FROM pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime

WORKDIR /app

# Systemberoenden
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-swe \
    tesseract-ocr-eng \
    libgl1-mesa-glx \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

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

# Kopiera kod
COPY modeller/ ./modeller/
COPY traening/ ./traening/
COPY embeddings/ ./embeddings/
COPY dataset/ ./dataset/

# Miljövariabler
ENV PYTHONPATH=/app
ENV VISION_MODEL_DIR=/models
ENV VISION_DATASET_DIR=/data/dataset

VOLUME ["/models", "/data"]

# Default: träna
CMD ["python3", "-m", "traening.trainer"]