Merge branch 'master' of https://github.com/kaixindelele/gpt_academic into chatpaper-master

2023-06-30 12:01:08 +08:00
parent 22f377e2fb 146fde30b8
commit 3f8a145c1d
10 changed files with 164 additions and 226 deletions
--- a/.github/workflows/build-image.yaml
+++ b/.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
--- a/.github/workflows/build-with-chatglm.yml
+++ b/.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 }}
--- a/.github/workflows/build-with-jittorllms.yml
+++ b/.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 }}
--- a/.github/workflows/build-without-local-llms.yml
+++ b/.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 }}
--- a/crazy_functional.py
+++ b/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
@ -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')
-
-    try:
-        from crazy_functions.联网的ChatGPT import 连接网络回答问题
+    from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
    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）": {
+        "ArXiv Latex一键翻译（输入arXiv ID）": {
            "Color": "stop",
-                "AsButton": False,  # 加入下拉菜单中
-                "Function": HotReload(连接网络回答问题)
+            "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)
        }
    })
-        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.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.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
--- a/crazy_functions/Latex输出PDF结果.py
+++ b/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 ------------->
--- a/crazy_functions/latex_utils.py
+++ b/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。}}\\\\" 

--- a/docs/use_azure.md
+++ b/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)
--- a/main.py
+++ b/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
@ -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:
--- a/sites/baidu_stats.html
+++ b/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>