Dockerfile

FROM runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04

# Install Ollama
RUN curl -fsSL https://ollama.com/install.sh | sh

# Set Ollama to listen on all interfaces
ENV OLLAMA_HOST=0.0.0.0

# Expose Ollama port
EXPOSE 11434

# Create a script to start Ollama and pull models
RUN echo '#!/bin/bash\n\
ollama serve &\n\
sleep 5\n\
ollama pull $MODEL\n\
ollama pull $MODEL2\n\
tail -f /dev/null\n\
' > /start.sh && chmod +x /start.sh

# Set the entrypoint to our start script
ENTRYPOINT ["/start.sh"]