update pdf translate fn

feat:联网搜索功能，cn.bing.com版，国内可用

.github/workflows/build-image.yaml

@@ -0,0 +1,38 @@
+name: Build Image
+
+
+on:
+  workflow_dispatch:
+    inputs:
+      release_tag:
+        description: 'Tag for the images'
+        required: true
+
+env:
+  REGISTRY: registry.cn-hongkong.aliyuncs.com
+  NAMESPACE: chatwithpaper
+  IMAGE: academic
+  TAG: ${{ github.event.inputs.release_tag || github.event.client_payload.release_tag }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    environment: production
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Login to Registry
+      uses: docker/login-action@v2.1.0
+      with:
+        registry: "${{ env.REGISTRY }}"
+        username: "${{ secrets.ACR_USER }}"
+        password: "${{ secrets.ACR_PASSWORD }}"
+
+    - name: Build and push image
+      uses: docker/build-push-action@v4
+      with:
+        context: .
+        file: docs/Dockerfile+NoLocal+Latex
+        tags: ${{ env.REGISTRY }}/${{ env.NAMESPACE }}/${{ env.IMAGE }}:${{ env.TAG }}
+        push: true

.github/workflows/build-with-chatglm.yml

@@ -1,44 +0,0 @@
-# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image for ChatGLM support
-
-on:
-  push:
-    branches:
-      - 'master'
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}_chatglm_moss
-
-jobs:
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v2
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          push: true
-          file: docs/GithubAction+ChatGLM+Moss
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-with-jittorllms.yml

@@ -1,44 +0,0 @@
-# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image for ChatGLM support
-
-on:
-  push:
-    branches:
-      - 'master'
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}_jittorllms
-
-jobs:
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v2
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          push: true
-          file: docs/GithubAction+JittorLLMs
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-without-local-llms.yml

@@ -1,44 +0,0 @@
-# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image
-
-on:
-  push:
-    branches:
-      - 'master'
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}_nolocal
-
-jobs:
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@v2
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v4
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          push: true
-          file: docs/GithubAction+NoLocal
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

README.md

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

config.py

@@ -45,9 +45,10 @@ WEB_PORT = -1
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
-# OpenAI模型选择是（gpt4现在只对申请成功的人开放）
+# 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 "chatglm"
+LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["newbing-free", "gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo"]
+# 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"]
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"

core_functional.py

@@ -42,6 +42,7 @@ def get_core_functions():
         "中译英": {
             "Prefix":   r"Please translate following sentence to English:" + "\n\n",
             "Suffix":   r"",
+            "Visible": False,
         },
         "学术中英互译": {
             "Prefix":   r"I want you to act as a scientific English-Chinese translator, " +
@@ -63,6 +64,7 @@ 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",

crazy_functional.py

@@ -26,6 +26,7 @@ def get_crazy_functions():
     from crazy_functions.对话历史存档 import 删除所有本地对话历史记录
     
     from crazy_functions.批量Markdown翻译 import Markdown英译中
+        
     function_plugins = {
         "解析整个Python项目": {
             "Color": "stop",    # 按钮颜色
@@ -47,10 +48,10 @@ def get_crazy_functions():
             "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
             "ArgsReminder": "若输入0，则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
         },
-        "批量总结Word文档": {
+        # "批量总结Word文档": {
-            "Color": "stop",
+        #     "Color": "stop",
-            "Function": HotReload(总结word文档)
+        #     "Function": HotReload(总结word文档)
-        },
+        # },
         "解析整个C++项目头文件": {
             "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
@@ -108,10 +109,10 @@ def get_crazy_functions():
         "保存当前的对话": {
             "Function": HotReload(对话历史存档)
         },
-        "[多线程Demo] 解析此项目本身（源码自译解）": {
+        # "[多线程Demo] 解析此项目本身（源码自译解）": {
-            "AsButton": False,  # 加入下拉菜单中
+        #     "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析项目本身)
+        #     "Function": HotReload(解析项目本身)
-        },
+        # },
         # "[老旧的Demo] 把本项目源代码切换成全英文": {
         #     # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
         #     "AsButton": False,  # 加入下拉菜单中
@@ -137,15 +138,15 @@ def get_crazy_functions():
     from crazy_functions.批量Markdown翻译 import Markdown中译英
 
     function_plugins.update({
-        "批量翻译PDF文档（多线程）": {
+        "本地PDF全文翻译": {
             "Color": "stop",
             "AsButton": True,  # 加入下拉菜单中
             "Function": HotReload(批量翻译PDF文档)
         },
-        "询问多个GPT模型": {
+        # "询问多个GPT模型": {
-            "Color": "stop",    # 按钮颜色
+        #     "Color": "stop",    # 按钮颜色
-            "Function": HotReload(同时问询)
+        #     "Function": HotReload(同时问询)
-        },
+        # },
         "[测试功能] 批量总结PDF文档": {
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
@@ -222,54 +223,57 @@ def get_crazy_functions():
         })
     except:
         print('Load function plugin failed')
+    from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
+    function_plugins.update({
+        "ArXiv Latex一键翻译（输入区给定arXiv ID）": {
+            "Color": "stop",
+            "AsButton": True,
+            "AdvancedArgs": True,
+            "ArgsReminder": 
+                "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+ 
+                "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+            "Function": HotReload(Latex翻译中文并重新编译PDF)
+        }
+    })
+    # try:
+    #     from crazy_functions.联网的ChatGPT import 连接网络回答问题
+    #     function_plugins.update({
+    #         "连接网络回答问题（先输入问题，再点击按钮，需要访问谷歌）": {
+    #             "Color": "stop",
+    #             "AsButton": False,  # 加入下拉菜单中
+    #             "Function": HotReload(连接网络回答问题)
+    #         }
+    #     })
+    # except:
+    #     print('Load function plugin failed')
 
-    try:
+    # try:
-        from crazy_functions.联网的ChatGPT import 连接网络回答问题
+    #     from crazy_functions.解析项目源代码 import 解析任意code项目
-        function_plugins.update({
+    #     function_plugins.update({
-            "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
+    #         "解析项目源代码（手动指定和筛选源代码文件类型）": {
-                "Color": "stop",
+    #             "Color": "stop",
-                "AsButton": False,  # 加入下拉菜单中
+    #             "AsButton": False,
-                "Function": HotReload(连接网络回答问题)
+    #             "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-            }
+    #             "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
-        })
+    #             "Function": HotReload(解析任意code项目)
-        from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
+    #         },
-        function_plugins.update({
+    #     })
-            "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
+    # except:
-                "Color": "stop",
+    #     print('Load function plugin failed')
-                "AsButton": False,  # 加入下拉菜单中
-                "Function": HotReload(连接bing搜索回答问题)
-            }
-        })
-    except:
-        print('Load function plugin failed')
 
-    try:
+    # try:
-        from crazy_functions.解析项目源代码 import 解析任意code项目
+    #     from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
-        function_plugins.update({
+    #     function_plugins.update({
-            "解析项目源代码（手动指定和筛选源代码文件类型）": {
+    #         "询问多个GPT模型（手动指定询问哪些模型）": {
-                "Color": "stop",
+    #             "Color": "stop",
-                "AsButton": False,
+    #             "AsButton": False,
-                "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
+    #             "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-                "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
+    #             "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
-                "Function": HotReload(解析任意code项目)
+    #             "Function": HotReload(同时问询_指定模型)
-            },
+    #         },
-        })
+    #     })
-    except:
+    # except:
-        print('Load function plugin failed')
+    #     print('Load function plugin failed')
-
-    try:
-        from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
-        function_plugins.update({
-            "询问多个GPT模型（手动指定询问哪些模型）": {
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-                "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
-                "Function": HotReload(同时问询_指定模型)
-            },
-        })
-    except:
-        print('Load function plugin failed')
 
     try:
         from crazy_functions.图片生成 import 图片生成
@@ -364,29 +368,18 @@ def get_crazy_functions():
                 "Function": HotReload(Latex英文纠错加PDF对比)
             }
         })
-        from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
+        
-        function_plugins.update({
+        # function_plugins.update({
-            "Arixv翻译（输入arxivID）[需Latex]": {
+        #     "本地论文翻译（上传Latex压缩包） [需Latex]": {
-                "Color": "stop",
+        #         "Color": "stop",
-                "AsButton": False,
+        #         "AsButton": False,
-                "AdvancedArgs": True,
+        #         "AdvancedArgs": True,
-                "ArgsReminder": 
+        #         "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。 "+ 
+        #             "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+ 
-                    "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+        #             "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
-                "Function": HotReload(Latex翻译中文并重新编译PDF)
+        #         "Function": HotReload(Latex翻译中文并重新编译PDF)
-            }
+        #     }
-        })
+        # })
-        function_plugins.update({
-            "本地论文翻译（上传Latex压缩包）[需Latex]": {
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": 
-                    "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+ 
-                    "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
-                "Function": HotReload(Latex翻译中文并重新编译PDF)
-            }
-        })
     except:
         print('Load function plugin failed')
 
@@ -404,4 +397,18 @@ def get_crazy_functions():
     # except:
     #     print('Load function plugin failed')
 
+    # try:
+    #     from crazy_functions.虚空终端 import 终端
+    #     function_plugins.update({
+    #         "超级终端": {
+    #             "Color": "stop",
+    #             "AsButton": False,
+    #             # "AdvancedArgs": True,
+    #             # "ArgsReminder": "",
+    #             "Function": HotReload(终端)
+    #         }
+    #     })
+    # except:
+    #     print('Load function plugin failed')
+
     return function_plugins

crazy_functions/Latex输出PDF结果.py

@@ -3,7 +3,9 @@ from toolbox import CatchException, report_execption, update_ui_lastest_msg, zip
 from functools import partial
 import glob, os, requests, time
 pj = os.path.join
-ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+# ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+# ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+ARXIV_CACHE_DIR = os.getenv("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". '
@@ -190,9 +192,9 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
 
 
     # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
+    if not os.path.exists(project_folder + '/merge_proofread.tex'):
         yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
+                                chatbot, history, system_prompt, mode='proofread_latex', switch_prompt=switch_prompt)
 
 
     # <-------------- compile PDF ------------->

crazy_functions/crazy_functions_test.py

@@ -193,8 +193,9 @@ 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"C:\Users\fuqingxu\Desktop\9"
     
 
     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

@@ -449,9 +449,10 @@ class LatexPaperSplit():
     """
     def __init__(self) -> None:
         self.nodes = None
-        self.msg = "*{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
+        self.msg = "{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
             "版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
-            "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
+            "项目Github地址: \\url{https://github.com/binary-husky/gpt_academic/}。" + \
+            "项目在线体验地址: \\url{https://chatpaper.org}。"
         # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
         self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\" 
 

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
+from toolbox import update_ui, promote_file_to_downloadzone
 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
@@ -147,23 +147,14 @@ 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'./gpt_log/翻译-{os.path.basename(pdf_path)}'
+        rename_file = f'翻译-{os.path.basename(pdf_path)}'
-        if os.path.exists(rename_file):
+        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
-            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'./gpt_log/翻译-{os.path.basename(html_path)}'
+        rename_file = f'翻译-{os.path.basename(html_path)}'
-        if os.path.exists(rename_file):
+        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
-            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gpt-3.5和gpt-4……"))
+    chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
-    llm_kwargs['llm_model'] = 'gpt-3.5-turbo&gpt-4' # 支持任意数量的llm接口，用&符号分隔
+    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt, 
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 

crazy_functions/谷歌检索小助手.py

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

docs/use_azure.md

@@ -96,15 +96,6 @@
 
 ● 部署名（不是模型名）
 
-# 修改 config.py
-
-```
-AZURE_ENDPOINT = "填入终结点"
-AZURE_API_KEY = "填入azure openai api的密钥"
-AZURE_API_VERSION = "2023-05-15"  # 默认使用 2023-05-15 版本，无需修改
-AZURE_ENGINE = "填入部署名"
-
-```
 # API的使用
 
 接下来就是具体怎么使用API了，还是可以参考官方文档：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)

main.py

@@ -1,10 +1,9 @@
 import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
+from pathlib import Path
 
 def main():
-    import subprocess, sys
-    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'gradio-stable-fork'])
     import gradio as gr
-    if gr.__version__ not in ['3.28.3','3.32.3']: assert False, "请用 pip install -r requirements.txt 安装依赖"
+    if gr.__version__ not in ['3.28.3','3.32.2']: assert False, "需要特殊依赖，请务必用 pip install -r requirements.txt 指令安装依赖，详情信息见requirements.txt"
     from request_llm.bridge_all import predict
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
@@ -17,7 +16,7 @@ def main():
 
     from check_proxy import get_current_version
     initial_prompt = "Serve me as a writing and programming assistant."
-    title_html = f"<h1 align=\"center\">ChatGPT 学术优化 {get_current_version()}</h1>"
+    title_html = f"<h1 align=\"center\">ChatGPT 学术优化 网页测试版 {get_current_version()}</h1>"
     description =  """代码开源和更新[地址🚀](https://github.com/binary-husky/chatgpt_academic)，感谢热情的[开发者们❤️](https://github.com/binary-husky/chatgpt_academic/graphs/contributors)"""
 
     # 问询记录, python 版本建议3.9+（越新越好）
@@ -54,9 +53,22 @@ def main():
         CHATBOT_HEIGHT /= 2
 
     cancel_handles = []
+    # Read your Baidu statistics code from the file
+    baidu_stats_code = Path('./sites/baidu_stats.html').read_text()
     with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
+        # Insert your Baidu statistics code here
+        gradio_original_template_fn = gr.routes.templates.TemplateResponse
+
+        def gradio_new_template_fn(*args, **kwargs):
+            res = gradio_original_template_fn(*args, **kwargs)
+            res.body = res.body.replace(b'</html>', f'{baidu_stats_code}</html>'.encode("utf8"))
+            res.init_headers()
+            return res
+
+        gr.routes.templates.TemplateResponse = gradio_new_template_fn  # override gradio template
+
+        # Insert Title
         gr.HTML(title_html)
-        gr.HTML('''<center><a href="https://huggingface.co/spaces/qingxu98/gpt-academic?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>请您打开此页面后务必点击上方的“复制空间”（Duplicate Space）按钮！<font color="#FF00FF">使用时，先在输入框填入API-KEY然后回车。</font><br/>切忌在“复制空间”（Duplicate Space）之前填入API_KEY或进行提问，否则您的API_KEY将极可能被空间所有者攫取！<br/>支持任意数量的OpenAI的密钥和API2D的密钥共存，例如输入"OpenAI密钥1,API2D密钥2"，然后提交，即可同时使用两种模型接口。</center>''')
         cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
         with gr_L1():
             with gr_L2(scale=2):
@@ -66,7 +78,7 @@ def main():
             with gr_L2(scale=1):
                 with gr.Accordion("输入区", open=True) as area_input_primary:
                     with gr.Row():
-                        txt = gr.Textbox(show_label=False, lines=2, placeholder="输入问题或API密钥，输入多个密钥时，用英文逗号间隔。支持OpenAI密钥和API2D密钥共存。").style(container=False)
+                        txt = gr.Textbox(show_label=False, placeholder="Input question here.").style(container=False)
                     with gr.Row():
                         submitBtn = gr.Button("提交", variant="primary")
                     with gr.Row():
@@ -74,7 +86,13 @@ def main():
                         stopBtn = gr.Button("停止", variant="secondary"); stopBtn.style(size="sm")
                         clearBtn = gr.Button("清除", variant="secondary", visible=False); clearBtn.style(size="sm")
                     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}")
+                        status = gr.Markdown(f"""Tips: 1. 按Enter提交, 按Shift+Enter换行；2. 当前模型: {LLM_MODEL} \n {proxy_info}.
+                                             3. 请注意隐私保护和遵守法律法规；
+                                             4. 请勿使用本服务进行违法犯罪活动；
+                                             5. 我和qingxu都希望能够为大家提供一个好的**学术工具**，希望大家不要攻击和滥用本服务；
+                                             6. 本服务还存在各种bug，如果发现bug，欢迎加群反馈或者发issue告诉我们；
+                                             7. 希望大家能结合ChatPaper的速读，找到需要精读的，再用本工具的全文翻译，实现快速知识摄取。
+                                             """)
                 with gr.Accordion("基础功能区", open=True) as area_basic_fn:
                     with gr.Row():
                         for k in functional:
@@ -170,6 +188,7 @@ def main():
                 ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
             return ret
         dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
+        
         def on_md_dropdown_changed(k):
             return {chatbot: gr.update(label="当前模型："+k)}
         md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
@@ -183,6 +202,7 @@ def main():
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
         stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
+        demo.load(on_dropdown_changed, inputs=gr.State("ArXiv Latex一键翻译（输入区给定arXiv ID）"), outputs=[switchy_bt, plugin_advanced_arg])
 
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def auto_opentab_delay():
@@ -200,7 +220,10 @@ def main():
         threading.Thread(target=warm_up_modules, name="warm-up", daemon=True).start()
 
     auto_opentab_delay()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png", blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
+    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
+        server_name="0.0.0.0", server_port=PORT,
+        favicon_path="docs/logo.png", auth=AUTHENTICATION,
+        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
 
     # 如果需要在二级路径下运行
     # CUSTOM_PATH, = get_conf('CUSTOM_PATH')

request_llm/bridge_all.py

@@ -152,7 +152,7 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # 将 chatglm 直接对齐到 chatglm2
+    # chatglm
     "chatglm": {
         "fn_with_ui": chatglm_ui,
         "fn_without_ui": chatglm_noui,
@@ -161,15 +161,6 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-    "chatglm2": {
-        "fn_with_ui": chatglm_ui,
-        "fn_without_ui": chatglm_noui,
-        "endpoint": None,
-        "max_token": 1024,
-        "tokenizer": tokenizer_gpt35,
-        "token_cnt": get_token_num_gpt35,
-    },
-    
     # newbing
     "newbing": {
         "fn_with_ui": newbing_ui,

request_llm/bridge_chatglm.py

@@ -40,12 +40,12 @@ class GetGLMHandle(Process):
         while True:
             try:
                 if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
                     device, = get_conf('LOCAL_MODEL_DEVICE')
                     if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float()
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
                     self.chatglm_model = self.chatglm_model.eval()
                     break
                 else:

requirements.txt

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

sites/baidu_stats.html

@@ -0,0 +1,10 @@
+<!-- baidu_stats.html -->
+<script>
+var _hmt = _hmt || [];
+(function() {
+  var hm = document.createElement("script");
+  hm.src = "https://hm.baidu.com/hm.js?208673d55832a94b9bbe10b1f4e70c09";
+  var s = document.getElementsByTagName("script")[0];
+  s.parentNode.insertBefore(hm, s);
+})();
+</script>

toolbox.py

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