Dockerfile.base

# Base stage: Install common dependencies
FROM python:3.10-slim AS base

# Set working directory and environment variables
WORKDIR /usr/src/app
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1

# Copy only requirements files first to leverage Docker cache
COPY pyproject.toml ./

# Install system and Python dependencies in a single layer
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    build-essential \
    gcc \
    libssl-dev && \
    pip install --upgrade pip setuptools setuptools-scm && \
    rm -rf /var/lib/apt/lists/* && \
    rm -rf /root/.cache/pip/*

# Copy project files
COPY . .

# Install base project
RUN pip install -e ./ && \
    rm -rf /root/.cache/pip/*

# Ko stage with minimal dependencies
FROM base AS ko
RUN pip install --no-cache-dir "AutoRAG[ko]" && \
    rm -rf /root/.cache/pip/*
ENTRYPOINT ["python", "-m", "autorag.cli"]

# Dev stage with all development tools
FROM base AS dev
RUN pip install --no-cache-dir \
    -r ./tests/requirements.txt \
    -r ./docs/requirements.txt \
    "AutoRAG[dev]" && \
    rm -rf /root/.cache/pip/*
ENTRYPOINT ["python", "-m", "autorag.cli"]

# Ja stage with Japanese support
FROM base AS ja
RUN pip install --no-cache-dir "AutoRAG[ja]" && \
    rm -rf /root/.cache/pip/*
ENTRYPOINT ["python", "-m", "autorag.cli"]

# API stage with minimal footprint
FROM base AS api
RUN rm -rf \
    ./sample_dataset \
    ./tests \
    ./docs \
    /root/.cache/pip/*
ENTRYPOINT ["python", "-m", "autorag.cli"]

# Parsing stage with OCR support
FROM base AS parsing
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    poppler-utils \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-kor && \
    pip install --no-cache-dir "AutoRAG[parse]" && \
    rm -rf /var/lib/apt/lists/* && \
    rm -rf /root/.cache/pip/*
ENTRYPOINT ["python", "-m", "autorag.cli"]