Dockerfile

# Use the official Python image as a base
FROM python:3.8-slim

# Install Java for Spark NLP
RUN apt-get update && apt-get install -y openjdk-8-jdk && apt-get clean

# Set Java environment variables
ENV JAVA_HOME="/usr/lib/jvm/java-8-openjdk-amd64"
ENV PATH="$JAVA_HOME/bin:$PATH"

# Install Python dependencies
COPY requirements.txt /app/requirements.txt
RUN pip install --upgrade pip && pip install -r /app/requirements.txt

# Copy application code
COPY . /app
WORKDIR /app

# Expose port for Streamlit
EXPOSE 7860

# Run Streamlit app
CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]