Dockerfile

# Use Python 3.11 slim image
FROM python:3.11-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

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

# Copy the rest of the application
COPY . .

# Create necessary directories
RUN mkdir -p /app/data/raw /app/data/processed /app/data/vectordb

# Set permissions
RUN chmod -R 755 /app

# Expose port
EXPOSE 8000

# Run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]