Dockerfile

# =========================
# Base image
# =========================
FROM python:3.10-slim

# =========================
# Set working directory
# =========================
WORKDIR /app

# =========================
# Environment variables
# =========================
ENV MODEL_NAME=prajjwal1/bert-tiny
ENV PYTHONUNBUFFERED=1
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/tessdata

# =========================
# Install system dependencies (no poppler)
# =========================
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    tesseract-ocr \
    libtesseract-dev \
    libleptonica-dev \
    pkg-config \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# =========================
# Copy requirements and install Python packages
# =========================
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip
RUN pip install --no-cache-dir -r requirements.txt

# =========================
# Copy app and model adapter
# =========================
COPY app.py .
COPY lora_adapter ./lora_adapter

# Optional: custom Streamlit config
COPY .streamlit ./.streamlit

# =========================
# Expose Streamlit port
# =========================
EXPOSE 8501

# =========================
# Run the app
# =========================
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]