Dockerfile

FROM python:3.11-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    TRANSFORMERS_NO_TF=1 \
    USE_TF=0 \
    TF_ENABLE_ONEDNN_OPTS=0 \
    TRANSFORMERS_CACHE=/app/.cache/huggingface \
    HF_HOME=/app/.cache/huggingface \
    SENTENCE_TRANSFORMERS_HOME=/app/.cache/sentence-transformers

WORKDIR /app

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

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

# Create cache directories with proper permissions
RUN mkdir -p /app/.cache/huggingface /app/.cache/sentence-transformers \
    && chmod -R 777 /app/.cache

# Pre-download embedding model to avoid runtime errors in HF Spaces
RUN python -c "from sentence_transformers import SentenceTransformer; \
    print('Downloading embedding model...'); \
    model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2'); \
    print('Model cached successfully'); \
    print(f'Model saved to: {model._model_card_vars.get(\"model_name\", \"unknown\")}')"

COPY . .

EXPOSE 7860

CMD ["uvicorn", "orchestrator:app", "--host", "0.0.0.0", "--port", "7860"]