Dockerfile

FROM python:3.9-slim

# Set working directory
WORKDIR /app

# Avoid permission and telemetry issues
ENV TRANSFORMERS_CACHE=/app/cache \
    HF_HOME=/app/cache \
    STREAMLIT_HOME=/app/.streamlit \
    XDG_CACHE_HOME=/app/.cache \
    BROWSER_GATHERUSAGESTATS=false \
    HF_HUB_DISABLE_TELEMETRY=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

# Create cache and config directories with proper permissions
RUN mkdir -p $STREAMLIT_HOME $XDG_CACHE_HOME $HF_HOME && \
    chmod -R 777 /app

# Copy requirements and source code
COPY requirements.txt ./requirements.txt
COPY src/ ./src/
COPY src/vectorstore_en_recursive/ ./vectorstore_en_recursive/
COPY src/vectorstore_bn_recursive/ ./vectorstore_bn_recursive/

# Install Python dependencies
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# (Optional) Clear huggingface cache
# RUN huggingface-cli delete-cache || true

# Port to expose
EXPOSE 8501

# Healthcheck (optional but helpful)
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health || exit 1

# Run Streamlit
ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]