Dockerfile

# Multi-stage Dockerfile for RAG Terminal Application
# Optimized for production deployment with CPU-only PyTorch

# Stage 1: Builder - Install dependencies
FROM python:3.12-slim AS builder

# Set working directory
WORKDIR /app

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

# Copy requirements file
COPY requirements.txt .

# Create virtual environment and install Python dependencies
RUN python -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Install dependencies with CPU-only PyTorch to save space
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu

# Stage 2: Runtime - Create minimal production image
FROM python:3.12-slim

# Set working directory
WORKDIR /app

# Install runtime dependencies only
RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Copy virtual environment from builder
COPY --from=builder /opt/venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Copy application code
COPY ./app/ .

# Create directories for data persistence
RUN mkdir -p ./rag_data ./.embedding_cache

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV GRADIO_SERVER_NAME=0.0.0.0
ENV GRADIO_SERVER_PORT=7860

# Expose Gradio port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:7860/ || exit 1

# Default command: run the RAG application
CMD ["python", "app.py"]