FROM python:3.12-slim

# System deps: pdfplumber, ffmpeg for video audio extraction, build tools
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        curl \
        ffmpeg \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install PyTorch with ROCm support first (big layer, cache it)
RUN pip install --no-cache-dir \
    torch torchvision torchaudio \
    --index-url https://download.pytorch.org/whl/nightly/rocm7.2/

# Install remaining Python dependencies
COPY app/requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY app/ .

# Pre-download the embedding model at build time so startup is fast
RUN python -c "\
from sentence_transformers import SentenceTransformer; \
m = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2'); \
print('Model cached:', m.encode(['test']).shape)"

EXPOSE 8899

VOLUME ["/app/data", "/app/logs"]

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8899", "--log-level", "info"]