Dockerfile

# Use Python 3.9 slim image for smaller size
FROM python:3.9-slim

# Set working directory
WORKDIR /app

# Install system dependencies required for PDF processing
RUN apt-get update && apt-get install -y \
    build-essential \
    python3-dev \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

# Install Python packages and download models
RUN pip install --no-cache-dir -r requirements.txt && \
    python -m spacy download en_core_web_sm && \
    # Pre-download sentence transformer model
    python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('paraphrase-MiniLM-L6-v2')" && \
    # Create cache directories
    mkdir -p /root/.cache/torch/sentence_transformers && \
    mkdir -p /root/.cache/huggingface

#    
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-mpnet-base-v2')" 
# Copy the script
COPY script.py .

# Create input and output directories with proper permissions
RUN mkdir -p /app/input /app/output && \
    chmod 777 /app/output

# Set environment variable to use local models
ENV HF_DATASETS_OFFLINE=1 \
    TRANSFORMERS_OFFLINE=1 \
    HF_HUB_OFFLINE=1

# Set the entrypoint
ENTRYPOINT ["python", "script.py"]