Dockerfile

FROM python:3.10

ENV CUDA_VISIBLE_DEVICES=-1
ARG PIP_NO_CACHE_DIR=1

# Install system dependencies, including Poppler
RUN apt-get update && apt-get install -y poppler-utils && rm -rf /var/lib/apt/lists/*

# Install specific version of numpy for compatibility
RUN pip install numpy==1.26.4

# Install pymongo for MongoDB Operations
RUN pip install pymongo

# Install JsonSchema for JSON Validation
RUN pip install jsonschema

#Install pdf2image dependency
RUN pip install --no-cache-dir pdf2image

# Install paddlepaddle (latest stable version)
RUN pip install paddlepaddle -i https://pypi.org/simple

# Install dependencies
RUN pip install torch==2.1.1 -i https://download.pytorch.org/whl/cpu
RUN pip install transformers fastapi pypdf2 fitz boto3 pillow openai==0.28 setuptools pymupdf python-dotenv uvicorn
# Install libGL (needed for OpenCV)
RUN apt-get update && apt-get install -y libgl1
RUN pip install paddleocr==2.7.0.3 && pip uninstall -y opencv-python opencv-contrib-python && pip install opencv-python

RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user
WORKDIR $HOME/app
RUN mkdir output
COPY --chown=user app.py $HOME/app

CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]