# FROM nvidia/cuda:12.5.1-devel-ubuntu22.04
FROM nvidia/cuda:12.6.3-devel-ubuntu22.04
# FROM julia:latest
# FROM debian:latest


# ------------------------------------------------------------------------------------------------ #
#                                   install required APT packages                                  #
# ------------------------------------------------------------------------------------------------ #
RUN export DEBIAN_FRONTEND=noninteractive && apt-get update && apt-get install -y \
    software-properties-common \
    build-essential \
    busybox \
    g++ \
    gcc \
    wget \
    net-tools \
    curl \
    iputils-ping \
    unzip \
    unixodbc \
    unixodbc-dev \
    libicu-dev \
    nano \
    libmosquitto-dev \
    git \
    git-lfs \
    ffmpeg \
    libsm6 \
    libxext6 \
    tar \
    zip \
    libssl-dev \
    cmake \
    ccache \
    # python3 \
    # python3-pip \
    # python-is-python3 \
    # python3-venv \
    postgresql-client \
    cargo \
    procps

# ------------------------------------------------------------------------------------------------ #
#                                      Set up folder structure                                     #
# ------------------------------------------------------------------------------------------------ #
RUN mkdir /appfolder \
  && mkdir /appfolder/mountvolume \
  && mkdir /appfolder/app \
  && mkdir /appfolder/app/temp
COPY . /appfolder/app/temp
RUN mv /appfolder/app/temp/env_preparation.jl /appfolder/app

# ------------------------------------------------------------------------------------------------ #
#                                       Set up for Julia app                                       #
# ------------------------------------------------------------------------------------------------ #
RUN mkdir /appfolder/julia
WORKDIR /appfolder/julia

    # Option 1) install julia by downloading the tar.gz file directly
# # RUN wget https://julialang-s3.julialang.org/bin/linux/x64/1.11/julia-1.11.3-linux-x86_64.tar.gz
# # RUN wget https://julialang-s3.julialang.org/bin/linux/aarch64/1.11/julia-1.11.3-linux-aarch64.tar.gz

# COPY ./julia-1.11.3-linux-x86_64.tar.gz /appfolder/julia
# #COPY ./julia-1.11.3-linux-aarch64.tar.gz /appfolder/julia

# RUN tar zxvf julia-1.11.3-linux-x86_64.tar.gz
# #RUN tar zxvf julia-1.11.3-linux-aarch64.tar.gz

# RUN rm julia-1.11.3-linux-x86_64.tar.gz
# #RUN rm julia-1.11.3-linux-aarch64.tar.gz

# # add julia executable softlink(symlink) to usr/local/bin to be able to run julia everywhere
# RUN ln -s /appfolder/julia/julia-1.11.3/bin/julia /usr/local/bin
# #RUN echo "alias julia='~/julia/julia-1.11.3/bin/julia'" >> ~/.bashrc && source ~/.bashrc


    # Option 2) install julia by downloading the tar.gz file directly using juliaup
# RUN curl -fsSL https://install.julialang.org | sh -s -- -y
# SHELL ["/bin/bash", "--login" , "-c"]


# ------------------------------------------------------------------------------------------------ #
#                                    Set up for webapp frontend                                    #
# ------------------------------------------------------------------------------------------------ #
# # make folder path according to URL ***assuming root folder is at /appfolder/app as specified in Caddyfile***
# RUN mkdir -p /appfolder/app/hq/agent/sommelier/frontend/user
# COPY . /appfolder/app/hq/agent/sommelier/frontend/user

# -------------------------------------- install web server -------------------------------------- #

    # option 1) NGINX
# RUN apt-get update && apt-get install -y nginx
# COPY nginx.conf /etc/nginx/nginx.conf
# # Copy your static website files to the Nginx HTML directory
# COPY . /usr/share/nginx/html

    # option 2) Caddy
# RUN apt-get update && apt-get install -y caddy

# ---------------------------------------- install backend --------------------------------------- #

    # option 1) nodejs    https://deb.nodesource.com/
# RUN curl -sL https://deb.nodesource.com/setup_20.x | bash - && \
#   apt-get update && apt-get install -y nodejs


# ------------------------------------------------------------------------------------------------ #
#             install Conda as primary python environment with specified python version            #
# ------------------------------------------------------------------------------------------------ #
# WORKDIR /appfolder/app/temp
# RUN PATH="${HOME}/conda/bin:${PATH}" \
#     && wget -O Miniforge3.sh "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh" \
#     && bash Miniforge3.sh -b -p "${HOME}/conda" \
#     && rm -f Miniforge3.sh \
#     && source "${HOME}/conda/etc/profile.d/conda.sh" \
#     && source "${HOME}/conda/etc/profile.d/mamba.sh" \
#     && conda activate \
#     && conda update conda -y \
#     && conda install python=3.11 -y \
#     && conda install pip -y \
#     && pip install --trusted-host pypi.python.org -r /appfolder/app/temp/required_python_packages.txt 
#     # && . /root/.bashrc 

# # add python to path to allow CMD python -m at the last line AND to be able to call python -m at linux shell
# ENV PATH=/root/conda/bin:$PATH

#     # && CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DLLAMA_AVX2=OFF -DLLAMA_F16C=OFF -DLLAMA_FMA=OFF" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir
#     # && CMAKE_ARGS="-DLLAMA_CUBLAS=on -DLLAMA_AVX2=OFF -DLLAMA_F16C=OFF -DLLAMA_FMA=OFF" FORCE_CMAKE=1 pip install llama-cpp-python==0.2.77 --no-cache-dir
# # https://github.com/abetlen/llama-cpp-python/issues/412 old CPU cause CUBLAS compile problem


# ------------------------------------------------------------------------------------------------ #
#                                 install julia package for my app                                 #
# ------------------------------------------------------------------------------------------------ #
WORKDIR /appfolder/app
# RUN julia -t auto env_preparation.jl


# ------------------------------------------------------------------------------------------------ #
#                                        install powershell                                        #
# ------------------------------------------------------------------------------------------------ #
WORKDIR /appfolder/app/temp

    # Option 1) using .deb package 
# RUN wget https://github.com/PowerShell/PowerShell/releases/download/v7.5.0/powershell_7.5.0-1.deb_amd64.deb
# RUN dpkg -i powershell_7.5.0-1.deb_amd64.deb
# RUN apt-get install -f

    # Option 2) using binary package
# https://learn.microsoft.com/en-us/powershell/scripting/install/install-other-linux?view=powershell-7.5
# RUN wget https://github.com/PowerShell/PowerShell/releases/download/v7.5.2/powershell-7.5.2-linux-x64.tar.gz \
#   && mkdir -p /opt/microsoft/powershell/7 \
#   && tar -zxf powershell-7.5.2-linux-x64.tar.gz -C /opt/microsoft/powershell/7 \
#   && chmod +x /opt/microsoft/powershell/7/pwsh \
#   && ln -s /opt/microsoft/powershell/7/pwsh /usr/bin/pwsh
 

# ------------------------------------------------------------------------------------------------ #
#                            remove temp folder after everything is done                           #
# ------------------------------------------------------------------------------------------------ #
WORKDIR /appfolder/app
RUN rm -r /appfolder/app/temp

# Make port 80 available to the world outside this container. If I use --publish at docker run command, there is no need to use EXPOSE
# EXPOSE 1883


# ------------------------------------------------------------------------------------------------ #
#                                      Build llama.cpp with CUDA                                   #
# ------------------------------------------------------------------------------------------------ #
WORKDIR /appfolder/mountvolume/
# clone llama.cpp repo
# RUN git clone https://github.com/ggml-org/llama.cpp

# build llama.cpp (change directory in the same RUN command) didn't work in Dockerfile, I need to sleep the container then get inside
# to build it myself.
# WORKDIR /appfolder/mountvolume/llama.cpp
# RUN cmake -B build -DGGML_CUDA=ON
# RUN cmake --build build --config Release -j


# ------------------------------------------------------------------------------------------------ #
#                                Run app when the container launches                               #
# ------------------------------------------------------------------------------------------------ #
WORKDIR /appfolder/app
# CMD julia --project -t auto main.jl
# CMD ["caddy", "run", "--config", "/appfolder/mountvolume/config/Caddyfile"]
# CMD ["nginx", "-g", "daemon off;"]
# CMD [ "sleep", "infinity" ]
# CMD ["/appfolder/mountvolume/llama.cpp/build/bin/llama-server", "-m", "/appfolder/mountvolume/Tiel-Coder-35B-A3B-UD-IQ3_XXS.gguf", "--host", "0.0.0.0", "--port", "8080"]
# CMD /appfolder/mountvolume/llama.cpp/build/bin/llama-server \
#   -m /appfolder/mountvolume/$MODELFILENAME \
#   $SERVERARGS
CMD ["/appfolder/mountvolume/llama.cpp/build/bin/llama-server", "-m", "/appfolder/mountvolume/Tiel-Coder-35B-A3B-UD-IQ3_XXS.gguf", "--host", "0.0.0.0", "--port", "8080", "--fit-ctx", "204800", "--jinja", "--fit-target", "2048", "--cache-reuse", "256", "--temp", "1.0", "--top-k", "20", "--min-p", "0"]
# CMD ["/appfolder/mountvolume/llama.cpp/build/bin/llama-server", "-m", "/appfolder/mountvolume/gemma-4-E4B-it-qat-UD-Q4_K_XL.gguf", "--mmproj", "/appfolder/mountvolume/gemma-4-E4B-it-qat-UD-Q4_K_XL-mmproj-BF16.gguf", "--jinja", "--chat-template-file", "/appfolder/mountvolume/gemma-4-E4B-chat_template.jinja", "--host", "0.0.0.0", "--port", "8080", "--fit-ctx", "131072", "--fit-target", "2048", "--cache-reuse", "256", "--temp", "1.0", "--top-k", "20", "--min-p", "0"]