python-pdf2txt/Dockerfile

FROM python:3.10

# Set the working directory in the container
WORKDIR /app

# Install poppler-utils for pdf2image
RUN apt-get update && apt-get install -y poppler-utils \
  && apt-get -y install tesseract-ocr


# Copy the current directory contents into the container at /app
COPY . /app

# Install any needed packages specified in requirements.txt
RUN pip install -r requirements.txt

# Make port 5000 available to the world outside this container
EXPOSE 5000

# Run app.py when the container launches
CMD ["python", "app.py"]