FROM python:3.11-slim

WORKDIR /app

ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

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

# ZP Wiki je do kontajnera pripájaná ako /zpwiki
RUN git config --system --add safe.directory /zpwiki

# CPU-only PyTorch.
RUN python -m pip install --no-cache-dir \
    torch==2.11.0 \
    --index-url https://download.pytorch.org/whl/cpu

COPY requirements.txt .

RUN python -m pip install --no-cache-dir \
    -r requirements.txt

COPY app ./app
COPY tools ./tools
COPY runtime_assets/ /opt/zp-assets/

ARG EMBEDDING_MODEL=intfloat/multilingual-e5-small
ARG EMBEDDING_REVISION=""
ARG CHUNK_TOKEN_ENCODING=cl100k_base
ARG RAG_LLM_TOKEN_ENCODING=cl100k_base

RUN python -m tools.runtime_assets prepare --output /opt/zp-assets \
    --model "$EMBEDDING_MODEL" --revision "$EMBEDDING_REVISION" \
    --encoding "$CHUNK_TOKEN_ENCODING" --encoding "$RAG_LLM_TOKEN_ENCODING"

ENV ZP_RUNTIME_ASSETS=/opt/zp-assets
ENV ZP_ASSETS_REQUIRED=1
ENV HF_HUB_OFFLINE=1
ENV TRANSFORMERS_OFFLINE=1
ENV TIKTOKEN_CACHE_DIR=/opt/zp-assets/tiktoken

RUN mkdir -p data

EXPOSE 8000

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]