feat: extract OCR worker into separate service
- Remove Python/OCR steps from backend.Dockerfile (builder + runtime) - Remove Python/OCR steps from backend-dev.Dockerfile - Add OCR_BASE_URL env var to both Dockerfiles (http://ocr-worker:8100) - Add ocr-worker service to docker-compose.yml with healthcheck - Add ocr-worker service to docker-compose.dev.yml with healthcheck + port - Update backend depends_on in both compose files to include ocr-worker - Replace OCR_PROJECT_ROOT with OCR_BASE_URL in compose env vars - Remove pip install line from start-dev-container.sh
This commit is contained in:
@@ -11,12 +11,10 @@ FROM node:22-bookworm AS builder
|
||||
|
||||
ARG DEBIAN_MIRROR=mirrors.cloud.tencent.com
|
||||
ARG NPM_REGISTRY=https://registry.npmmirror.com
|
||||
ARG UV_INDEX_URL=https://mirrors.cloud.tencent.com/pypi/simple
|
||||
|
||||
# NOTE: Use HTTP (not HTTPS) for apt mirrors — OrbStack BuildKit cannot verify
|
||||
# TLS certs during build. Apt packages are GPG-signed so HTTP is safe.
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV PIP_INDEX_URL=${UV_INDEX_URL}
|
||||
ENV NPM_CONFIG_REGISTRY=${NPM_REGISTRY}
|
||||
|
||||
WORKDIR /app
|
||||
@@ -28,7 +26,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
|
||||
&& sed -i "s|http://security.debian.org/debian-security|http://${DEBIAN_MIRROR}/debian-security|g" /etc/apt/sources.list.d/debian.sources \
|
||||
&& apt-get update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
python3 python3-pip python3-venv curl ca-certificates tzdata
|
||||
curl ca-certificates tzdata
|
||||
|
||||
# --- Node dependencies (full, including devDeps for postinstall scripts) ---
|
||||
COPY apps/backend/package.json apps/backend/package-lock.json ./
|
||||
@@ -46,34 +44,24 @@ RUN --mount=type=cache,target=/ms-playwright-cache,sharing=locked \
|
||||
npx playwright install --with-deps chromium \
|
||||
&& cp -r /ms-playwright-cache /ms-playwright
|
||||
|
||||
# --- Python venv for OCR worker ---
|
||||
# Use a virtual environment instead of --break-system-packages
|
||||
COPY apps/backend/subservices/ocr-worker/ ./subservices/ocr-worker/
|
||||
RUN python3 -m venv /app/subservices/ocr-worker/.venv \
|
||||
&& /app/subservices/ocr-worker/.venv/bin/pip install --no-cache-dir -U pip \
|
||||
&& /app/subservices/ocr-worker/.venv/bin/pip install --no-cache-dir ./subservices/ocr-worker
|
||||
|
||||
# --- Copy application source ---
|
||||
COPY apps/backend/ ./
|
||||
|
||||
# --------------------------- Runtime Stage -----------------------------------
|
||||
FROM node:22-bookworm-slim AS runtime
|
||||
|
||||
ARG DEBIAN_MIRROR=mirrors.cloud.tencent.com
|
||||
|
||||
# HTTP mirrors — see builder note about OrbStack TLS
|
||||
ENV DEBIAN_FRONTEND=noninteractive
|
||||
ENV TZ=Asia/Shanghai
|
||||
ENV NODE_ENV=production
|
||||
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
|
||||
ENV OCR_PROJECT_ROOT=/app/subservices/ocr-worker
|
||||
ENV OCR_BASE_URL=http://ocr-worker:8100
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# --- Minimal runtime apt packages ---
|
||||
# - curl: health check (docker-compose uses `curl -fsS http://127.0.0.1:3000/health/ready`)
|
||||
# - ca-certificates: TLS for outbound HTTPS calls
|
||||
# - python3: needed by venv (links to system libpython)
|
||||
# - tzdata: timezone data for TZ=Asia/Shanghai
|
||||
# - Chromium runtime libs: minimal set for headless Chromium on slim
|
||||
#
|
||||
@@ -86,7 +74,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
|
||||
--mount=type=cache,target=/var/lib/apt,sharing=locked \
|
||||
apt-get update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
curl ca-certificates python3 tzdata \
|
||||
curl ca-certificates tzdata \
|
||||
libnss3 libnspr4 libdbus-1-3 libatk1.0-0 libatk-bridge2.0-0 \
|
||||
libcups2 libdrm2 libxkbcommon0 libatspi2.0-0 libxcomposite1 \
|
||||
libxdamage1 libxfixes3 libxrandr2 libgbm1 libpango-1.0-0 \
|
||||
@@ -105,10 +93,6 @@ COPY --from=builder /app/src ./src
|
||||
COPY --from=builder /app/config ./config
|
||||
# Playwright browsers
|
||||
COPY --from=builder /ms-playwright /ms-playwright
|
||||
# Python venv for OCR worker (located at .venv inside subservices/ocr-worker)
|
||||
COPY --from=builder /app/subservices/ocr-worker/.venv ./subservices/ocr-worker/.venv
|
||||
COPY --from=builder /app/subservices/ocr-worker/src ./subservices/ocr-worker/src
|
||||
COPY --from=builder /app/subservices/ocr-worker/pyproject.toml ./subservices/ocr-worker/pyproject.toml
|
||||
|
||||
# --- Non-root user for security ---
|
||||
RUN groupadd -g 1001 appuser \
|
||||
|
||||
Reference in New Issue
Block a user