Introduced NEED_MIRROR (#3907)

### What problem does this PR solve?

Introduced NEED_MIRROR

### Type of change

- [x] Refactoring

.github/workflows/tests.yml

@@ -53,11 +53,11 @@ jobs:
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
           sudo docker pull ubuntu:22.04
-          sudo docker build --progress=plain --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
+          sudo docker build --progress=plain --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
 
       - name: Build ragflow:dev
         run: |
-          sudo docker build --progress=plain -f Dockerfile -t infiniflow/ragflow:dev .
+          sudo docker build --progress=plain --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev .
 
       - name: Start ragflow:dev-slim
         run: |

Dockerfile

@@ -3,6 +3,7 @@ FROM ubuntu:22.04 AS base
 USER root
 SHELL ["/bin/bash", "-c"]
 
+ARG NEED_MIRROR=0
 ARG LIGHTEN=0
 ENV LIGHTEN=${LIGHTEN}
 
@@ -16,7 +17,7 @@ RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/huggingface.co
         /huggingface.co/InfiniFlow/deepdoc \
         | tar -xf - --strip-components=3 -C /ragflow/rag/res/deepdoc
 RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/huggingface.co,target=/huggingface.co \
-    if [ "$LIGHTEN" == "0" ]; then \
+    if [ "$LIGHTEN" != "1" ]; then \
         (tar -cf - \
             /huggingface.co/BAAI/bge-large-zh-v1.5 \
             /huggingface.co/BAAI/bge-reranker-v2-m3 \
@@ -35,25 +36,27 @@ RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/,target=/deps
 ENV TIKA_SERVER_JAR="file:///ragflow/tika-server-standard-3.0.0.jar"
 
 # Setup apt
-RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
-    sed -i 's|http://archive.ubuntu.com|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list && \
-    rm -f /etc/apt/apt.conf.d/docker-clean && \
-    echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache && \
-    apt update && apt --no-install-recommends install -y ca-certificates && \
-    rm -rf /var/lib/apt/lists/*
-
 # cv2 requires libGL.so.1
 RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
-    apt update && DEBIAN_FRONTEND=noninteractive apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus default-jdk python3-pip pipx \
+    if [ "$NEED_MIRROR" == "1" ]; then \
-    libatk-bridge2.0-0 libgtk-4-1 libnss3 xdg-utils unzip libgbm-dev wget git nginx libgl1 vim less && \
+        sed -i 's|http://archive.ubuntu.com|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list; \
-    rm -rf /var/lib/apt/lists/*
+    fi; \
+    rm -f /etc/apt/apt.conf.d/docker-clean && \
+    echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache && \
+    apt update && \
+    apt --no-install-recommends install -y ca-certificates && \
+    apt update && \
+    DEBIAN_FRONTEND=noninteractive apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus default-jdk python3-pip pipx \
+    libatk-bridge2.0-0 libgtk-4-1 libnss3 xdg-utils unzip libgbm-dev wget git nginx libgl1 vim less
 
-RUN pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
+RUN if [ "$NEED_MIRROR" == "1" ]; then \
-    pip3 config set global.trusted-host pypi.tuna.tsinghua.edu.cn && \
+        pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
-    pipx install poetry && \
+        pip3 config set global.trusted-host pypi.tuna.tsinghua.edu.cn; \
-    pipx runpip poetry config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && \
+    fi; \
-    pipx runpip poetry config set global.trusted-host pypi.tuna.tsinghua.edu.cn && \
+    pipx install poetry; \
-    /root/.local/bin/poetry self add poetry-plugin-pypi-mirror
+    if [ "$NEED_MIRROR" == "1" ]; then \
+        pipx inject poetry poetry-plugin-pypi-mirror; \
+    fi
 
 ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
 ENV PATH=/root/.local/bin:$PATH
@@ -62,7 +65,6 @@ ENV POETRY_NO_INTERACTION=1
 ENV POETRY_VIRTUALENVS_IN_PROJECT=true
 ENV POETRY_VIRTUALENVS_CREATE=true
 ENV POETRY_REQUESTS_TIMEOUT=15
-ENV POETRY_PYPI_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple/
 
 # nodejs 12.22 on Ubuntu 22.04 is too old
 RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
@@ -70,8 +72,7 @@ RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
     apt purge -y nodejs npm && \
     apt autoremove && \
     apt update && \
-    apt install -y nodejs cargo && \
+    apt install -y nodejs cargo
-    rm -rf /var/lib/apt/lists/*
 
 # Add dependencies of selenium
 RUN --mount=type=bind,from=infiniflow/ragflow_deps:latest,source=/chrome-linux64-121-0-6167-85,target=/chrome-linux64.zip \
@@ -103,6 +104,9 @@ WORKDIR /ragflow
 COPY pyproject.toml poetry.toml poetry.lock ./
 
 RUN --mount=type=cache,id=ragflow_poetry,target=/root/.cache/pypoetry,sharing=locked \
+    if [ "$NEED_MIRROR" == "1" ]; then \
+        export POETRY_PYPI_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple/; \
+    fi; \
     if [ "$LIGHTEN" == "1" ]; then \
         poetry install --no-root; \
     else \

README.md

@@ -289,14 +289,14 @@ docker build -f Dockerfile -t infiniflow/ragflow:dev .
 
 1. Install Poetry, or skip this step if it is already installed:
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
+   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ```
 
 2. Clone the source code and install Python dependencies:
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ~/.local/bin/poetry install --sync --no-root --with=full # install RAGFlow dependent python modules
    ```
 

README_id.md

@@ -264,14 +264,14 @@ docker build -f Dockerfile -t infiniflow/ragflow:dev .
 
 1. Instal Poetry, atau lewati langkah ini jika sudah terinstal:
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
+   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ```
 
 2. Clone kode sumber dan instal dependensi Python:
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ~/.local/bin/poetry install --sync --no-root # install modul python RAGFlow
    ```
 

README_ja.md

@@ -245,14 +245,14 @@ docker build -f Dockerfile -t infiniflow/ragflow:dev .
 
 1. Poetry をインストールする。すでにインストールされている場合は、このステップをスキップしてください:
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
+   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ```
 
 2. ソースコードをクローンし、Python の依存関係をインストールする:
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ~/.local/bin/poetry install --sync --no-root # install RAGFlow dependent python modules
    ```
 

README_ko.md

@@ -247,14 +247,14 @@ docker build -f Dockerfile -t infiniflow/ragflow:dev .
 
 1. Poetry를 설치하거나 이미 설치된 경우 이 단계를 건너뜁니다:
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
+   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ```
 
 2. 소스 코드를 클론하고 Python 의존성을 설치합니다:
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ~/.local/bin/poetry install --sync --no-root # install RAGFlow dependent python modules
    ```
 

README_zh.md

@@ -235,7 +235,7 @@ RAGFlow 默认使用 Elasticsearch 存储文本和向量数据. 如果要切换
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
+docker build --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
 ```
 
 ## 🔧 源码编译 Docker 镜像（包含 embedding 模型）
@@ -245,21 +245,23 @@ docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim
 ```bash
 git clone https://github.com/infiniflow/ragflow.git
 cd ragflow/
-docker build -f Dockerfile -t infiniflow/ragflow:dev .
+docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev .
 ```
 
 ## 🔨 以源代码启动服务
 
 1. 安装 Poetry。如已经安装，可跳过本步骤：  
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
+   pipx inject poetry poetry-plugin-pypi-mirror
+   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
+   export POETRY_PYPI_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple/
    ```
 
 2. 下载源代码并安装 Python 依赖：  
    ```bash
    git clone https://github.com/infiniflow/ragflow.git
    cd ragflow/
-   export POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true
    ~/.local/bin/poetry install --sync --no-root # install RAGFlow dependent python modules
    ```
 

docs/guides/develop/launch_ragflow_from_source.md

@@ -38,7 +38,7 @@ cd ragflow/
 1. Install Poetry:
    
    ```bash
-   curl -sSL https://install.python-poetry.org | python3 -
+   pipx install poetry
    ```
 
 2. Configure Poetry: