Dockerfile

# Base image
FROM python:3.12

# Set working directory inside the container
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    libpoppler-cpp-dev \
    wget \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Install PyTorch (CPU version)
RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu

# Install Poetry
RUN pip install --no-cache-dir poetry

# Copy dependency files
COPY poetry.lock pyproject.toml /app/

# Configure Poetry
RUN poetry config virtualenvs.create false

# Install project dependencies using Poetry
RUN poetry install --no-root --no-dev

# Copy the rest of the project files
COPY . /app/

# Set environment variables
ENV PYTHONPATH=/app/src
ENV TOKENIZERS_PARALLELISM=false
ENV TORCH_CPP_LOG_LEVEL=ERROR
ENV PYTORCH_DISABLE_SYSTEM_MONITORING=1

# Set writable cache directory for Hugging Face
ENV HF_HOME=/app/cache

# Create and set permissions for the cache directory
RUN mkdir -p /app/cache && chmod -R 777 /app/cache

# Expose the app's default port
EXPOSE 7860

# Command to start the Gradio app
CMD ["python3", "app.py"]