Dockerfile

# 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
# # Below is to fix embedding bug as per
# # RUN curl -fsSL https://ollama.com/install.sh | sed 's#https://ollama.com/download#https://github.com/jmorganca/ollama/releases/download/v0.1.29#' | 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=${model}

# Expose the server port
# Use the official Ollama Docker image as the base image
FROM ollama/ollama:latest

RUN apt update && apt install -y python3 && apt install -y python3-pip

RUN pip install litellm
RUN pip install 'litellm[proxy]'

# Create a directory for Ollama data
RUN mkdir -p /.ollama
RUN chmod -R 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"]

# Set the model as an environment variable (this can be overridden)
ENV model=${model}

# Expose the port that Ollama runs on
EXPOSE 7860

# Command to start the Ollama server
CMD ["serve"]