Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.11-slim

# Set environment variables for Python
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

# Set environment variables for Hugging Face cache
ENV TRANSFORMERS_CACHE=/app/cache \
    HF_HOME=/app/cache
    
ENV MPLCONFIGDIR=/tmp

# Set the working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxrender1 \
    libxext6 \
    file \
    && rm -rf /var/lib/apt/lists/*

#adding the poppler 
RUN apt-get update && apt-get install -y poppler-utils

#adding the poppler 
RUN apt-get update && apt-get install -y tesseract-ocr

# Copy the requirements file into the container at /app
COPY requirements.txt /app/

# Install dependencies 
RUN pip install --no-cache-dir -r requirements.txt

# Create and set permissions for the cache directory
RUN mkdir -p /app/cache /app/VectorDB /app/TableDB /app/uploads /app/nltk_data /nltk_data && \ 
    chmod -R 777 /app/cache /app/VectorDB /app/TableDB /app/uploads /app/nltk_data /nltk_data

# Ensure all relevant directories have the correct permissions
RUN chmod -R 777 /app/VectorDB
RUN chmod -R 777 /app/TableDB
RUN chmod -R 777 /app/uploads
RUN chmod -R 777 /app/nltk_data
RUN chmod -R 777 /nltk_data
RUN chmod -R 777 /app
RUN chmod -R 777 /app/TableDB

# Copy the rest of the application code to /app
COPY . /app/

# Set environment variables for Flask
ENV FLASK_APP=app.py \
    FLASK_ENV=production

# Expose the port the app runs on
EXPOSE 7860

# Command to run the application
CMD ["gunicorn", "-w", "1", "-b", "0.0.0.0:7860", "--timeout", "360", "app:app"]