# Base Image
FROM python:3.10-slim

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1

WORKDIR /code

# System Dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    curl \
    libopenblas-dev \
    libomp-dev \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements and install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Hugging Face + model tools
RUN pip install --no-cache-dir huggingface-hub sentencepiece accelerate

# Hugging Face cache environment
ENV HF_HOME=/models/huggingface \
    TRANSFORMERS_CACHE=/models/huggingface \
    HUGGINGFACE_HUB_CACHE=/models/huggingface \
    HF_HUB_CACHE=/models/huggingface

# Created cache dir and set permissions
RUN mkdir -p /models/huggingface && chmod -R 777 /models/huggingface

# Pre-download models at build time (sports predictor specific models)
RUN python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='valhalla/distilbart-mnli-12-1')" \
 && python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='google/flan-t5-base')" \
 && python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='sentence-transformers/all-MiniLM-L6-v2')" \
 && find /models/huggingface -name '*.lock' -delete

# Preload tokenizers (avoid runtime delays)
RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('valhalla/distilbart-mnli-12-1', use_fast=True)" \
 && python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('google/flan-t5-base', use_fast=True)" \
 && python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2', use_fast=True)"

# Copy project files
COPY . .

# Expose FastAPI port
EXPOSE 7860

# Run FastAPI app with uvicorn (1 workers for concurrency)
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]