Dockerfile

# ---- Build stage ----
FROM python:3.12-slim AS builder

WORKDIR /app

# Install build deps
COPY pyproject.toml .
RUN pip install --no-cache-dir --prefix=/install .

# ---- Runtime stage ----
FROM python:3.12-slim

LABEL maintainer="locallmq"
LABEL description="Cloud-to-local LLM inference queue with resource-aware scheduling"

WORKDIR /app

# Copy installed packages from builder
COPY --from=builder /install /usr/local

# Copy application code
COPY src/ src/

# Create data directory for SQLite
RUN mkdir -p /data

# Environment defaults
ENV LOCALLMQ_DB_PATH=/data/locallmq.db \
    LOCALLMQ_HOST=0.0.0.0 \
    LOCALLMQ_PORT=8000 \
    LOCALLMQ_OLLAMA_URL=http://ollama:11434 \
    LOCALLMQ_DEFAULT_MODEL=qwen3:8b \
    LOCALLMQ_MAX_QUEUE_SIZE=5 \
    LOCALLMQ_JOB_TIMEOUT=300 \
    LOCALLMQ_MEMORY_PRESSURE_THRESHOLD=80

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/v1/health')" || exit 1

# Single worker — critical for resource management
CMD ["python", "-m", "uvicorn", "locallmq.main:app", \
     "--host", "0.0.0.0", "--port", "8000", "--workers", "1"]