Dockerfile.backend

# ============================================================
# ResearchOS Backend Dockerfile - FastAPI + Worker
# @author Color2333
# ============================================================

ARG BASE_REGISTRY=docker.io
FROM ${BASE_REGISTRY}/library/python:3.11-slim

WORKDIR /app

# 默认使用官方 apt 源；如需加速可在构建时传入 APT_MIRROR（如 mirrors.aliyun.com）
ARG APT_MIRROR=
RUN if [ -n "${APT_MIRROR}" ]; then \
      sed -i "s/deb.debian.org/${APT_MIRROR}/g" /etc/apt/sources.list.d/debian.sources 2>/dev/null || true; \
      sed -i "s/deb.debian.org/${APT_MIRROR}/g" /etc/apt/sources.list 2>/dev/null || true; \
    fi

# 安装系统依赖
RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    git \
    poppler-utils \
    sqlite3 \
    && rm -rf /var/lib/apt/lists/*

# 复制项目文件
COPY pyproject.toml constraints.txt ./
COPY packages/ packages/
COPY apps/ apps/
COPY scripts/ scripts/
COPY alembic.ini ./
COPY infra/migrations/ infra/migrations/

# 默认走官方 PyPI，避免部分镜像源返回损坏索引导致构建失败；
# 如需自定义镜像源，仍可在 docker build 时覆盖这些 build args。
ARG PIP_INDEX_URL=https://pypi.org/simple
ARG PIP_EXTRA_INDEX_URL=
ENV PIP_DEFAULT_TIMEOUT=180
ENV PIP_NO_CACHE_DIR=1
ENV PIP_DISABLE_PIP_VERSION_CHECK=1
ENV PIP_INDEX_URL=${PIP_INDEX_URL}
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}

RUN python -m pip install --no-cache-dir --retries 6 --no-build-isolation -c constraints.txt ".[llm,pdf]" \
    && python -m pip install --no-cache-dir --retries 6 -c constraints.txt \
        umap-learn \
        psutil \
        supervisor

# 创建数据目录和日志目录
RUN mkdir -p /app/data/papers /app/data/briefs /app/logs

# 强制设置数据库路径（避免环境变量冲突问题）
ENV DATABASE_URL=sqlite:////app/data/researchos.db
ENV PYTHONUNBUFFERED=1

# 初始化数据库（如果不存在）
RUN python scripts/local_bootstrap.py || true

EXPOSE 8000

HEALTHCHECK --interval=30s --timeout=5s --start-period=40s --retries=3 \
    CMD curl -sf http://localhost:8000/health || exit 1

# 默认命令（可以被 docker-compose 覆盖）
CMD ["python", "-m", "uvicorn", "apps.api.main:app", "--host", "0.0.0.0", "--port", "8000"]