vector-search-api-v1.0.1/Dockerfile

# Multi-stage build for optimized image size
FROM python:3.11-slim as builder

# Set working directory
WORKDIR /app

# Install system dependencies for building
RUN apt-get update && apt-get install -y \
    gcc \
    g++ \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements (Linux-compatible version)
COPY requirements-docker.txt ./requirements.txt

# Upgrade pip and install Python dependencies
RUN pip install --upgrade pip
RUN pip install --no-cache-dir --user -r requirements.txt

# Final stage
FROM python:3.11-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PATH=/root/.local/bin:$PATH

# Set working directory
WORKDIR /app

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

# Copy Python packages from builder
COPY --from=builder /root/.local /root/.local

# Copy application code
COPY app/ ./app/
COPY main.py .
COPY requirements-docker.txt ./requirements.txt
# Copy models configuration file
COPY models_config.yaml .

# Create directories for models and cache (will be mounted as volumes)
RUN mkdir -p /app/models /app/.cache/huggingface

# Set Hugging Face cache directory
ENV HF_HOME=/app/.cache/huggingface
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
ENV SENTENCE_TRANSFORMERS_HOME=/app/.cache/huggingface

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:5200/health || exit 1

# Expose port
EXPOSE 5200

# Run the application
CMD ["python", "main.py"]