dgx-spark-playbooks/nvidia/txt2kg/assets/deploy/services/sentence-transformers/Dockerfile
2025-10-06 17:05:41 +00:00

23 lines
647 B
Docker

FROM python:3.9-slim
WORKDIR /app
# Copy requirements and install dependencies first for better caching
COPY requirements.txt /app/
RUN pip install --no-cache-dir -r requirements.txt
# Copy application code
COPY app.py /app/
# Set default model name
ENV MODEL_NAME="all-MiniLM-L6-v2"
ENV TRANSFORMERS_CACHE="/app/.cache"
# Pre-download the model during build for faster startup
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('${MODEL_NAME}')"
# Expose the port
EXPOSE 80
# Use Gunicorn for better performance
CMD ["gunicorn", "--bind", "0.0.0.0:80", "--workers", "1", "--threads", "8", "app:app"]