DealDocumentScreening/srv/worker-extract/Dockerfile
2026-08-17 20:49:29 +03:00

44 lines
1.3 KiB
Docker

# syntax=docker/dockerfile:1
# ─── Stage 1: build deps + project into a venv via uv ─────────────────────────
FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim AS builder
ENV UV_COMPILE_BYTECODE=1 \
UV_LINK_MODE=copy \
UV_PYTHON_DOWNLOADS=never \
UV_PROJECT_ENVIRONMENT=/app/.venv
WORKDIR /app
COPY pyproject.toml uv.lock ./
COPY README.md ./
COPY src ./src
# Install only the extract group (core + db/mq/s3/obs + pymupdf/tesseract).
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --frozen --no-default-groups --group extract --no-install-project && \
uv pip install --no-deps .
# ─── Stage 2: runtime with tesseract-ocr + language packs ────────────────────
FROM python:3.13-slim
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
PATH=/app/.venv/bin:$PATH
WORKDIR /app
# Tesseract and Russian/English language data for scanned PDFs; libmagic1
# backs python-magic content sniffing in the extraction factory.
RUN apt-get update && apt-get install -y --no-install-recommends \
tesseract-ocr \
tesseract-ocr-rus \
tesseract-ocr-eng \
fonts-dejavu-core \
libmagic1 \
&& rm -rf /var/lib/apt/lists/*
COPY --from=builder /app/.venv /app/.venv
EXPOSE 9101
CMD ["python", "-m", "contract_check.worker_extract"]