b6713870ef
This commit updates the Dockerfile to install Crawl4AI with the specified options. The `INSTALL_OPTION` build argument is used to determine which additional packages to install. If the option is set to "all", all models will be downloaded. If the option is set to "torch", only torch models will be downloaded. If the option is set to "transformer", only transformer models will be downloaded. If no option is specified, the default installation will be used. This change improves the flexibility and customization of the Crawl4AI installation process.
67 lines
2.0 KiB
Docker
67 lines
2.0 KiB
Docker
# First stage: Build and install dependencies
|
|
FROM python:3.10-slim-bookworm
|
|
|
|
# Set the working directory in the container
|
|
WORKDIR /usr/src/app
|
|
|
|
# Define build arguments
|
|
ARG INSTALL_OPTION=default
|
|
|
|
# Install build dependencies
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
wget \
|
|
git \
|
|
curl \
|
|
unzip \
|
|
gnupg \
|
|
xvfb \
|
|
ca-certificates \
|
|
apt-transport-https \
|
|
software-properties-common && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
# Copy the application code
|
|
COPY . .
|
|
|
|
# Install Crawl4AI using the local setup.py with the specified option
|
|
# and download models only for torch, transformer, or all options
|
|
RUN if [ "$INSTALL_OPTION" = "all" ]; then \
|
|
pip install --no-cache-dir .[all] && \
|
|
crawl4ai-download-models; \
|
|
elif [ "$INSTALL_OPTION" = "torch" ]; then \
|
|
pip install --no-cache-dir .[torch] && \
|
|
crawl4ai-download-models; \
|
|
elif [ "$INSTALL_OPTION" = "transformer" ]; then \
|
|
pip install --no-cache-dir .[transformer] && \
|
|
crawl4ai-download-models; \
|
|
else \
|
|
pip install --no-cache-dir .; \
|
|
fi
|
|
|
|
# Install Google Chrome
|
|
RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - && \
|
|
sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google-chrome.list' && \
|
|
apt-get update && \
|
|
apt-get install -y google-chrome-stable
|
|
|
|
# Set environment to use Chrome properly
|
|
ENV CHROME_BIN=/usr/bin/google-chrome \
|
|
DISPLAY=:99 \
|
|
DBUS_SESSION_BUS_ADDRESS=/dev/null \
|
|
PYTHONUNBUFFERED=1
|
|
|
|
# Ensure the PATH environment variable includes the location of the installed packages
|
|
ENV PATH=/opt/conda/bin:$PATH
|
|
|
|
# Make port 80 available to the world outside this container
|
|
EXPOSE 80
|
|
|
|
# Install mkdocs
|
|
RUN pip install mkdocs mkdocs-terminal
|
|
|
|
# Call mkdocs to build the documentation
|
|
RUN mkdocs build
|
|
|
|
# Run uvicorn
|
|
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--workers", "4"] |