Added jdk to happify tika (#3165)

### What problem does this PR solve?

Added jdk to happify tika(https://pypi.org/project/tika/). The image
size become ~400MB bigger. Close #2886

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Dockerfile

@@ -15,13 +15,15 @@ RUN --mount=type=cache,id=ragflow_base_apt,target=/var/cache/apt,sharing=locked
 
 # If you download Python modules too slow, you can use a pip mirror site to speed up apt and poetry
 RUN sed -i 's|http://archive.ubuntu.com|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources
-ENV POETRY_PYPI_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple/
 
 RUN --mount=type=cache,id=ragflow_base_apt,target=/var/cache/apt,sharing=locked \
-    apt update && apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus python3-pip python3-poetry \
-    && pip3 install --user --break-system-packages poetry-plugin-pypi-mirror --index-url https://pypi.tuna.tsinghua.edu.cn/simple/ \
+    apt update && apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus default-jdk python3-pip pipx \
     && rm -rf /var/lib/apt/lists/*
 
+RUN pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && pip3 config set global.trusted-host "pypi.tuna.tsinghua.edu.cn mirrors.pku.edu.cn" && pip3 config set global.extra-index-url "https://mirrors.pku.edu.cn/pypi/web/simple" \
+    && pipx install poetry \
+    && /root/.local/bin/poetry self add poetry-plugin-pypi-mirror
+
 # https://forum.aspose.com/t/aspose-slides-for-net-no-usable-version-of-libssl-found-with-linux-server/271344/13
 # aspose-slides on linux/arm64 is unavailable
 RUN --mount=type=bind,source=libssl1.1_1.1.1f-1ubuntu2_amd64.deb,target=/root/libssl1.1_1.1.1f-1ubuntu2_amd64.deb \
@@ -30,12 +32,13 @@ RUN --mount=type=bind,source=libssl1.1_1.1.1f-1ubuntu2_amd64.deb,target=/root/li
     fi
 
 ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
-
+ENV PATH=/root/.local/bin:$PATH
 # Configure Poetry
 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/
 
 # builder stage
 FROM base AS builder
@@ -57,9 +60,9 @@ COPY pyproject.toml poetry.toml poetry.lock ./
 
 RUN --mount=type=cache,id=ragflow_builder_poetry,target=/root/.cache/pypoetry,sharing=locked \
     if [ "$LIGHTEN" -eq 0 ]; then \
-        poetry install --sync --no-root --with=full; \
+        poetry install --no-root --with=full; \
     else \
-        poetry install --sync --no-root; \
+        poetry install --no-root; \
     fi
 
 # production stage

Dockerfile.slim

@@ -15,26 +15,30 @@ RUN --mount=type=cache,id=ragflow_base_apt,target=/var/cache/apt,sharing=locked
 
 # If you download Python modules too slow, you can use a pip mirror site to speed up apt and poetry
 RUN sed -i 's|http://archive.ubuntu.com|https://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources
-ENV POETRY_PYPI_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple/
 
 RUN --mount=type=cache,id=ragflow_base_apt,target=/var/cache/apt,sharing=locked \
-    apt update && apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus python3-pip python3-poetry \
-    && pip3 install --user --break-system-packages poetry-plugin-pypi-mirror --index-url https://pypi.tuna.tsinghua.edu.cn/simple/ \
+    apt update && apt install -y curl libpython3-dev nginx libglib2.0-0 libglx-mesa0 pkg-config libicu-dev libgdiplus default-jdk python3-pip pipx \
     && rm -rf /var/lib/apt/lists/*
 
+RUN pip3 config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple && pip3 config set global.trusted-host "pypi.tuna.tsinghua.edu.cn mirrors.pku.edu.cn" && pip3 config set global.extra-index-url "https://mirrors.pku.edu.cn/pypi/web/simple" \
+    && pipx install poetry \
+    && /root/.local/bin/poetry self add poetry-plugin-pypi-mirror
+
 # https://forum.aspose.com/t/aspose-slides-for-net-no-usable-version-of-libssl-found-with-linux-server/271344/13
 # aspose-slides on linux/arm64 is unavailable
-RUN if [ "${ARCH}" = "amd64" ]; then \
-        curl -o libssl1.deb http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb && dpkg -i libssl1.deb && rm -f libssl1.deb; \
+RUN --mount=type=bind,source=libssl1.1_1.1.1f-1ubuntu2_amd64.deb,target=/root/libssl1.1_1.1.1f-1ubuntu2_amd64.deb \
+    if [ "${ARCH}" = "amd64" ]; then \
+        dpkg -i /root/libssl1.1_1.1.1f-1ubuntu2_amd64.deb; \
     fi
 
 ENV PYTHONDONTWRITEBYTECODE=1 DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1
-
+ENV PATH=/root/.local/bin:$PATH
 # Configure Poetry
 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/
 
 # builder stage
 FROM base AS builder
@@ -56,9 +60,9 @@ COPY pyproject.toml poetry.toml poetry.lock ./
 
 RUN --mount=type=cache,id=ragflow_builder_poetry,target=/root/.cache/pypoetry,sharing=locked \
     if [ "$LIGHTEN" -eq 0 ]; then \
-        poetry install --sync --no-root --with=full; \
+        poetry install --no-root --with=full; \
     else \
-        poetry install --sync --no-root; \
+        poetry install --no-root; \
     fi
 
 # production stage