update pdf translate fn

Patch 1

.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 }}

check_proxy.py

@@ -1,10 +1,10 @@
 
-def check_proxy(proxies: dict):
+def check_proxy(proxies):
     import requests
-    proxies_https = proxies.get('https') if proxies is not None else '无'
+    proxies_https = proxies['https'] if proxies is not None else '无'
     try:
         response = requests.get("https://ipapi.co/json/",
-                                proxies=proxies, timeout=30)
+                                proxies=proxies, timeout=4)
         data = response.json()
         print(f'查询代理的地理位置，返回的结果是{data}')
         if 'country_name' in data:
@@ -12,12 +12,10 @@ def check_proxy(proxies: dict):
             result = f"代理配置 {proxies_https}, 代理所在地：{country}"
         elif 'error' in data:
             result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
-        else:
-            result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
         print(result)
         return result
-    except Exception as e:
-        result = f"代理 {proxies_https} 查询出现异常: {e}，代理可能无效"
+    except:
+        result = f"代理配置 {proxies_https}, 代理所在地查询超时，代理可能无效"
         print(result)
         return result
 

config.py

@@ -47,7 +47,7 @@ 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"]
+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
@@ -56,9 +56,6 @@ 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

@@ -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, " +
@@ -74,5 +75,6 @@ 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_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": {
-            "Color": "stop",
-            "Function": HotReload(总结word文档)
-        },
+        # "批量总结Word文档": {
+        #     "Color": "stop",
+        #     "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）": {
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析项目本身)
-        },
+        # "[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
+        #     "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": {
-            "Color": "stop",    # 按钮颜色
-            "Function": HotReload(同时问询)
-        },
+        # "询问多个GPT模型": {
+        #     "Color": "stop",    # 按钮颜色
+        #     "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:
-        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（输入问题后点击该插件，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)
-            }
-        })
-        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）": {
-                "Color": "stop",
-                "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:
+    #     from crazy_functions.解析项目源代码 import 解析任意code项目
+    #     function_plugins.update({
+    #         "解析项目源代码（手动指定和筛选源代码文件类型）": {
+    #             "Color": "stop",
+    #             "AsButton": 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
+    #             "Function": HotReload(解析任意code项目)
+    #         },
+    #     })
+    # except:
+    #     print('Load function plugin failed')
 
-    try:
-        from crazy_functions.解析项目源代码 import 解析任意code项目
-        function_plugins.update({
-            "解析项目源代码（手动指定和筛选源代码文件类型）": {
-                "Color": "stop",
-                "AsButton": 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
-                "Function": HotReload(解析任意code项目)
-            },
-        })
-    except:
-        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.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({
-            "Arixv翻译（输入arxivID）[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)
-            }
-        })
-        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)
-            }
-        })
+        
+        # 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

@@ -195,7 +195,7 @@ def test_Latex():
     # txt = r"https://arxiv.org/abs/2303.08774"
     # 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！
+    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/crazy_utils.py

@@ -1,19 +1,16 @@
 from toolbox import update_ui, get_conf, trimmed_format_exc
 import threading
 
-
 def input_clipping(inputs, history, max_token_limit):
     import numpy as np
     from request_llm.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=()))
+    def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
 
     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
 
@@ -21,13 +18,13 @@ def input_clipping(inputs, history, max_token_limit):
     everything.extend(history)
     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
-
+    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=())
-        clipped_encoded = encoded[:len(encoded) - delta]
-        everything[where] = enc.decode(clipped_encoded)[:-1]  # -1 to remove the may-be illegal char
+        clipped_encoded = encoded[:len(encoded)-delta]
+        everything[where] = enc.decode(clipped_encoded)[:-1]    # -1 to remove the may-be illegal char
         everything_token[where] = get_token_num(everything[where])
         n_token = get_token_num('\n'.join(everything))
 
@@ -38,13 +35,12 @@ def input_clipping(inputs, history, max_token_limit):
     history = everything[1:]
     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,
-):
+        ):
     """
     Request GPT model，请求GPT模型同时维持用户界面活跃。
 
@@ -68,16 +64,15 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     from request_llm.bridge_all import predict_no_ui_long_connection
     # 用户反馈
     chatbot.append([inputs_show_user, ""])
-    yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
     executor = ThreadPoolExecutor(max_workers=16)
     mutable = ["", time.time(), ""]
-
     def _req_gpt(inputs, history, sys_prompt):
         retry_op = retry_times_at_unknown_error
         exceeded_cnt = 0
         while True:
             # watchdog error
-            if len(mutable) >= 2 and (time.time() - mutable[1]) > 5:
+            if len(mutable) >= 2 and (time.time()-mutable[1]) > 5: 
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
@@ -94,14 +89,14 @@ def request_gpt_model_in_new_thread_with_ui_alive(
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
                     MAX_TOKEN = 4096
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
-                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN - EXCEED_ALLO)
+                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
                     mutable[0] += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
-                    continue  # 返回重试
+                    continue # 返回重试
                 else:
                     # 【选择放弃】
                     tb_str = '```\n' + trimmed_format_exc() + '```'
                     mutable[0] += f"[Local Message] 警告，在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
-                    return mutable[0]  # 放弃
+                    return mutable[0] # 放弃
             except:
                 # 【第三种情况】：其他错误：重试几次
                 tb_str = '```\n' + trimmed_format_exc() + '```'
@@ -109,15 +104,14 @@ def request_gpt_model_in_new_thread_with_ui_alive(
                 mutable[0] += f"[Local Message] 警告，在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if retry_op > 0:
                     retry_op -= 1
-                    mutable[
-                        0] += f"[Local Message] 重试中，请稍等 {retry_times_at_unknown_error - retry_op}/{retry_times_at_unknown_error}：\n\n"
+                    mutable[0] += f"[Local Message] 重试中，请稍等 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}：\n\n"
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
                         time.sleep(30)
                     time.sleep(5)
-                    continue  # 返回重试
+                    continue # 返回重试
                 else:
                     time.sleep(5)
-                    return mutable[0]  # 放弃
+                    return mutable[0] # 放弃
 
     # 提交任务
     future = executor.submit(_req_gpt, inputs, history, sys_prompt)
@@ -129,21 +123,21 @@ def request_gpt_model_in_new_thread_with_ui_alive(
         if future.done():
             break
         chatbot[-1] = [chatbot[-1][0], mutable[0]]
-        yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
 
     final_result = future.result()
     chatbot[-1] = [chatbot[-1][0], final_result]
-    yield from update_ui(chatbot=chatbot, history=[])  # 如果最后成功了，则删除报错信息
+    yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
     return final_result
 
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-        inputs_array, inputs_show_user_array, llm_kwargs,
-        chatbot, history_array, sys_prompt_array,
+        inputs_array, inputs_show_user_array, llm_kwargs, 
+        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,
-):
+        ):
     """
     Request GPT model using multiple threads with UI and high efficiency
     请求GPT模型的[多线程]版。
@@ -176,21 +170,19 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     from request_llm.bridge_all import predict_no_ui_long_connection
     assert len(inputs_array) == len(history_array)
     assert len(inputs_array) == len(sys_prompt_array)
-    if max_workers == -1:  # 读取配置文件
-        try:
-            max_workers, = get_conf('DEFAULT_WORKER_NUM')
-        except:
-            max_workers = 8
+    if max_workers == -1: # 读取配置文件
+        try: max_workers, = get_conf('DEFAULT_WORKER_NUM')
+        except: max_workers = 8
         if max_workers <= 0: max_workers = 3
     # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
     if not (llm_kwargs['llm_model'].startswith('gpt-') or llm_kwargs['llm_model'].startswith('api2d-')):
         max_workers = 1
-
+        
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
     chatbot.append(["请开始多线程操作。", ""])
-    yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
     # 跨线程传递
     mutable = [["", time.time(), "等待中"] for _ in range(n_frag)]
 
@@ -202,13 +194,13 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         mutable[index][2] = "执行中"
         while True:
             # watchdog error
-            if len(mutable[index]) >= 2 and (time.time() - mutable[index][1]) > 5:
+            if len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > 5: 
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
                 # time.sleep(10); raise RuntimeError("测试")
                 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"
@@ -222,26 +214,24 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
                     MAX_TOKEN = 4096
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
-                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN - EXCEED_ALLO)
+                    inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
                     gpt_say += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
                     mutable[index][2] = f"截断重试"
-                    continue  # 返回重试
+                    continue # 返回重试
                 else:
                     # 【选择放弃】
                     tb_str = '```\n' + trimmed_format_exc() + '```'
                     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 len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
                     mutable[index][2] = "输入过长已放弃"
-                    return gpt_say  # 放弃
-            except Exception as e:
+                    return gpt_say # 放弃
+            except:
                 # 【第三种情况】：其他错误
                 tb_str = '```\n' + trimmed_format_exc() + '```'
-                print(f"发生异常：{e}, 调用栈信息：{tb_str}")
+                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 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: 
                     retry_op -= 1
                     wait = random.randint(5, 20)
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
@@ -251,22 +241,19 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                         fail_info = ""
                     # 也许等待十几秒后，情况会好转
                     for i in range(wait):
-                        mutable[index][2] = f"{fail_info}等待重试 {wait - i}";
-                        time.sleep(1)
+                        mutable[index][2] = f"{fail_info}等待重试 {wait-i}"; time.sleep(1)
                     # 开始重试
-                    mutable[index][
-                        2] = f"重试中 {retry_times_at_unknown_error - retry_op}/{retry_times_at_unknown_error}"
-                    continue  # 返回重试
+                    mutable[index][2] = f"重试中 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}"
+                    continue # 返回重试
                 else:
                     mutable[index][2] = "已失败"
                     wait = 5
                     time.sleep(5)
-                    return gpt_say  # 放弃
+                    return gpt_say # 放弃
 
     # 异步任务开始
-    futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in
-               zip(
-                   range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
+    futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in zip(
+        range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
     cnt = 0
     while True:
         # yield一次以刷新前端页面
@@ -280,17 +267,17 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             mutable[thread_index][1] = time.time()
         # 在前端打印些好玩的东西
         for thread_index, _ in enumerate(worker_done):
-            print_something_really_funny = "[ ...`" + mutable[thread_index][0][-scroller_max_len:]. \
+            print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
                 replace('\n', '').replace('```', '...').replace(
-                ' ', '.').replace('<br/>', '.....').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'
-                            if not done else f'`{mutable[thread_index][2]}`\n\n'
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\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))]
-        yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
+        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))]
+        yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
         if all(worker_done):
             executor.shutdown()
             break
@@ -300,13 +287,13 @@ 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):
             gpt_res = f.result()
             chatbot.append([inputs_show_user, gpt_res])
-            yield from update_ui(chatbot=chatbot, history=[])  # 刷新界面
+            yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
             time.sleep(0.3)
     return gpt_response_collection
 
@@ -319,7 +306,6 @@ def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
             lines = txt_tocut.split('\n')
             estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
             estimated_line_cut = int(estimated_line_cut)
-            cnt = 0
             for cnt in reversed(range(estimated_line_cut)):
                 if must_break_at_empty_line:
                     if lines[cnt] != "":
@@ -336,7 +322,6 @@ def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
             result = [prev]
             result.extend(cut(post, must_break_at_empty_line))
             return result
-
     try:
         return cut(txt, must_break_at_empty_line=True)
     except RuntimeError:
@@ -352,10 +337,9 @@ def force_breakdown(txt, limit, get_token_fn):
             return txt[:i], txt[i:]
     return "Tiktoken未知错误", "Tiktoken未知错误"
 
-
 def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
     # 递归
-    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):
+    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):  
         if get_token_fn(txt_tocut) <= limit:
             return [txt_tocut]
         else:
@@ -381,7 +365,6 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
             result = [prev]
             result.extend(cut(post, must_break_at_empty_line, break_anyway=break_anyway))
             return result
-
     try:
         # 第1次尝试，将双空行（\n\n）作为切分点
         return cut(txt, must_break_at_empty_line=True)
@@ -392,7 +375,7 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
         except RuntimeError:
             try:
                 # 第3次尝试，将英文句号（.）作为切分点
-                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False)  # 这个中文的句号是故意的，作为一个标识而存在
+                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
                 return [r.replace('。\n', '.') for r in res]
             except RuntimeError as e:
                 try:
@@ -404,6 +387,7 @@ def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
                     return cut(txt, must_break_at_empty_line=False, break_anyway=True)
 
 
+
 def read_and_clean_pdf_text(fp):
     """
     这个函数用于分割pdf，用了很多trick，逻辑较乱，效果奇好
@@ -431,9 +415,8 @@ def read_and_clean_pdf_text(fp):
     fc = 0  # Index 0 文本
     fs = 1  # Index 1 字体
     fb = 2  # Index 2 框框
-    REMOVE_FOOT_NOTE = True  # 是否丢弃掉 不是正文的内容 （比正文字体小，如参考文献、脚注、图注等）
-    REMOVE_FOOT_FFSIZE_PERCENT = 0.95  # 小于正文的？时，判定为不是正文（有些文章的正文部分字体大小不是100%统一的，有肉眼不可见的小变化）
-
+    REMOVE_FOOT_NOTE = True # 是否丢弃掉 不是正文的内容 （比正文字体小，如参考文献、脚注、图注等）
+    REMOVE_FOOT_FFSIZE_PERCENT = 0.95 # 小于正文的？时，判定为不是正文（有些文章的正文部分字体大小不是100%统一的，有肉眼不可见的小变化）
     def primary_ffsize(l):
         """
         提取文本块主字体
@@ -443,12 +426,12 @@ 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):
+        
+    def ffsize_same(a,b):
         """
         提取字体大小是否近似相等
         """
-        return abs((a - b) / max(a, b)) < 0.02
+        return abs((a-b)/max(a,b)) < 0.02
 
     with fitz.open(fp) as doc:
         meta_txt = []
@@ -468,19 +451,18 @@ def read_and_clean_pdf_text(fp):
                         if len(txt_line) == 0: continue
                         pf = primary_ffsize(l)
                         meta_line.append([txt_line, pf, l['bbox'], l])
-                        for wtf in l['spans']:  # for l in t['lines']:
+                        for wtf in l['spans']: # for l in t['lines']:
                             meta_span.append([wtf['text'], wtf['size'], len(wtf['text'])])
                     # meta_line.append(["NEW_BLOCK", pf])
-            # 块元提取                           for each word segment with in line                       for each line
-            # cross-line words                          for each block
+            # 块元提取                           for each word segment with in line                       for each line         cross-line words                          for each block
             meta_txt.extend([" ".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])
             meta_font.extend([np.mean([np.mean([wtf['size'] for wtf in l['spans']])
-                                       for l in t['lines']]) for t in text_areas['blocks'] if 'lines' in t])
+                             for l in t['lines']]) for t in text_areas['blocks'] if 'lines' in t])
             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> ##################################
         fsize_statiscs = {}
         for span in meta_span:
@@ -494,33 +476,32 @@ 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:
                 if meta_line[index][fs] <= give_up_fize_threshold:
                     continue
-            if ffsize_same(meta_line[index][fs], meta_line[index - 1][fs]):
+            if ffsize_same(meta_line[index][fs], meta_line[index-1][fs]):
                 # 尝试识别段落
-                if meta_line[index][fc].endswith('.') and \
-                        (meta_line[index - 1][fc] != 'NEW_BLOCK') and \
-                        (meta_line[index][fb][2] - meta_line[index][fb][0]) < (
-                        meta_line[index - 1][fb][2] - meta_line[index - 1][fb][0]) * 0.7:
+                if meta_line[index][fc].endswith('.') and\
+                    (meta_line[index-1][fc] != 'NEW_BLOCK') and \
+                    (meta_line[index][fb][2] - meta_line[index][fb][0]) < (meta_line[index-1][fb][2] - meta_line[index-1][fb][0]) * 0.7:
                     sec[-1] += line[fc]
                     sec[-1] += "\n\n"
                 else:
                     sec[-1] += " "
                     sec[-1] += line[fc]
             else:
-                if (index + 1 < len(meta_line)) and \
-                        meta_line[index][fs] > main_fsize:
+                if (index+1 < len(meta_line)) and \
+                    meta_line[index][fs] > main_fsize:
                     # 单行 + 字体大
                     mega_sec.append(copy.deepcopy(sec))
                     sec = []
                     sec.append("# " + line[fc])
                 else:
                     # 尝试识别section
-                    if meta_line[index - 1][fs] > meta_line[index][fs]:
+                    if meta_line[index-1][fs] > meta_line[index][fs]:
                         sec.append("\n" + line[fc])
                     else:
                         sec.append(line[fc])
@@ -539,15 +520,13 @@ def read_and_clean_pdf_text(fp):
                 if len(block_txt) < 100:
                     meta_txt[index] = '\n'
             return meta_txt
-
         meta_txt = 把字符太少的块清除为回车(meta_txt)
 
         def 清理多余的空行(meta_txt):
             for index in reversed(range(1, len(meta_txt))):
-                if meta_txt[index] == '\n' and meta_txt[index - 1] == '\n':
+                if meta_txt[index] == '\n' and meta_txt[index-1] == '\n':
                     meta_txt.pop(index)
             return meta_txt
-
         meta_txt = 清理多余的空行(meta_txt)
 
         def 合并小写开头的段落块(meta_txt):
@@ -558,18 +537,16 @@ def read_and_clean_pdf_text(fp):
                     return True
                 else:
                     return False
-
             for _ in range(100):
                 for index, block_txt in enumerate(meta_txt):
                     if starts_with_lowercase_word(block_txt):
-                        if meta_txt[index - 1] != '\n':
-                            meta_txt[index - 1] += ' '
+                        if meta_txt[index-1] != '\n':
+                            meta_txt[index-1] += ' '
                         else:
-                            meta_txt[index - 1] = ''
-                        meta_txt[index - 1] += meta_txt[index]
+                            meta_txt[index-1] = ''
+                        meta_txt[index-1] += meta_txt[index]
                         meta_txt[index] = '\n'
             return meta_txt
-
         meta_txt = 合并小写开头的段落块(meta_txt)
         meta_txt = 清理多余的空行(meta_txt)
 
@@ -589,7 +566,7 @@ def read_and_clean_pdf_text(fp):
     return meta_txt, page_one_meta
 
 
-def get_files_from_everything(txt, type):  # type='.md'
+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：
@@ -611,10 +588,9 @@ def get_files_from_everything(txt, type):  # type='.md'
         from toolbox import get_conf
         proxies, = get_conf('proxies')
         r = requests.get(txt, proxies=proxies)
-        with open('./gpt_log/temp' + type, 'wb+') as f:
-            f.write(r.content)
+        with open('./gpt_log/temp'+type, 'wb+') as f: f.write(r.content)
         project_folder = './gpt_log/'
-        file_manifest = ['./gpt_log/temp' + type]
+        file_manifest = ['./gpt_log/temp'+type]
     elif txt.endswith(type):
         # 直接给定文件
         file_manifest = [txt]
@@ -622,7 +598,7 @@ def get_files_from_everything(txt, type):  # type='.md'
     elif os.path.exists(txt):
         # 本地路径，递归搜索
         project_folder = txt
-        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*' + type, recursive=True)]
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*'+type, recursive=True)]
         if len(file_manifest) == 0:
             success = False
     else:
@@ -633,14 +609,16 @@ def get_files_from_everything(txt, type):  # type='.md'
     return success, file_manifest, project_folder
 
 
+
+
 def Singleton(cls):
     _instance = {}
-
+ 
     def _singleton(*args, **kargs):
         if cls not in _instance:
             _instance[cls] = cls(*args, **kargs)
         return _instance[cls]
-
+ 
     return _singleton
 
 
@@ -659,30 +637,31 @@ class knowledge_archive_interface():
             from toolbox import ProxyNetworkActivate
             print('Checking Text2vec ...')
             from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-            with ProxyNetworkActivate():  # 临时地激活代理网络
+            with ProxyNetworkActivate():    # 临时地激活代理网络
                 self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
 
         return self.text2vec_large_chinese
 
+
     def feed_archive(self, file_manifest, id="default"):
         self.threadLock.acquire()
         # import uuid
         self.current_id = id
         from zh_langchain import construct_vector_store
-        self.qa_handle, self.kai_path = construct_vector_store(
-            vs_id=self.current_id,
-            files=file_manifest,
+        self.qa_handle, self.kai_path = construct_vector_store(   
+            vs_id=self.current_id, 
+            files=file_manifest, 
             sentence_size=100,
             history=[],
             one_conent="",
             one_content_segmentation="",
-            text2vec=self.get_chinese_text2vec(),
+            text2vec = self.get_chinese_text2vec(),
         )
         self.threadLock.release()
 
     def get_current_archive_id(self):
         return self.current_id
-
+    
     def get_loaded_file(self):
         return self.qa_handle.get_loaded_file()
 
@@ -691,31 +670,30 @@ class knowledge_archive_interface():
         if not self.current_id == id:
             self.current_id = id
             from zh_langchain import construct_vector_store
-            self.qa_handle, self.kai_path = construct_vector_store(
-                vs_id=self.current_id,
-                files=[],
+            self.qa_handle, self.kai_path = construct_vector_store(   
+                vs_id=self.current_id, 
+                files=[], 
                 sentence_size=100,
                 history=[],
                 one_conent="",
                 one_content_segmentation="",
-                text2vec=self.get_chinese_text2vec(),
+                text2vec = self.get_chinese_text2vec(),
             )
         VECTOR_SEARCH_SCORE_THRESHOLD = 0
         VECTOR_SEARCH_TOP_K = 4
         CHUNK_SIZE = 512
         resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
-            query=txt,
-            vs_path=self.kai_path,
+            query = txt,
+            vs_path = self.kai_path,
             score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-            vector_search_top_k=VECTOR_SEARCH_TOP_K,
+            vector_search_top_k=VECTOR_SEARCH_TOP_K, 
             chunk_conent=True,
             chunk_size=CHUNK_SIZE,
-            text2vec=self.get_chinese_text2vec(),
+            text2vec = self.get_chinese_text2vec(),
         )
         self.threadLock.release()
         return resp, prompt
 
-
 def try_install_deps(deps):
     for dep in deps:
         import subprocess, sys

crazy_functions/latex_utils.py

@@ -203,7 +203,6 @@ def merge_tex_files_(project_foler, main_file, mode):
                 c = fx.read()
         else:  
             # e.g., \input{srcs/07_appendix}
-            assert os.path.exists(fp+'.tex'), f'即找不到{fp}，也找不到{fp}.tex，Tex源文件缺失！'
             with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
                 c = fx.read()
         c = merge_tex_files_(project_foler, c, mode)
@@ -450,9 +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/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/读文章写摘要.py

@@ -1,78 +1,67 @@
-from toolbox import CatchException, report_execption, write_results_to_file
 from toolbox import update_ui
+from toolbox import CatchException, report_execption, write_results_to_file
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-
 fast_debug = False
 
 
 def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    import time
-    import os
+    import time, glob, os
     print('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
         with open(fp, 'r', encoding='utf-8', errors='replace') as f:
             file_content = f.read()
 
-        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index == 0 else ""
+        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
         i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
         i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-        if not fast_debug:
+        if not fast_debug: 
             msg = '正常'
             # ** gpt request **
-            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs,
-                                                                               chatbot, history=[],
-                                                                               sys_prompt=system_prompt)  # 带超时倒计时
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs, chatbot, history=[], sys_prompt=system_prompt)   # 带超时倒计时
 
             chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user);
-            history.append(gpt_say)
-            yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
+            history.append(i_say_show_user); history.append(gpt_say)
+            yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
             if not fast_debug: time.sleep(2)
 
     all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
     i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
     chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    if not fast_debug:
+    if not fast_debug: 
         msg = '正常'
         # ** gpt request **
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot,
-                                                                           history=history,
-                                                                           sys_prompt=system_prompt)  # 带超时倒计时
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot, history=history, sys_prompt=system_prompt)   # 带超时倒计时
 
         chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say)
-        history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
+        history.append(i_say); history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
         res = write_results_to_file(history)
         chatbot.append(("完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg)  # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+
 
 
 @CatchException
-def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, system_prompt, web_port, history=None):
-    # history = []    # 清空历史，以免输入溢出
-    if history is None:
-        history = []  # 清空历史，以免输入溢出
-    import glob
-    import os
+def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    history = []    # 清空历史，以免输入溢出
+    import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
-        if txt == "":
-            txt = '空空如也的输入栏'
-        report_execption(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
+        if txt == "": txt = '空空如也的输入栏'
+        report_execption(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)]  # + \
-    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
-    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] # + \
+                    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
+                    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(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
+        report_execption(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
     yield from 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/辅助回答.py

@@ -1,28 +0,0 @@
-# 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/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

@@ -1,4 +1,5 @@
 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 gradio as gr
@@ -6,8 +7,8 @@ def main():
     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
@@ -15,7 +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）
@@ -52,7 +53,21 @@ 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)
         cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
         with gr_L1():
@@ -71,7 +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:
@@ -104,7 +125,7 @@ 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 +165,6 @@ 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
@@ -172,6 +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] )
@@ -185,6 +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():

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:

request_llm/bridge_chatgpt.py

@@ -28,7 +28,6 @@ proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \
 timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
                   '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
 
-
 def get_full_error(chunk, stream_response):
     """
         获取完整的从Openai返回的报错
@@ -41,9 +40,7 @@ def get_full_error(chunk, stream_response):
     return chunk
 
 
-def predict_no_ui_long_connection(
-        inputs, llm_kwargs, history=None, sys_prompt="", observe_window=None, console_slience=False
-):
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
     """
     发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
     inputs：
@@ -57,59 +54,45 @@ def predict_no_ui_long_connection(
     observe_window = None：
         用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
     """
-    if history is None:
-        history = []
-    watch_dog_patience = 5  # 看门狗的耐心, 设置5秒即可
+    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
     headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
     retry = 0
-    from bridge_all import model_info
     while True:
         try:
             # make a POST request to the API endpoint, stream=False
+            from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
             response = requests.post(endpoint, headers=headers, proxies=proxies,
-                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS)
-            stream_response = response.iter_lines()
-            break
-        except (requests.exceptions.ReadTimeout, requests.exceptions.ConnectionError):
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
+        except requests.exceptions.ReadTimeout as e:
             retry += 1
             traceback.print_exc()
-            if retry > MAX_RETRY:
-                raise TimeoutError
-            if MAX_RETRY != 0:
-                print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
-        except Exception as e:
-            print(f"出现异常：{e}")
-            raise e
+            if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
 
+    stream_response =  response.iter_lines()
     result = ''
     while True:
-        try:
-            chunk = next(stream_response).decode()
+        try: chunk = next(stream_response).decode()
         except StopIteration: 
             break
-        # except requests.exceptions.ConnectionError:
-        #     chunk = next(stream_response).decode()  # 失败了，重试一次？再失败就没办法了。
-        if len(chunk) == 0:
-            continue
+        except requests.exceptions.ConnectionError:
+            chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。
+        if len(chunk)==0: continue
         if not chunk.startswith('data:'): 
             error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
             else:
                 raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
-        if 'data: [DONE]' in chunk:
-            break  # api2d 正常完成
+        if ('data: [DONE]' in chunk): break # api2d 正常完成
         json_data = json.loads(chunk.lstrip('data:'))['choices'][0]
         delta = json_data["delta"]
-        if len(delta) == 0:
-            break
-        if "role" in delta:
-            continue
+        if len(delta) == 0: break
+        if "role" in delta: continue
         if "content" in delta: 
             result += delta["content"]
-            if not console_slience:
-                print(delta["content"], end='')
+            if not console_slience: print(delta["content"], end='')
             if observe_window is not None: 
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1: observe_window[0] += delta["content"]
@@ -117,8 +100,7 @@ def predict_no_ui_long_connection(
                 if len(observe_window) >= 2:  
                     if (time.time()-observe_window[1]) > watch_dog_patience:
                         raise RuntimeError("用户取消了程序。")
-        else:
-            raise RuntimeError("意外Json结构："+delta)
+        else: raise RuntimeError("意外Json结构："+delta)
     if json_data['finish_reason'] == 'length':
         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。")
     return result
@@ -246,7 +228,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
                     return
 
-
 def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     """
     整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
@@ -266,19 +247,23 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     messages = [{"role": "system", "content": system_prompt}]
     if conversation_cnt:
         for index in range(0, 2*conversation_cnt, 2):
-            what_i_have_asked = {"role": "user", "content": history[index]}
-            what_gpt_answer = {"role": "assistant", "content": history[index + 1]}
+            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
+                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 = {"role": "user", "content": inputs}
+    what_i_ask_now = {}
+    what_i_ask_now["role"] = "user"
+    what_i_ask_now["content"] = inputs
     messages.append(what_i_ask_now)
 
     payload = {
@@ -293,8 +278,8 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     }
     try:
         print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
-    except Exception as e:
-        print(f'输入中可能存在乱码。抛出异常: {e}')
-    return headers, payload
+    except:
+        print('输入中可能存在乱码。')
+    return headers,payload
 
 

requirements.txt

@@ -1,4 +1,4 @@
-gradio>=3.33.1
+./docs/gradio-3.32.2-py3-none-any.whl
 tiktoken>=0.3.3
 requests[socks]
 transformers
@@ -15,6 +15,4 @@ pymupdf
 openai
 numpy
 arxiv
-rich
-langchain
-zh_langchain
+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

@@ -21,7 +21,6 @@ pj = os.path.join
 ========================================================================
 """
 
-
 class ChatBotWithCookies(list):
     def __init__(self, cookie):
         self._cookies = cookie
@@ -72,13 +71,11 @@ def update_ui(chatbot, history, msg='正常', **kwargs):  # 刷新界面
     assert isinstance(chatbot, ChatBotWithCookies), "在传递chatbot的过程中不要将其丢弃。必要时，可用clear将其清空，然后用for+append循环重新赋值。"
     yield chatbot.get_cookies(), chatbot, history, msg
 
-
 def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
     """
     刷新用户界面
     """
-    if len(chatbot) == 0:
-        chatbot.append(["update_ui_last_msg", lastmsg])
+    if len(chatbot) == 0: chatbot.append(["update_ui_last_msg", lastmsg])
     chatbot[-1] = list(chatbot[-1])
     chatbot[-1][-1] = lastmsg
     yield from update_ui(chatbot=chatbot, history=history)
@@ -86,25 +83,24 @@ def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
 
 
 def trimmed_format_exc():
-    import os
-    import traceback
-    _str = traceback.format_exc()
+    import os, traceback
+    str = traceback.format_exc()
     current_path = os.getcwd()
     replace_path = "."
-    return _str.replace(current_path, replace_path)
-
+    return str.replace(current_path, replace_path)
 
 def CatchException(f):
     """
     装饰器函数，捕捉函数f中的异常并封装到一个生成器中返回，并显示到聊天当中。
     """
+
     @wraps(f)
     def decorated(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT=-1):
         try:
             yield from f(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT)
         except Exception as e:
             from check_proxy import check_proxy
-            # from toolbox import get_conf  # 不需要导入本文件内容
+            from toolbox import get_conf
             proxies, = get_conf('proxies')
             tb_str = '```\n' + trimmed_format_exc() + '```'
             if len(chatbot) == 0:
@@ -112,7 +108,7 @@ def CatchException(f):
                 chatbot.append(["插件调度异常", "异常原因"])
             chatbot[-1] = (chatbot[-1][0],
                            f"[Local Message] 实验性函数调用出错: \n\n{tb_str} \n\n当前代理可用性: \n\n{check_proxy(proxies)}")
-            yield from update_ui(chatbot=chatbot, history=history, msg=f'异常 {e}')  # 刷新界面
+            yield from update_ui(chatbot=chatbot, history=history, msg=f'异常 {e}') # 刷新界面
     return decorated
 
 
@@ -152,7 +148,6 @@ def HotReload(f):
 ========================================================================
 """
 
-
 def get_reduce_token_percent(text):
     """
         * 此函数未来将被弃用
@@ -212,6 +207,8 @@ def regular_txt_to_markdown(text):
     return text
 
 
+
+
 def report_execption(chatbot, history, a, b):
     """
     向chatbot中添加错误信息
@@ -241,7 +238,6 @@ def text_divide_paragraph(text):
         text = "</br>".join(lines)
         return pre + text + suf
 
-
 @lru_cache(maxsize=128) # 使用 lru缓存 加快转换速度
 def markdown_convertion(txt):
     """
@@ -444,7 +440,6 @@ def find_recent_files(directory):
 
     return recent_files
 
-
 def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
     # 将文件复制一份到下载区
     import shutil
@@ -457,7 +452,6 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
         else: current = []
         chatbot._cookies.update({'file_to_promote': [new_path] + current})
 
-
 def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
     """
     当文件被上传时的回调函数
@@ -511,20 +505,17 @@ def on_report_generated(cookies, files, chatbot):
     chatbot.append(['报告如何远程获取？', f'报告已经添加到右侧“文件上传区”（可能处于折叠状态），请查收。{file_links}'])
     return cookies, report_files, chatbot
 
-
 def is_openai_api_key(key):
     API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
     API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{32}$", key)
     return bool(API_MATCH_ORIGINAL) or bool(API_MATCH_AZURE)
 
-
 def is_api2d_key(key):
     if key.startswith('fk') and len(key) == 41:
         return True
     else:
         return False
 
-
 def is_any_api_key(key):
     if ',' in key:
         keys = key.split(',')
@@ -534,7 +525,6 @@ def is_any_api_key(key):
     else:
         return is_openai_api_key(key) or is_api2d_key(key)
 
-
 def what_keys(keys):
     avail_key_list = {'OpenAI Key':0, "API2D Key":0}
     key_list = keys.split(',')
@@ -549,7 +539,6 @@ def what_keys(keys):
 
     return f"检测到： OpenAI Key {avail_key_list['OpenAI Key']} 个，API2D Key {avail_key_list['API2D Key']} 个"
 
-
 def select_api_key(keys, llm_model):
     import random
     avail_key_list = []
@@ -569,7 +558,6 @@ def select_api_key(keys, llm_model):
     api_key = random.choice(avail_key_list) # 随机负载均衡
     return api_key
 
-
 def read_env_variable(arg, default_value):
     """
     环境变量可以是 `GPT_ACADEMIC_CONFIG`(优先)，也可以直接是`CONFIG`
@@ -624,7 +612,6 @@ def read_env_variable(arg, default_value):
     print亮绿(f"[ENV_VAR] 成功读取环境变量{arg}")
     return r
 
-
 @lru_cache(maxsize=128)
 def read_single_conf_with_lru_cache(arg):
     from colorful import print亮红, print亮绿, print亮蓝
@@ -689,7 +676,6 @@ class DummyWith():
     def __exit__(self, exc_type, exc_value, traceback):
         return
 
-
 def run_gradio_in_subpath(demo, auth, port, custom_path):
     """
     把gradio的运行地址更改到指定的二次路径上
@@ -784,7 +770,6 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
 ========================================================================
 """
 
-
 def zip_folder(source_folder, dest_folder, zip_name):
     import zipfile
     import os
@@ -816,7 +801,6 @@ def zip_folder(source_folder, dest_folder, zip_name):
 
     print(f"Zip file created at {zip_file}")
 
-
 def zip_result(folder):
     import time
     t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
@@ -827,7 +811,6 @@ def gen_time_str():
     import time
     return time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
 
-
 class ProxyNetworkActivate():
     """
     这段代码定义了一个名为TempProxy的空上下文管理器, 用于给一小段代码上代理
@@ -847,14 +830,12 @@ class ProxyNetworkActivate():
         if 'HTTPS_PROXY' in os.environ: os.environ.pop('HTTPS_PROXY')
         return
 
-
 def objdump(obj, file='objdump.tmp'):
     import pickle
     with open(file, 'wb+') as f:
         pickle.dump(obj, f)
     return
 
-
 def objload(file='objdump.tmp'):
     import pickle, os
     if not os.path.exists(file):