Dockerfile

FROM pytorch/pytorch:2.1.0-cuda11.8-cudnn8-runtime

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

# Set working directory
WORKDIR /app

# Copy requirements first for better caching
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Create cache directory for models
RUN mkdir -p /app/cache

# Pre-download the model during build
RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('BAAI/bge-large-en-v1.5', cache_folder='/app/cache'); print('Model downloaded successfully')"

# Set environment variables
ENV TRANSFORMERS_CACHE=/app/cache
ENV SENTENCE_TRANSFORMERS_HOME=/app/cache
ENV HF_HOME=/app/cache
ENV CUDA_VISIBLE_DEVICES=0

# Expose port
EXPOSE 7860

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