+        gr.HTML('''<center><a href="https://huggingface.co/spaces/qingxu98/gpt-academic?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>请您打开此页面后务必点击上方的“复制空间”（Duplicate Space）按钮！<font color="#FF00FF">使用时，先在输入框填入API-KEY然后回车。</font><br/>切忌在“复制空间”（Duplicate Space）之前填入API_KEY或进行提问，否则您的API_KEY将极可能被空间所有者攫取！<br/>支持任意数量的OpenAI的密钥和API2D的密钥共存，例如输入"OpenAI密钥1,API2D密钥2"，然后提交，即可同时使用两种模型接口。</center>''')
         cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
         with gr_L1():
             with gr_L2(scale=2):
@@ -63,7 +66,7 @@ def main():
             with gr_L2(scale=1):
                 with gr.Accordion("输入区", open=True) as area_input_primary:
                     with gr.Row():
-                        txt = gr.Textbox(show_label=False, placeholder="Input question here.").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OpenAI密钥和API2D密钥共存。").style(container=False)
                     with gr.Row():
                         submitBtn = gr.Button("提交", variant="primary")
                     with gr.Row():
@@ -104,7 +107,7 @@ def main():
                     system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
                     top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
                     temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
-                    max_length_sl = gr.Slider(minimum=256, maximum=8192, value=4096, step=1, interactive=True, label="Local LLM MaxLength",)
+                    max_length_sl = gr.Slider(minimum=256, maximum=4096, value=512, step=1, interactive=True, label="Local LLM MaxLength",)
                     checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "底部输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区")
                     md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
 
@@ -144,11 +147,6 @@ def main():
         resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
         clearBtn.click(lambda: ("",""), None, [txt, txt2])
         clearBtn2.click(lambda: ("",""), None, [txt, txt2])
-        if AUTO_CLEAR_TXT:
-            submitBtn.click(lambda: ("",""), None, [txt, txt2])
-            submitBtn2.click(lambda: ("",""), None, [txt, txt2])
-            txt.submit(lambda: ("",""), None, [txt, txt2])
-            txt2.submit(lambda: ("",""), None, [txt, txt2])
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
@@ -202,10 +200,7 @@ def main():
         threading.Thread(target=warm_up_modules, name="warm-up", daemon=True).start()
 
     auto_opentab_delay()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
-        server_name="0.0.0.0", server_port=PORT,
-        favicon_path="docs/logo.png", auth=AUTHENTICATION,
-        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
+    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"])
 
     # 如果需要在二级路径下运行
     # CUSTOM_PATH, = get_conf('CUSTOM_PATH')

config.py

@@ -45,10 +45,9 @@ 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
 
-# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 )
-LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt35", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"]
-# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+# OpenAI模型选择是（gpt4现在只对申请成功的人开放）
+LLM_MODEL = "gpt-3.5-turbo" # 可选 "chatglm"
+AVAIL_LLM_MODELS = ["newbing-free", "gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
@@ -56,9 +55,6 @@ LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
-# 是否在提交时自动清空输入框
-AUTO_CLEAR_TXT = False
-
 # 加一个live2d装饰
 ADD_WAIFU = False
 

core_functional.py

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

crazy_functions/crazy_functions_test.py

@@ -193,9 +193,8 @@ def test_Latex():
     # txt = r"https://arxiv.org/abs/2212.10156"
     # txt = r"https://arxiv.org/abs/2211.11559"
     # txt = r"https://arxiv.org/abs/2303.08774"
-    # txt = r"https://arxiv.org/abs/2303.12712"
+    txt = r"https://arxiv.org/abs/2303.12712"
     # txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
-    txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
     
 
     for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):

crazy_functions/latex_utils.py

@@ -189,18 +189,6 @@ def rm_comments(main_file):
     main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
     return main_file
 
-def find_tex_file_ignore_case(fp):
-    dir_name = os.path.dirname(fp)
-    base_name = os.path.basename(fp)
-    if not base_name.endswith('.tex'): base_name+='.tex'
-    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
-    # go case in-sensitive
-    import glob
-    for f in glob.glob(dir_name+'/*.tex'):
-        base_name_s = os.path.basename(fp)
-        if base_name_s.lower() == base_name.lower(): return f
-    return None
-
 def merge_tex_files_(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -209,11 +197,14 @@ def merge_tex_files_(project_foler, main_file, mode):
     for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
         f = s.group(1)
         fp = os.path.join(project_foler, f)
-        fp = find_tex_file_ignore_case(fp)
-        if fp:
-            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
-        else:
-            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
+        if os.path.exists(fp):  
+            # e.g., \input{srcs/07_appendix.tex}
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx:
+                c = fx.read()
+        else:  
+            # e.g., \input{srcs/07_appendix}
+            with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
+                c = fx.read()
         c = merge_tex_files_(project_foler, c, mode)
         main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
     return main_file

crazy_functions/图片生成.py

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

crazy_functions/批量翻译PDF文档_多线程.py

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

crazy_functions/询问多个大语言模型.py

@@ -13,11 +13,11 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     web_port        当前软件运行的端口号
     """
     history = []    # 清空历史，以免输入溢出
-    chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
+    chatbot.append((txt, "正在同时咨询gpt-3.5和gpt-4……"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
-    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
+    llm_kwargs['llm_model'] = 'gpt-3.5-turbo&gpt-4' # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt, 
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 

crazy_functions/谷歌检索小助手.py

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

requirements.txt

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

toolbox.py

@@ -842,4 +842,4 @@ def objload(file='objdump.tmp'):
         return
     with open(file, 'rb') as f:
         return pickle.load(f)
-    
+