feat(ocr): add PaddleOCR GPU Docker image and FastAPI OCR server with entrypoint; implement OCR endpoints and consensus extraction testing

Dockerfile_paddleocr

@@ -0,0 +1,51 @@
+# PaddleOCR GPU Variant
+# OCR processing with NVIDIA GPU support using PaddlePaddle
+FROM paddlepaddle/paddle:3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6
+
+LABEL maintainer="Task Venture Capital GmbH <hello@task.vc>"
+LABEL description="PaddleOCR PP-OCRv4 - GPU optimized"
+LABEL org.opencontainers.image.source="https://code.foss.global/host.today/ht-docker-ai"
+
+# Environment configuration
+ENV OCR_LANGUAGE="en"
+ENV SERVER_PORT="5000"
+ENV SERVER_HOST="0.0.0.0"
+ENV PYTHONUNBUFFERED=1
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+RUN pip install --no-cache-dir \
+    paddleocr \
+    fastapi \
+    uvicorn[standard] \
+    python-multipart \
+    opencv-python-headless \
+    pillow
+
+# Copy server files
+COPY image_support_files/paddleocr-server.py /app/paddleocr-server.py
+COPY image_support_files/paddleocr-entrypoint.sh /usr/local/bin/paddleocr-entrypoint.sh
+RUN chmod +x /usr/local/bin/paddleocr-entrypoint.sh
+
+# Pre-download OCR models during build (PP-OCRv4)
+RUN python -c "from paddleocr import PaddleOCR; \
+    ocr = PaddleOCR(use_angle_cls=True, lang='en', use_gpu=False, show_log=True); \
+    print('English model downloaded')"
+
+# Expose API port
+EXPOSE 5000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:5000/health || exit 1
+
+ENTRYPOINT ["/usr/local/bin/paddleocr-entrypoint.sh"]