Dockerfile

# First stage: Build and install dependencies
FROM python:3.10-slim-bookworm as builder

# Set the working directory in the container
WORKDIR /usr/src/app

# Install build dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    wget \
    curl \
    unzip 

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir spacy torch torchvision torchaudio onnxruntime uvicorn && \
    python -m spacy download en_core_web_sm

# Download and install ChromeDriver
RUN CHROMEDRIVER_VERSION=$(curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE) && \
    wget -N https://chromedriver.storage.googleapis.com/$CHROMEDRIVER_VERSION/chromedriver_linux64.zip -P /tmp && \
    unzip /tmp/chromedriver_linux64.zip -d /tmp && \
    mv /tmp/chromedriver /usr/local/bin/chromedriver && \
    chmod +x /usr/local/bin/chromedriver && \
    rm /tmp/chromedriver_linux64.zip

# Second stage: Create final runtime image
FROM python:3.10-slim-bookworm

# Set the working directory in the container
WORKDIR /usr/src/app

# Install runtime dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    wget \
    git \
    xvfb \
    gnupg2 \
    ca-certificates \
    apt-transport-https \
    software-properties-common && \
    wget -q -O - https://dl.google.com/linux/linux_signing_key.pub | apt-key add - && \
    echo "deb http://dl.google.com/linux/chrome/deb/ stable main" > /etc/apt/sources.list.d/google-chrome.list && \
    apt-get update && \
    apt-get install -y --no-install-recommends google-chrome-stable && \
    rm -rf /var/lib/apt/lists/* /etc/apt/sources.list.d/google-chrome.list

# Copy Chromedriver from the builder stage
COPY --from=builder /usr/local/bin/chromedriver /usr/local/bin/chromedriver

# Copy installed Python packages from builder stage
COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
COPY --from=builder /usr/local/bin /usr/local/bin

# Copy the rest of the application code
COPY . .

# Set environment to use Chrome and ChromeDriver properly
ENV CHROME_BIN=/usr/bin/google-chrome \
    CHROMEDRIVER=/usr/local/bin/chromedriver \
    DISPLAY=:99 \
    DBUS_SESSION_BUS_ADDRESS=/dev/null \
    PYTHONUNBUFFERED=1

# Ensure the PATH environment variable includes the location of the installed packages
ENV PATH /usr/local/bin:$PATH   

# Make port 80 available to the world outside this container
EXPOSE 80

# Run uvicorn
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--workers", "4"]