Dockerfile

FROM python:3.10-slim

# Install system dependencies for Playwright
RUN apt-get update && apt-get install -y \
    curl \
    net-tools \
    wget \
    unzip \
    libglib2.0-0 \
    libnss3 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libxkbcommon0 \
    libxcomposite1 \
    libxdamage1 \
    libxrandr2 \
    libgbm1 \
    libasound2 \
    libcups2 \
    libxfixes3 \
    libpango-1.0-0 \
    libcairo2 \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Create cache directory
RUN mkdir -p /app/cache/pip && \
    chmod -R 777 /app/cache

# Set pip cache directory
ENV XDG_CACHE_HOME=/app/cache/pip
ENV PIP_NO_CACHE_DIR=1

# Copy requirements
COPY requirements.txt .

# Install dependencies
RUN pip install --upgrade pip && \
    pip install -r requirements.txt && \
    pip install tokenizers==0.19.1 && \
    playwright install

# Verify transformers
RUN python -c "import transformers; from transformers import pipeline; print('Transformers pipeline imported successfully, version:', transformers.__version__)" && \
    python -c "import tokenizers; print('Tokenizers imported successfully, version:', tokenizers.__version__)"

# Copy application
COPY . .

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV STREAMLIT_OPT_OUT_OF_USAGE_STATISTICS=true
ENV HF_HOME=/app/cache

# Expose Streamlit port
EXPOSE 8501

# Run Streamlit
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.fileWatcherType=none", "--server.headless=true"]