Dockerfile

# Use Python 3.11 for HF Spaces
FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better caching
COPY requirements.txt .

# Install Python dependencies
RUN pip install --upgrade pip
RUN pip install -r requirements.txt

# Copy application code
COPY . .

# Create model cache directory
RUN mkdir -p ./model_cache

# Set environment variables for memory optimization
ENV SENTENCE_TRANSFORMERS_HOME=./model_cache
ENV HF_HOME=./model_cache
ENV TOKENIZERS_PARALLELISM=false
ENV ONNXRUNTIME_DISABLE=1
ENV DISABLE_OPENVINO=1

# Expose port (HF Spaces uses 7860)
EXPOSE 7860

# Run the application with HF Spaces port
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]