FROM node:20-alpine

# Install system dependencies for PDF and OCR processing
RUN apk add --no-cache \
    poppler-utils \
    tesseract-ocr \
    tesseract-ocr-data-eng \
    tesseract-ocr-data-ind

WORKDIR /app

# Copy package files and install dependencies
COPY package*.json ./
RUN npm ci

# Copy source code and build
COPY . .
RUN npm run build

# HF Spaces uses port 7860
ENV PORT=7860
EXPOSE 7860

CMD ["npm", "start"]