crawl4ai/Dockerfile-version-0

46 lines
1.5 KiB
Plaintext

# Use an official Python runtime as a parent image
FROM python:3.10-slim
# In case you had some weird issues, try this Image
# FROM python:3.10-slim-bookworm as builder
# Set the working directory in the container
WORKDIR /usr/src/app
# Copy the current directory contents into the container at /usr/src/app
COPY . .
# Install dependencies for Chrome and ChromeDriver
RUN apt-get update && apt-get install -y --no-install-recommends \
wget \
xvfb \
unzip \
curl \
gnupg2 \
ca-certificates \
apt-transport-https \
software-properties-common \
&& mkdir -p /etc/apt/keyrings \
&& curl -fsSL https://dl-ssl.google.com/linux/linux_signing_key.pub | gpg --dearmor -o /etc/apt/keyrings/google-linux-signing-keyring.gpg \
&& echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/google-linux-signing-keyring.gpg] http://dl.google.com/linux/chrome/deb/ stable main' | tee /etc/apt/sources.list.d/google-chrome.list \
&& apt-get update \
&& apt-get install -y google-chrome-stable \
&& rm -rf /var/lib/apt/lists/* \
&& apt-get install -y chromium-chromedriver
# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt
RUN pip install spacy torch torchvision torchaudio
# Set display port and dbus env to avoid hanging
ENV DISPLAY=:99
ENV DBUS_SESSION_BUS_ADDRESS=/dev/null
# Make port 80 available to the world outside this container
EXPOSE 80
# Define environment variable
ENV PYTHONUNBUFFERED 1
# Run uvicorn
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--workers", "4"]