Dockerfile

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

WORKDIR /app

# ===============================
# System dependencies + OCR libraries
# ===============================
RUN apt-get update && apt-get install -y --no-install-recommends \
    sqlite3 \
    ca-certificates \
    libgomp1 \
    tesseract-ocr \
    tesseract-ocr-eng \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgl1 \
    build-essential \
    gcc \
    g++ \
    python3-dev \
    && rm -rf /var/lib/apt/lists/*

# Verify Tesseract
RUN tesseract --version

# ===============================
# Python tooling
# ===============================
RUN pip install --no-cache-dir --upgrade pip setuptools wheel

# ===============================
# 🔒 CRITICAL: single dependency layer
# ===============================
RUN pip install --no-cache-dir \
    numpy==1.24.4 \
    pandas==2.0.3 \
    fastapi==0.104.1 \
    uvicorn[standard]==0.24.0 \
    pydantic==2.5.0 \
    scikit-learn==1.6.1 \
    lightgbm==4.1.0 \
    joblib==1.3.2 \
    python-dateutil==2.8.2 \
    filelock==3.13.1 \
    python-multipart==0.0.6 \
    httpx==0.25.2 \
    redis==5.0.1 \
    rq==1.15.1 \
    pdfplumber==0.10.3 \
    PyMuPDF==1.23.8 \
    pytesseract==0.3.10 \
    Pillow==10.1.0 \
    python-magic==0.4.27 \
    requests==2.31.0 \
    python-dotenv==1.0.0 \
    psycopg2-binary==2.9.7 \
    SQLAlchemy==2.0.20 \
    alembic==1.11.1 \
    google-generativeai \
    google-ai-generativelanguage \
    easyocr \
    opencv-python-headless

# ===============================
# Copy application code
# ===============================
COPY . .

# ===============================
# Runtime directories
# ===============================
RUN mkdir -p /app/data/logs /app/data/docs /app/backend/app/db \
    && chmod -R 777 /app/data

# ===============================
# Python package structure
# ===============================
RUN touch backend/__init__.py \
    backend/feature_builder/__init__.py \
    backend/app/__init__.py \
    backend/app/api/__init__.py \
    backend/app/agent/__init__.py \
    backend/app/wrappers/__init__.py \
    backend/app/db/__init__.py \
    backend/ingest/__init__.py

# ===============================
# Verify agent file exists
# ===============================
RUN test -f backend/app/agent/agent_orchestrator.py || \
    (echo "❌ ERROR: agent_orchestrator.py missing" && exit 1)

# ===============================
# Initialize database at build time
# ===============================
RUN echo "🗄️ Initializing database..." && \
    python backend/app/db/db_init.py && \
    echo "✅ Database ready"

# ===============================
# Expose port
# ===============================
EXPOSE 7860

# ===============================
# Startup script
# ===============================
RUN echo '#!/bin/bash\n\
set -e\n\
echo \"🔍 Checking database...\"\n\
python backend/app/db/db_init.py\n\
echo \"✅ Database ready\"\n\
echo \"🚀 Starting application...\"\n\
exec uvicorn app:app --host 0.0.0.0 --port 7860 --timeout-keep-alive 75\n\
' > /app/start.sh && chmod +x /app/start.sh

CMD ["/app/start.sh"]