43 lines
986 B
Docker
43 lines
986 B
Docker
# LLM Inference API Server
|
|
# Multi-stage build for smaller final image
|
|
|
|
FROM python:3.11.12-slim AS builder
|
|
|
|
# Install uv
|
|
COPY --from=ghcr.io/astral-sh/uv:0.10 /uv /usr/local/bin/uv
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy project files (uv.lock not committed; resolved at build time)
|
|
COPY pyproject.toml README.md ./
|
|
COPY src/ ./src/
|
|
|
|
# Install dependencies
|
|
RUN uv sync --no-dev
|
|
|
|
# Production image
|
|
FROM python:3.11.12-slim
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy virtual environment from builder
|
|
COPY --from=builder /app/.venv /app/.venv
|
|
|
|
# Copy source code
|
|
COPY src/ ./src/
|
|
|
|
# Set environment variables
|
|
ENV PATH="/app/.venv/bin:$PATH"
|
|
ENV PYTHONUNBUFFERED=1
|
|
ENV LLM_HOST=0.0.0.0
|
|
ENV LLM_PORT=14011
|
|
|
|
# Health check (using Python since curl not available in slim image)
|
|
HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
|
|
CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:14011/health')" || exit 1
|
|
|
|
# Expose port
|
|
EXPOSE 14011
|
|
|
|
# Run the server
|
|
CMD ["python", "-m", "llm_inference.cli"]
|