From 661fe63941c96a2983a34953e05a3cfbad2c1b14 Mon Sep 17 00:00:00 2001 From: binary-husky Date: Sat, 23 Aug 2025 19:11:42 +0800 Subject: [PATCH] opt dockerfiles --- .dockerignore | 6 ++ README.md | 6 +- docs/GithubAction+AllCapacity | 79 ++++++++++++++---------- docs/GithubAction+NoLocal+AudioAssistant | 8 +-- 4 files changed, 57 insertions(+), 42 deletions(-) create mode 100644 .dockerignore diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 00000000..0ee8f55f --- /dev/null +++ b/.dockerignore @@ -0,0 +1,6 @@ +.venv +.github +.vscode +gpt_log +tests +README.md \ No newline at end of file diff --git a/README.md b/README.md index 4e7aaef5..d7468465 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,6 @@ > [!IMPORTANT] -> `master主分支`最新动态(2025.7.31): 新GUI前端，Coming Soon -> `master主分支`最新动态(2025.3.2): 修复大量代码typo / 联网组件支持Jina的api / 增加deepseek-r1支持 -> `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 +> `master主分支`最新动态(2025.8.23): Dockerfile构建效率大幅优化 +> `master主分支`最新动态(2025.7.31): 新GUI前端，Coming Soon > > 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 diff --git a/docs/GithubAction+AllCapacity b/docs/GithubAction+AllCapacity index 00cec29c..3488a1b8 100644 --- a/docs/GithubAction+AllCapacity +++ b/docs/GithubAction+AllCapacity @@ -1,43 +1,56 @@ -# docker build -t gpt-academic-all-capacity -f docs/GithubAction+AllCapacity --network=host --build-arg http_proxy=http://localhost:10881 --build-arg https_proxy=http://localhost:10881 . +# 此Dockerfile适用于“无本地模型”的迷你运行环境构建 +# 如果需要使用chatglm等本地模型或者latex运行依赖，请参考 docker-compose.yml +# - 如何构建: 先修改 `config.py`， 然后 `docker build -t gpt-academic . ` +# - 如何运行(Linux下): `docker run --rm -it --net=host gpt-academic ` +# - 如何运行(其他操作系统，选择任意一个固定端口50923): `docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic ` -# 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3） -FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest -# edge-tts需要的依赖，某些pip包所需的依赖 -RUN apt update && apt install ffmpeg build-essential -y -RUN apt-get install -y fontconfig +FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest AS texlive +FROM ghcr.io/astral-sh/uv:python3.12-bookworm + + +# 非必要步骤，更换pip源 （以下三行，可以删除） +RUN echo '[global]' > /etc/pip.conf && \ + echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \ + echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf + +# 语音输出功能（以下1,2行更换阿里源，第3,4行安装ffmpeg，都可以删除） +RUN sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \ + sed -i 's/security.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \ + apt-get update +RUN apt-get install ffmpeg fontconfig build-essential -y + RUN ln -s /usr/local/texlive/2023/texmf-dist/fonts/truetype /usr/share/fonts/truetype/texlive RUN fc-cache -fv RUN apt-get clean +COPY --from=texlive /usr/local/texlive /usr/local/texlive -# use python3 as the system default python +# 进入工作路径（必要） WORKDIR /gpt -RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8 -# 下载pytorch -RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113 -# 准备pip依赖 -RUN python3 -m pip install openai numpy arxiv rich -RUN python3 -m pip install colorama Markdown pygments pymupdf -RUN python3 -m pip install python-docx moviepy pdfminer -RUN python3 -m pip install zh_langchain==0.2.1 pypinyin -RUN python3 -m pip install rarfile py7zr -RUN python3 -m pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git -# 下载分支 -WORKDIR /gpt -RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git -WORKDIR /gpt/gpt_academic -RUN git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss -RUN python3 -m pip install -r requirements.txt -RUN python3 -m pip install -r request_llms/requirements_moss.txt -RUN python3 -m pip install -r request_llms/requirements_qwen.txt -RUN python3 -m pip install -r request_llms/requirements_chatglm.txt -RUN python3 -m pip install -r request_llms/requirements_newbing.txt -RUN python3 -m pip install nougat-ocr -RUN python3 -m pip cache purge +# 安装大部分依赖，利用缓存加速以后的构建 +COPY requirements.txt ./ +RUN uv venv --python=3.12 +RUN uv pip install --verbose -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ +RUN uv pip install torch --verbose --index-url https://download.pytorch.org/whl/cpu +RUN uv pip install openai numpy arxiv rich colorama Markdown pygments pymupdf python-docx moviepy pdfminer zh_langchain==0.2.1 pypinyin rarfile py7zr nougat-ocr -i https://mirrors.aliyun.com/pypi/simple/ +RUN uv pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy -i https://mirrors.aliyun.com/pypi/simple/ +RUN uv pip install alibabacloud-nls-python-sdk -i https://mirrors.aliyun.com/pypi/simple/ +ENV PATH="/gpt/.venv/bin:$PATH" -# 预热Tiktoken模块 -RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()' +# 装载项目文件，安装剩余依赖（必要） +COPY . . -# 启动 -CMD ["python3", "-u", "main.py"] +RUN uv pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ + +# # 非必要步骤，用于预热模块（可以删除） +RUN python -c 'from check_proxy import warm_up_modules; warm_up_modules()' + +ENV CGO_ENABLED=0 +ENV PATH "/usr/local/texlive/2023/bin/x86_64-linux:$PATH" +ENV PATH "/usr/local/texlive/2024/bin/x86_64-linux:$PATH" +ENV PATH "/usr/local/texlive/2025/bin/x86_64-linux:$PATH" +ENV PATH "/usr/local/texlive/2026/bin/x86_64-linux:$PATH" + +# 启动（必要） +CMD ["bash", "-c", "python main.py"] diff --git a/docs/GithubAction+NoLocal+AudioAssistant b/docs/GithubAction+NoLocal+AudioAssistant index 80b25d93..63996991 100644 --- a/docs/GithubAction+NoLocal+AudioAssistant +++ b/docs/GithubAction+NoLocal+AudioAssistant @@ -24,7 +24,8 @@ WORKDIR /gpt # 安装大部分依赖，利用Docker缓存加速以后的构建 （以下两行，可以删除） COPY requirements.txt ./ RUN uv venv --python=3.12 && uv pip install --verbose -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ -RUN uv venv --python=3.12 && uv pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git +RUN uv venv --python=3.12 && uv pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy RUN uv pip install alibabacloud-nls-python-sdk -i https://mirrors.aliyun.com/pypi/simple/ + ENV PATH="/gpt/.venv/bin:$PATH" RUN python -c 'import loguru' @@ -38,7 +39,4 @@ RUN python -c 'from check_proxy import warm_up_modules; warm_up_modules()' ENV CGO_ENABLED=0 # 启动（必要） -CMD ["bash", "-c", "python main.py"] - -# 启动 -CMD ["python3", "-u", "main.py"] +CMD ["bash", "-c", "python main.py"] \ No newline at end of file