ollama-server-backend / Dockerfile
thewise's picture
Update Dockerfile
4b182fe verified
raw
history blame
1.25 kB
# Builder stage
FROM ubuntu:latest
# Update packages and install curl and gnupg
RUN apt-get update && apt-get install -y \
curl \
gnupg
# Add NVIDIA package repositories
RUN curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
&& echo "deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://nvidia.github.io/libnvidia-container/stable/deb/ $(. /etc/os-release; echo $UBUNTU_CODENAME) main" > /etc/apt/sources.list.d/nvidia-container-toolkit.list
# Install NVIDIA container toolkit (Check for any updated methods or URLs for Ubuntu jammy)
RUN apt-get update && apt-get install -y nvidia-container-toolkit || true
# Install application
RUN curl https://ollama.ai/install.sh | sh
# Create the directory and give appropriate permissions
RUN mkdir -p /.ollama && chmod 777 /.ollama
WORKDIR /.ollama
# Copy the entry point script
COPY entrypoint.sh /entrypoint.sh
RUN chmod +x /entrypoint.sh
# Set the entry point script as the default command
ENTRYPOINT ["/entrypoint.sh"]
CMD ["ollama", "serve"]
# Set the model as an environment variable (this can be overridden)
ENV model=llama2
# Expose the server port
EXPOSE 7860