Merge branch 'master' into frontier

* fix cookie overflow bug

* fix temp issue of o1

* compat bug fix

* support new azure ai key pattern

* support new azure ai key pattern

* allow disable openai proxy in `WHEN_TO_USE_PROXY`

* change padding

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

README.md

@@ -1,11 +1,11 @@
 > [!IMPORTANT]
-> `master主分支`最新动态(2025.2.4): 增加deepseek-r1支持  
+> `master主分支`最新动态(2025.2.4): 增加deepseek-r1支持；增加字体自定义功能  
+> `master主分支`最新动态(2025.2.2): 三分钟快速接入最强qwen2.5-max[视频](https://www.bilibili.com/video/BV1LeFuerEG4)  
 > `frontier开发分支`最新动态(2024.12.9): 更新对话时间线功能，优化xelatex论文翻译  
 > `wiki文档`最新动态(2024.12.5): 更新ollama接入指南  
 >
-> 2025.2.2: 三分钟快速接入最强qwen2.5-max[视频](https://www.bilibili.com/video/BV1LeFuerEG4)  
-> 2025.2.1: 支持自定义字体  
 > 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/drive/folders/14kR-3V-lIbvGxri4AHc8TpiA1fqsw7SK?usp=sharing)的文件服务器  
+> 2024.10.8: 版本3.90加入对llama-index的初步支持，版本3.80加入插件二级菜单功能（详见wiki）  
 > 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)  
 > 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/) 
 > 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
@@ -129,20 +129,20 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
 
 ```mermaid
 flowchart TD
-    A{"安装方法"} --> W1("I 🔑直接运行 (Windows, Linux or MacOS)")
+    A{"安装方法"} --> W1("I. 🔑直接运行 (Windows, Linux or MacOS)")
-    W1 --> W11["1 Python pip包管理依赖"]
+    W1 --> W11["1. Python pip包管理依赖"]
-    W1 --> W12["2 Anaconda包管理依赖（推荐⭐）"]
+    W1 --> W12["2. Anaconda包管理依赖（推荐⭐）"]
 
-    A --> W2["II 🐳使用Docker (Windows, Linux or MacOS)"]
+    A --> W2["II. 🐳使用Docker (Windows, Linux or MacOS)"]
 
-    W2 --> k1["1 部署项目全部能力的大镜像（推荐⭐）"]
+    W2 --> k1["1. 部署项目全部能力的大镜像（推荐⭐）"]
-    W2 --> k2["2 仅在线模型（GPT, GLM4等）镜像"]
+    W2 --> k2["2. 仅在线模型（GPT, GLM4等）镜像"]
-    W2 --> k3["3 在线模型 + Latex的大镜像"]
+    W2 --> k3["3. 在线模型 + Latex的大镜像"]
 
-    A --> W4["IV 🚀其他部署方法"]
+    A --> W4["IV. 🚀其他部署方法"]
-    W4 --> C1["1 Windows/MacOS 一键安装运行脚本（推荐⭐）"]
+    W4 --> C1["1. Windows/MacOS 一键安装运行脚本（推荐⭐）"]
-    W4 --> C2["2 Huggingface, Sealos远程部署"]
+    W4 --> C2["2. Huggingface, Sealos远程部署"]
-    W4 --> C4["3 其他 ..."]
+    W4 --> C4["3. ... 其他 ..."]
 ```
 
 ### 安装方法I：直接运行 (Windows, Linux or MacOS)

config.py

@@ -14,7 +14,7 @@ API_KEY = "在此处填写APIKEY"    # 可同时填写多个API-KEY，用英文
 DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
 
 # [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
-DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
+DEEPSEEK_API_KEY = ""
 
 # [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
 USE_PROXY = False
@@ -91,18 +91,18 @@ AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gsta
 
 FONT = "Theme-Default-Font"
 AVAIL_FONTS = [
-    "默认值(Theme-Default-Font)",
+    "默认值(Theme-Default-Font)", 
-    "宋体(SimSun)",
+    "宋体(SimSun)",  
-    "黑体(SimHei)",
+    "黑体(SimHei)",  
-    "楷体(KaiTi)",
+    "楷体(KaiTi)",  
-    "仿宋(FangSong)",
+    "仿宋(FangSong)",  
     "华文细黑(STHeiti Light)",
-    "华文楷体(STKaiti)",
+    "华文楷体(STKaiti)",  
-    "华文仿宋(STFangsong)",
+    "华文仿宋(STFangsong)",  
-    "华文宋体(STSong)",
+    "华文宋体(STSong)",  
-    "华文中宋(STZhongsong)",
+    "华文中宋(STZhongsong)",  
-    "华文新魏(STXinwei)",
+    "华文新魏(STXinwei)",  
-    "华文隶书(STLiti)",
+    "华文隶书(STLiti)", 
     "思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
     "月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
     "珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",

config_private.py

@@ -1,444 +0,0 @@
-"""
-    以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
-    读取优先级：环境变量 > config_private.py > config.py
-    --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
-    All the following configurations also support using environment variables to override,
-    and the environment variable configuration format can be seen in docker-compose.yml.
-    Configuration reading priority: environment variable > config_private.py > config.py
-"""
-
-# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
-API_KEY = "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"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
-
-# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
-DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
-
-# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
-DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
-
-# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
-USE_PROXY = True
-if USE_PROXY:
-    proxies = {
-        "http":"socks5h://192.168.8.9:1070",  # 再例如  "http":  "http://127.0.0.1:7890",
-        "https":"socks5h://192.168.8.9:1070",  # 再例如  "https": "http://127.0.0.1:7890",
-    }
-else:
-    proxies = None
-DEFAULT_WORKER_NUM = 256
-
-# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
-LLM_MODEL = "gpt-4-32k" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["deepseek-chat", "deepseek-coder", "deepseek-reasoner",
-                    "gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
-                    "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
-                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
-                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
-                    "gemini-1.5-pro", "chatglm3", "chatglm4",
-                    ]
-
-EMBEDDING_MODEL = "text-embedding-3-small"
-
-# --- --- --- ---
-# P.S. 其他可用的模型还包括
-# AVAIL_LLM_MODELS = [
-#   "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
-#   "qianfan", "deepseekcoder",
-#   "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
-#   "qwen-turbo", "qwen-plus", "qwen-local",
-#   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
-#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
-#   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
-#   "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
-#   "deepseek-chat" ,"deepseek-coder",
-#   "gemini-1.5-flash",
-#   "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
-#   "grok-beta",
-# ]
-# --- --- --- ---
-# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
-# 使用"one-api-*","vllm-*","ollama-*","openrouter-*"前缀直接使用非标准方式接入的模型，例如
-# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)","openrouter-openai/gpt-4o-mini","openrouter-openai/chatgpt-4o-latest"]
-# --- --- --- ---
-
-
-# --------------- 以下配置可以优化体验 ---------------
-
-# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
-# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
-# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
-API_URL_REDIRECT = {}
-
-
-# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
-# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
-DEFAULT_WORKER_NUM = 64
-
-
-# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
-# 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
-THEME = "Default"
-AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
-
-FONT = "Theme-Default-Font"
-AVAIL_FONTS = [
-    "默认值(Theme-Default-Font)",
-    "宋体(SimSun)",
-    "黑体(SimHei)",
-    "楷体(KaiTi)",
-    "仿宋(FangSong)",
-    "华文细黑(STHeiti Light)",
-    "华文楷体(STKaiti)",
-    "华文仿宋(STFangsong)",
-    "华文宋体(STSong)",
-    "华文中宋(STZhongsong)",
-    "华文新魏(STXinwei)",
-    "华文隶书(STLiti)",
-    "思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
-    "月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
-    "珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
-    "平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
-    "Helvetica",
-    "ui-sans-serif",
-    "sans-serif",
-    "system-ui"
-]
-
-
-# 默认的系统提示词（system prompt）
-INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
-
-
-# 对话窗的高度 （仅在LAYOUT="TOP-DOWN"时生效）
-CHATBOT_HEIGHT = 1115
-
-
-# 代码高亮
-CODE_HIGHLIGHT = True
-
-
-# 窗口布局
-LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
-
-
-# 暗色模式 / 亮色模式
-DARK_MODE = True
-
-
-# 发送请求到OpenAI后，等待多久判定为超时
-TIMEOUT_SECONDS = 60
-
-
-# 网页的端口, -1代表随机端口
-WEB_PORT = 19998
-
-# 是否自动打开浏览器页面
-AUTO_OPEN_BROWSER = True
-
-
-# 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
-MAX_RETRY = 5
-
-
-# 插件分类默认选项
-DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
-
-
-# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
-MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
-
-
-# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
-# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
-# 也可以是具体的模型路径
-QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
-
-
-# 百度千帆（LLM_MODEL="qianfan"）
-BAIDU_CLOUD_API_KEY = ''
-BAIDU_CLOUD_SECRET_KEY = ''
-BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
-
-
-# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
-CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
-
-# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
-CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
-
-
-# 本地LLM模型如ChatGLM的执行方式 CPU/GPU
-LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
-LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
-
-
-# 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
-
-
-# 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
-# [("username", "password"), ("username2", "password2"), ...]
-AUTHENTICATION = [("van", "L807878712"),("林", "L807878712"),("源", "L807878712"),("欣", "L807878712"),("z", "czh123456789")]
-
-
-# 如果需要在二级路径下运行（常规情况下，不要修改!!）
-# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
-CUSTOM_PATH = "/"
-
-
-# HTTPS 秘钥和证书（不需要修改）
-SSL_KEYFILE = ""
-SSL_CERTFILE = ""
-
-
-# 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
-API_ORG = ""
-
-
-# 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
-SLACK_CLAUDE_BOT_ID = ''
-SLACK_CLAUDE_USER_TOKEN = ''
-
-
-# 如果需要使用AZURE（方法一：单个azure模型部署）详情请见额外文档 docs\use_azure.md
-AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
-AZURE_API_KEY = "填入azure openai api的密钥"    # 建议直接在API_KEY处填写，该选项即将被弃用
-AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.md
-
-
-# 如果需要使用AZURE（方法二：多个azure模型部署+动态切换）详情请见额外文档 docs\use_azure.md
-AZURE_CFG_ARRAY = {}
-
-
-# 阿里云实时语音识别 配置难度较高
-# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
-ENABLE_AUDIO = False
-ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
-ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
-ALIYUN_ACCESSKEY="" # （无需填写）
-ALIYUN_SECRET=""    # （无需填写）
-
-
-# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
-TTS_TYPE = "DISABLE" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
-GPT_SOVITS_URL = ""
-EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
-
-
-# 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
-XFYUN_APPID = "00000000"
-XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
-XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
-
-
-# 接入智谱大模型
-ZHIPUAI_API_KEY = ""
-ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
-
-
-# Claude API KEY
-ANTHROPIC_API_KEY = ""
-
-
-# 月之暗面 API KEY
-MOONSHOT_API_KEY = ""
-
-
-# 零一万物(Yi Model) API KEY
-YIMODEL_API_KEY = ""
-
-
-# 紫东太初大模型 https://ai-maas.wair.ac.cn
-TAICHU_API_KEY = ""
-
-# Grok API KEY
-GROK_API_KEY = ""
-
-# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
-MATHPIX_APPID = ""
-MATHPIX_APPKEY = ""
-
-
-# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
-DOC2X_API_KEY = ""
-
-
-# 自定义API KEY格式
-CUSTOM_API_KEY_PATTERN = ""
-
-
-# Google Gemini API-Key
-GEMINI_API_KEY = ''
-
-
-# HUGGINGFACE的TOKEN，下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
-HUGGINGFACE_ACCESS_TOKEN = "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"
-
-
-# GROBID服务器地址（填写多个可以均衡负载），用于高质量地读取PDF文档
-# 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
-GROBID_URLS = [
-    "https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
-    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
-    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
-]
-
-
-# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
-SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
-
-
-# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
-ALLOW_RESET_CONFIG = False
-
-
-# 在使用AutoGen插件时，是否使用Docker容器运行代码
-AUTOGEN_USE_DOCKER = False
-
-
-# 临时的上传文件夹位置，请尽量不要修改
-PATH_PRIVATE_UPLOAD = "private_upload"
-
-
-# 日志文件夹的位置，请尽量不要修改
-PATH_LOGGING = "gpt_log"
-
-
-# 存储翻译好的arxiv论文的路径，请尽量不要修改
-ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
-
-
-# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
-WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
-                     "Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
-
-
-# 启用插件热加载
-PLUGIN_HOT_RELOAD = False
-
-
-# 自定义按钮的最大数量限制
-NUM_CUSTOM_BASIC_BTN = 4
-
-
-# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
-DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
-
-
-
-"""
---------------- 配置关联关系说明 ---------------
-
-在线大模型配置关联关系示意图
-│
-├── "gpt-3.5-turbo" 等openai模型
-│   ├── API_KEY
-│   ├── CUSTOM_API_KEY_PATTERN（不常用）
-│   ├── API_ORG（不常用）
-│   └── API_URL_REDIRECT（不常用）
-│
-├── "azure-gpt-3.5" 等azure模型（单个azure模型，不需要动态切换）
-│   ├── API_KEY
-│   ├── AZURE_ENDPOINT
-│   ├── AZURE_API_KEY
-│   ├── AZURE_ENGINE
-│   └── API_URL_REDIRECT
-│
-├── "azure-gpt-3.5" 等azure模型（多个azure模型，需要动态切换，高优先级）
-│   └── AZURE_CFG_ARRAY
-│
-├── "spark" 星火认知大模型 spark & sparkv2
-│   ├── XFYUN_APPID
-│   ├── XFYUN_API_SECRET
-│   └── XFYUN_API_KEY
-│
-├── "claude-3-opus-20240229" 等claude模型
-│   └── ANTHROPIC_API_KEY
-│
-├── "stack-claude"
-│   ├── SLACK_CLAUDE_BOT_ID
-│   └── SLACK_CLAUDE_USER_TOKEN
-│
-├── "qianfan" 百度千帆大模型库
-│   ├── BAIDU_CLOUD_QIANFAN_MODEL
-│   ├── BAIDU_CLOUD_API_KEY
-│   └── BAIDU_CLOUD_SECRET_KEY
-│
-├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
-│   └── ZHIPUAI_API_KEY
-│
-├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
-│   └── YIMODEL_API_KEY
-│
-├── "qwen-turbo" 等通义千问大模型
-│   └──  DASHSCOPE_API_KEY
-│
-├── "Gemini"
-│   └──  GEMINI_API_KEY
-│
-└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
-    ├── AVAIL_LLM_MODELS
-    ├── API_KEY
-    └── API_URL_REDIRECT
-
-
-本地大模型示意图
-│
-├── "chatglm4"
-├── "chatglm3"
-├── "chatglm"
-├── "chatglm_onnx"
-├── "chatglmft"
-├── "internlm"
-├── "moss"
-├── "jittorllms_pangualpha"
-├── "jittorllms_llama"
-├── "deepseekcoder"
-├── "qwen-local"
-├──  RWKV的支持见Wiki
-└── "llama2"
-
-
-用户图形界面布局依赖关系示意图
-│
-├── CHATBOT_HEIGHT 对话窗的高度
-├── CODE_HIGHLIGHT 代码高亮
-├── LAYOUT 窗口布局
-├── DARK_MODE 暗色模式 / 亮色模式
-├── DEFAULT_FN_GROUPS 插件分类默认选项
-├── THEME 色彩主题
-├── AUTO_CLEAR_TXT 是否在提交时自动清空输入框
-├── ADD_WAIFU 加一个live2d装饰
-└── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
-
-
-插件在线服务配置依赖关系示意图
-│
-├── 互联网检索
-│   └── SEARXNG_URLS
-│
-├── 语音功能
-│   ├── ENABLE_AUDIO
-│   ├── ALIYUN_TOKEN
-│   ├── ALIYUN_APPKEY
-│   ├── ALIYUN_ACCESSKEY
-│   └── ALIYUN_SECRET
-│
-└── PDF文档精准解析
-    ├── GROBID_URLS
-    ├── MATHPIX_APPID
-    └── MATHPIX_APPKEY
-
-
-"""
-
-
-

crazy_functions/Conversation_To_File.py

@@ -172,7 +172,7 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     user_request    当前用户的请求信息（IP地址等）
     """
     from crazy_functions.crazy_utils import get_files_from_everything
-    success, file_manifest, _ = get_files_from_everything(txt, type='.html')
+    success, file_manifest, _ = get_files_from_everything(txt, type='.html',chatbot=chatbot)
 
     if not success:
         if txt == "": txt = '空空如也的输入栏'

crazy_functions/Latex_Project_Polish.py

@@ -1,3 +1,4 @@
+from shared_utils.fastapi_server import validate_path_safety
 from toolbox import update_ui, trimmed_format_exc, promote_file_to_downloadzone, get_log_folder
 from toolbox import CatchException, report_exception, write_history_to_file, zip_folder
 from loguru import logger
@@ -155,6 +156,7 @@ def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -193,6 +195,7 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -229,6 +232,7 @@ def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")

crazy_functions/Markdown_Translate.py

@@ -1,5 +1,6 @@
 import glob, shutil, os, re
 from loguru import logger
+from shared_utils.fastapi_server import validate_path_safety
 from toolbox import update_ui, trimmed_format_exc, gen_time_str
 from toolbox import CatchException, report_exception, get_log_folder
 from toolbox import write_history_to_file, promote_file_to_downloadzone
@@ -118,7 +119,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 
-def get_files_from_everything(txt, preference=''):
+def get_files_from_everything(txt, preference='', chatbox=None):
     if txt == "": return False, None, None
     success = True
     if txt.startswith('http'):
@@ -146,9 +147,11 @@ def get_files_from_everything(txt, preference=''):
         # 直接给定文件
         file_manifest = [txt]
         project_folder = os.path.dirname(txt)
+        validate_path_safety(project_folder, chatbot.get_user())
     elif os.path.exists(txt):
         # 本地路径，递归搜索
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
         file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.md', recursive=True)]
     else:
         project_folder = None
@@ -177,7 +180,7 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         return
     history = []    # 清空历史，以免输入溢出
 
-    success, file_manifest, project_folder = get_files_from_everything(txt, preference="Github")
+    success, file_manifest, project_folder = get_files_from_everything(txt, preference="Github", chatbox=chatbot)
 
     if not success:
         # 什么都没有

crazy_functions/PDF_Translate.py

@@ -26,7 +26,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
     # 清空历史，以免输入溢出
     history = []
-    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
+    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf', chatbot=chatbot)
 
     # 检测输入参数，如没有给定输入参数，直接退出
     if (not success) and txt == "": txt = '空空如也的输入栏。提示：请先上传文件（把PDF文件拖入对话）。'

crazy_functions/crazy_utils.py

@@ -2,6 +2,7 @@ import os
 import threading
 from loguru import logger
 from shared_utils.char_visual_effect import scolling_visual_effect
+from shared_utils.fastapi_server import validate_path_safety
 from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
 
 def input_clipping(inputs, history, max_token_limit, return_clip_flags=False):
@@ -539,7 +540,7 @@ 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, chatbot=None): # 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：
@@ -551,6 +552,7 @@ def get_files_from_everything(txt, type): # type='.md'
     - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
     - project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
     该函数详细注释已添加，请确认是否满足您的需要。
+    - chatbot 带Cookies的Chatbot类，为实现更多强大的功能做基础
     """
     import glob, os
 
@@ -573,9 +575,13 @@ def get_files_from_everything(txt, type): # type='.md'
         # 直接给定文件
         file_manifest = [txt]
         project_folder = os.path.dirname(txt)
+        if chatbot is not None:
+            validate_path_safety(project_folder, chatbot.get_user())
     elif os.path.exists(txt):
         # 本地路径，递归搜索
         project_folder = txt
+        if chatbot is not None:
+            validate_path_safety(project_folder, chatbot.get_user())
         file_manifest = [f for f in glob.glob(f'{project_folder}/**/*'+type, recursive=True)]
         if len(file_manifest) == 0:
             success = False

crazy_functions/pdf_fns/parse_pdf_via_doc2x.py

@@ -242,9 +242,7 @@ def 解析PDF_DOC2X_单文件(
         extract_archive(file_path=this_file_path, dest_dir=ex_folder)
 
         # edit markdown files
-        success, file_manifest, project_folder = get_files_from_everything(
+        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md', chatbot=chatbot)
-            ex_folder, type=".md"
-        )
         for generated_fp in file_manifest:
             # 修正一些公式问题
             with open(generated_fp, "r", encoding="utf8") as f:

crazy_functions/pdf_fns/parse_word.py

@@ -27,10 +27,10 @@ def extract_text_from_files(txt, chatbot, history):
         return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
 
     #查找输入区内容中的文件
-    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
+    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf', chatbot=chatbot)
-    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
+    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md', chatbot=chatbot)
-    file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
+    file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx', chatbot=chatbot)
-    file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
+    file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc', chatbot=chatbot)
 
     if file_doc:
         excption = "word"

crazy_functions/总结word文档.py

@@ -104,6 +104,8 @@ def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pr
     # 检测输入参数，如没有给定输入参数，直接退出
     if os.path.exists(txt):
         project_folder = txt
+        from shared_utils.fastapi_server import validate_path_safety
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -61,7 +61,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     history = []
 
     from crazy_functions.crazy_utils import get_files_from_everything
-    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
+    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf', chatbot=chatbot)
     if len(file_manifest) > 0:
         # 尝试导入依赖，如果缺少依赖，则给出安装建议
         try:
@@ -73,7 +73,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
                              b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade nougat-ocr tiktoken```。")
             yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
             return
-    success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
+    success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd', chatbot=chatbot)
     success = success or success_mmd
     file_manifest += file_manifest_mmd
     chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);

crazy_functions/理解PDF文档内容.py

@@ -87,6 +87,8 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     # 检测输入参数，如没有给定输入参数，直接退出
     if os.path.exists(txt):
         project_folder = txt
+        from shared_utils.fastapi_server import validate_path_safety
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "":
             txt = '空空如也的输入栏'

crazy_functions/生成函数注释.py

@@ -39,6 +39,8 @@ def 批量生成函数注释(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        from shared_utils.fastapi_server import validate_path_safety
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")

crazy_functions/知识库问答.py

@@ -49,7 +49,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     file_manifest = []
     spl = ["txt", "doc", "docx", "email", "epub", "html", "json", "md", "msg", "pdf", "ppt", "pptx", "rtf"]
     for sp in spl:
-        _, file_manifest_tmp, _ = get_files_from_everything(txt, type=f'.{sp}')
+        _, file_manifest_tmp, _ = get_files_from_everything(txt, type=f'.{sp}', chatbot=chatbot)
         file_manifest += file_manifest_tmp
 
     if len(file_manifest) == 0:

crazy_functions/解析JupyterNotebook.py

@@ -126,6 +126,8 @@ def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     import os
     if os.path.exists(txt):
         project_folder = txt
+        from shared_utils.fastapi_server import validate_path_safety
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "":
             txt = '空空如也的输入栏'

crazy_functions/读文章写摘要.py

@@ -48,6 +48,8 @@ def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        from shared_utils.fastapi_server import validate_path_safety
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")

main.py

@@ -1,7 +1,10 @@
 import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
 
 help_menu_description = \
-"""
+"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
+感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors).
+</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki),
+如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues).
 </br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
 </br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
 </br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
@@ -181,7 +184,7 @@ def main():
         from themes.gui_floating_menu import define_gui_floating_menu
         area_input_secondary, txt2, area_customize, _, resetBtn2, clearBtn2, stopBtn2 = \
             define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
-
+        
         # 浮动时间线定义
         gr.Spark()
 
@@ -214,7 +217,7 @@ def main():
         input_combo_order = ["cookies", "max_length_sl", "md_dropdown", "txt", "txt2", "top_p", "temperature", "chatbot", "history", "system_prompt", "plugin_advanced_arg"]
         output_combo = [cookies, chatbot, history, status]
         predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
-
+        
         # 提交按钮、重置按钮
         multiplex_submit_btn.click(
             None, [multiplex_sel], None, _js="""(multiplex_sel)=>multiplex_function_begin(multiplex_sel)""")

shared_utils/fastapi_server.py

@@ -51,7 +51,7 @@ def validate_path_safety(path_or_url, user):
     from toolbox import get_conf, default_user_name
     from toolbox import FriendlyException
     PATH_PRIVATE_UPLOAD, PATH_LOGGING = get_conf('PATH_PRIVATE_UPLOAD', 'PATH_LOGGING')
-    sensitive_path = None
+    sensitive_path = None   # 必须不能包含 '/'，即不能是多级路径
     path_or_url = os.path.relpath(path_or_url)
     if path_or_url.startswith(PATH_LOGGING):    # 日志文件（按用户划分）
         sensitive_path = PATH_LOGGING

shared_utils/key_pattern_manager.py

@@ -4,7 +4,6 @@ from functools import wraps, lru_cache
 from shared_utils.advanced_markdown_format import format_io
 from shared_utils.config_loader import get_conf as get_conf
 
-
 pj = os.path.join
 default_user_name = 'default_user'
 
@@ -12,11 +11,13 @@ default_user_name = 'default_user'
 openai_regex = re.compile(
     r"sk-[a-zA-Z0-9_-]{48}$|" +
     r"sk-[a-zA-Z0-9_-]{92}$|" +
-    r"sk-proj-[a-zA-Z0-9_-]{48}$|"+
+    r"sk-proj-[a-zA-Z0-9_-]{48}$|" +
-    r"sk-proj-[a-zA-Z0-9_-]{124}$|"+
+    r"sk-proj-[a-zA-Z0-9_-]{124}$|" +
-    r"sk-proj-[a-zA-Z0-9_-]{156}$|"+ #新版apikey位数不匹配故修改此正则表达式
+    r"sk-proj-[a-zA-Z0-9_-]{156}$|" +  #新版apikey位数不匹配故修改此正则表达式
     r"sess-[a-zA-Z0-9]{40}$"
 )
+
+
 def is_openai_api_key(key):
     CUSTOM_API_KEY_PATTERN = get_conf('CUSTOM_API_KEY_PATTERN')
     if len(CUSTOM_API_KEY_PATTERN) != 0:
@@ -27,7 +28,7 @@ def is_openai_api_key(key):
 
 
 def is_azure_api_key(key):
-    API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{32}$", key)
+    API_MATCH_AZURE = re.match(r"^[a-zA-Z0-9]{32}$|^[a-zA-Z0-9]{84}", key)
     return bool(API_MATCH_AZURE)
 
 
@@ -35,10 +36,12 @@ def is_api2d_key(key):
     API_MATCH_API2D = re.match(r"fk[a-zA-Z0-9]{6}-[a-zA-Z0-9]{32}$", key)
     return bool(API_MATCH_API2D)
 
+
 def is_openroute_api_key(key):
     API_MATCH_OPENROUTE = re.match(r"sk-or-v1-[a-zA-Z0-9]{64}$", key)
     return bool(API_MATCH_OPENROUTE)
 
+
 def is_cohere_api_key(key):
     API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{40}$", key)
     return bool(API_MATCH_AZURE)
@@ -101,7 +104,7 @@ def select_api_key(keys, llm_model):
     if llm_model.startswith('cohere-'):
         for k in key_list:
             if is_cohere_api_key(k): avail_key_list.append(k)
-    
+
     if llm_model.startswith('openrouter-'):
         for k in key_list:
             if is_openroute_api_key(k): avail_key_list.append(k)
@@ -109,7 +112,7 @@ def select_api_key(keys, llm_model):
     if len(avail_key_list) == 0:
         raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（左上角更换模型菜单中可切换openai,azure,claude,cohere等请求源）。")
 
-    api_key = random.choice(avail_key_list) # 随机负载均衡
+    api_key = random.choice(avail_key_list)  # 随机负载均衡
     return api_key
 
 
@@ -125,5 +128,5 @@ def select_api_key_for_embed_models(keys, llm_model):
     if len(avail_key_list) == 0:
         raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源。")
 
-    api_key = random.choice(avail_key_list) # 随机负载均衡
+    api_key = random.choice(avail_key_list)  # 随机负载均衡
     return api_key

start.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-GPT_COMMAND="/home/van/.env/python3.12-venv/bin/python main.py"
-LOG_FILE="/home/van/project/gpt/gpt.log"
-GPT_PROCESS=$(ps aux | grep "$/home/van/.env/python3.12-venv/bin/python main.py" | grep -v grep)
-if [ -n "$GPT_PROCESS" ]; then
-echo "gpt is running..."
-else
-cd /home/van/project/gpt/
-$GPT_COMMAND > "$LOG_FILE" 2>&1 &
-echo "gpt start successfully. Log file: $LOG_FILE"
-fi

toolbox.py

@@ -499,6 +499,22 @@ def to_markdown_tabs(head: list, tabs: list, alignment=":---:", column=False, om
 
     return tabs_list
 
+def validate_file_size(files, max_size_mb=500):
+    """
+    验证文件大小是否在允许范围内。
+    :param files: 文件的完整路径的列表
+    :param max_size_mb: 最大文件大小，单位为MB（默认500MB）
+    :return: True 如果文件大小有效，否则抛出异常
+    """
+    # 获取文件大小（字节）
+    total_size = 0
+    max_size_bytes = max_size_mb * 1024 * 1024
+    for file in files:
+        total_size  += os.path.getsize(file.name)
+        if total_size > max_size_bytes:
+            raise ValueError(f"File size exceeds the allowed limit of {max_size_mb} MB. "
+                            f"Current size: {total_size / (1024 * 1024):.2f} MB")
+    return True
 
 def on_file_uploaded(
     request: gradio.Request, files:List[str], chatbot:ChatBotWithCookies,
@@ -510,6 +526,7 @@ def on_file_uploaded(
     if len(files) == 0:
         return chatbot, txt
 
+    validate_file_size(files, max_size_mb=500)
     # 创建工作路径
     user_name = default_user_name if not request.username else request.username
     time_tag = gen_time_str()