ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Redme and Docker file

Browse Source
This commit is contained in:
unclecode
2024-06-30 00:15:43 +08:00
parent 61ae2de841
commit 7b0979e134
2 changed files with 15 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
Dockerfile
View File

@@ -18,12 +18,11 @@ RUN apt-get update && \
software-properties-common && \
rm -rf /var/lib/apt/lists/*
# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt && \
pip install --no-cache-dir spacy torch onnxruntime uvicorn && \
python -m spacy download en_core_web_sm
# pip install --no-cache-dir spacy torch torchvision torchaudio onnxruntime uvicorn && \
# Copy the application code
COPY . .
# Install Crawl4AI using the local setup.py (which will use the default installation)
RUN pip install --no-cache-dir .
# Install Google Chrome and ChromeDriver
RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - && \
@@ -33,9 +32,6 @@ RUN wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key
wget -O /tmp/chromedriver.zip http://chromedriver.storage.googleapis.com/`curl -sS chromedriver.storage.googleapis.com/LATEST_RELEASE`/chromedriver_linux64.zip && \
unzip /tmp/chromedriver.zip chromedriver -d /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 \
@@ -43,9 +39,6 @@ ENV CHROME_BIN=/usr/bin/google-chrome \
DBUS_SESSION_BUS_ADDRESS=/dev/null \
PYTHONUNBUFFERED=1
# pip install -e .[all]
RUN pip install --no-cache-dir -e .[all]
# Ensure the PATH environment variable includes the location of the installed packages
ENV PATH /opt/conda/bin:$PATH
@@ -53,15 +46,13 @@ ENV PATH /opt/conda/bin:$PATH
EXPOSE 80
# Download models call cli "crawl4ai-download-models"
RUN crawl4ai-download-models
# RUN crawl4ai-download-models
# Instakk mkdocs
# 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"]
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--workers", "4"]