cf114fad3c
Some checks failed
Deploy to Staging / Build Images (pull_request) Failing after 3m16s
Deploy to Staging / Deploy to Staging (pull_request) Has been skipped
Deploy to Staging / Verify Staging (pull_request) Has been skipped
Deploy to Staging / Notify Staging Ready (pull_request) Has been skipped
Deploy to Staging / Notify Staging Failure (pull_request) Successful in 8s
48 lines
1.7 KiB
Docker
48 lines
1.7 KiB
Docker
# Production Dockerfile for MotoVaultPro OCR Service
|
|
# Uses mirrored base images from Gitea Package Registry
|
|
#
|
|
# Primary engine: PaddleOCR PP-OCRv4 (models baked into image)
|
|
# Backward compat: Tesseract 5.x (optional, via TesseractEngine)
|
|
# Cloud fallback: Google Vision (optional, requires API key at runtime)
|
|
|
|
# Build argument for registry (defaults to Gitea mirrors, falls back to Docker Hub)
|
|
ARG REGISTRY_MIRRORS=git.motovaultpro.com/egullickson/mirrors
|
|
|
|
FROM ${REGISTRY_MIRRORS}/python:3.13-slim
|
|
|
|
# System dependencies
|
|
# - tesseract-ocr/eng: Backward-compatible OCR engine (used by TesseractEngine)
|
|
# - libgomp1: OpenMP runtime required by PaddlePaddle
|
|
# - libheif1/libheif-dev: HEIF image support (iPhone photos)
|
|
# - libglib2.0-0: GLib shared library (OpenCV dependency)
|
|
# - libgl1-mesa-glx: OpenGL runtime (OpenCV cv2 dependency, pulled by PaddleX)
|
|
# - libmagic1: File type detection
|
|
# - curl: Health check endpoint
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
tesseract-ocr \
|
|
tesseract-ocr-eng \
|
|
libgomp1 \
|
|
libheif1 \
|
|
libheif-dev \
|
|
libglib2.0-0 \
|
|
libgl1-mesa-glx \
|
|
libmagic1 \
|
|
curl \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Python dependencies
|
|
WORKDIR /app
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Pre-download PaddleOCR PP-OCRv4 models during build (not at runtime).
|
|
# Models are baked into the image so container starts are fast and
|
|
# no network access is needed at runtime for model download.
|
|
RUN python -c "from paddleocr import PaddleOCR; PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False, show_log=False)" \
|
|
&& echo "PaddleOCR PP-OCRv4 models downloaded and verified"
|
|
|
|
COPY . .
|
|
|
|
EXPOSE 8000
|
|
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
|