edb72e9aba
New llm FastAPI service (src/llm/api.py + rag.py + web/chat.html): grounded streaming chat over indexed comments with cited sources. Own image, compose service, Traefik reef entry with git-sso, llm subdomain registered. Dashboard tile + README row. stack llm serve CLI.
33 lines
1.0 KiB
Docker
33 lines
1.0 KiB
Docker
# syntax=docker/dockerfile:1
|
|
FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
|
|
|
|
WORKDIR /app
|
|
|
|
# Local package registry (Gitea) — set via --build-arg to pull from mirror
|
|
ARG PYPI_INDEX_URL=""
|
|
|
|
# Patch base image CVEs + install curl for the healthcheck.
|
|
RUN apt-get update && apt-get upgrade -y && apt-get install -y --no-install-recommends curl && rm -rf /var/lib/apt/lists/*
|
|
|
|
COPY pyproject.toml uv.lock README.md ./
|
|
COPY src/ src/
|
|
|
|
# The chat service needs the `llm` extra (fastapi/uvicorn/langchain/pgvector).
|
|
ENV UV_PYTHON_PREFERENCE=only-system \
|
|
UV_LINK_MODE=copy \
|
|
UV_PROJECT_ENVIRONMENT=.venv \
|
|
UV_INDEX_URL=${PYPI_INDEX_URL}
|
|
RUN uv sync --no-dev --extra llm && uv pip install -e .
|
|
|
|
# Config (conf reads stack.toml by walking up from CWD)
|
|
COPY stack.toml ./
|
|
|
|
EXPOSE 8000
|
|
|
|
HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
|
|
CMD curl -sf --max-time 4 http://localhost:8000/health || exit 1
|
|
|
|
CMD ["uv", "run", "--no-sync", "uvicorn", "llm.api:app", \
|
|
"--host", "0.0.0.0", "--port", "8000", \
|
|
"--workers", "1", "--log-level", "info"]
|