FROM python:3.11-slim

# Install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Install sentencepiece explicitly to fix tokenizer error
RUN pip install --no-cache-dir sentencepiece

# Ensure consistent sklearn version
RUN pip install --no-cache-dir scikit-learn==1.6.1

# Set Hugging Face cache directory to avoid permission issues
ENV TRANSFORMERS_CACHE=/tmp/huggingface

# Copy application code
COPY . /app
WORKDIR /app

# Expose the port for FastAPI
EXPOSE 7860

# Run the FastAPI app using uvicorn
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]