Dockerfile

FROM python:3.11-slim

ENV PORT=7860                        \
    PYTHONDONTWRITEBYTECODE=1        \
    PYTHONUNBUFFERED=1               \
    HF_HOME=/app/.cache              \
    TRANSFORMERS_CACHE=/app/.cache   \
    MAX_NEW_TOKENS=1024              \
    MAX_INPUT_LEN=512

ENV MODEL_ID=Qwen/Qwen2.5-1.5B-Instruct

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential curl \
    && rm -rf /var/lib/apt/lists/*

# Torch CPU-only separado (evita baixar 2GB+ da versão CUDA)
RUN pip install --no-cache-dir \
    torch \
    --index-url https://download.pytorch.org/whl/cpu

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY app/ ./app/

RUN useradd -m -u 1000 appuser && \
    mkdir -p /app/.cache && \
    chown -R appuser:appuser /app

USER appuser

EXPOSE 7860
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]