pareshmishra
Initial AI Document Intelligence OCR implementation
8e798a2
Raw History Blame Contribute Delete
1.15 kB
# Multi-stage / Production Dockerfile for AI Document Intelligence OCR on Google Cloud Run
FROM python:3.10-slim
# Prevent Python from writing .pyc files and buffer stdout/stderr
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
PORT=8080
WORKDIR /app
# Install system dependencies for OpenCV, Pillow, PaddleOCR, and ONNX
RUN apt-get update && apt-get install -y --no-install-recommends \
build-essential \
curl \
libgl1 \
libglib2.0-0 \
libgomp1 \
libgstreamer1.0-0 \
&& rm -rf /var/lib/apt/lists/*
# Install python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r requirements.txt
# Copy application source code
COPY src/ ./src/
COPY app.py .
COPY frontend.py .
# Health check probe
HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
CMD curl -f http://localhost:${PORT}/health || exit 1
# Expose container port
EXPOSE 8080
# Run FastAPI with uvicorn listening on $PORT (Google Cloud Run dynamically injects PORT)
CMD ["sh", "-c", "uvicorn app:app --host 0.0.0.0 --port ${PORT:-8080} --workers 1"]