ocr / Dockerfile
Beijuka's picture
Upload folder using huggingface_hub
0f922c9 verified
raw
history blame contribute delete
796 Bytes
FROM python:3.10-slim
# Install system packages required for OCR (Tesseract, poppler for PDF tools)
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
tesseract-ocr \
libtesseract-dev \
libleptonica-dev \
pkg-config \
poppler-utils \
build-essential \
git \
&& rm -rf /var/lib/apt/lists/*
# Copy and install Python dependencies
COPY requirements.txt /tmp/requirements.txt
RUN python -m pip install --upgrade pip && \
pip install --no-cache-dir -r /tmp/requirements.txt
# Copy application
COPY . /app
WORKDIR /app
# Expose default port (Spaces will set PORT env var)
ENV PORT=7860
# Run Streamlit app on container start
CMD bash -lc "streamlit run streamlit_app.py --server.port ${PORT} --server.address 0.0.0.0"