MultilingualOCR / Dockerfile
PrathameshRaut's picture
Create Dockerfile
03cb119 verified
Raw
History Blame Contribute Delete
1.17 kB
FROM python:3.10-slim
# poppler-utils β†’ pdf2image (PDF rendering)
# libreoffice β†’ convert Word/PPT/ODT to PDF
# libgl1 β†’ OpenCV dependency used by Surya
RUN apt-get update && apt-get install -y --no-install-recommends \
poppler-utils \
libreoffice \
libgl1 \
libglib2.0-0 \
libsm6 \
libxext6 \
libxrender-dev \
&& rm -rf /var/lib/apt/lists/*
# Non-root user (HF Spaces requirement)
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user PATH=/home/user/.local/bin:$PATH
WORKDIR /home/user/app
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r requirements.txt
COPY --chown=user app.py .
# Pre-download model weights at build time so cold starts are fast
RUN python -c "\
from surya.foundation import FoundationPredictor; \
from surya.recognition import RecognitionPredictor; \
from surya.detection import DetectionPredictor; \
f = FoundationPredictor(); \
RecognitionPredictor(f); \
DetectionPredictor(); \
print('Models pre-downloaded.') \
"
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]