# syntax=docker/dockerfile:1
# Build as `docker build . -t localgpt`, requires BuildKit.
# Run as `docker run -it --mount src="$HOME/.cache",target=/root/.cache,type=bind --gpus=all localgpt`, requires Nvidia container toolkit.

ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
FROM nvidia/cuda:${CUDA_IMAGE}

RUN apt-get update && apt-get upgrade -y \
    && apt-get install -y git build-essential \
    python3 python3-pip gcc wget \
    ocl-icd-opencl-dev opencl-headers clinfo \
    libclblast-dev libopenblas-dev \
    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.

RUN python3 -m pip install --upgrade pip pytest cmake \
    scikit-build setuptools fastapi uvicorn sse-starlette \
    pydantic-settings starlette-context gradio huggingface_hub hf_transfer

RUN apt-get update && apt-get install -y software-properties-common
RUN apt-get install -y g++-11

ENV CUDA_DOCKER_ARCH=all
ENV LLAMA_CUBLAS=1

# only copy what's needed at every step to optimize layer cache
COPY ./requirements.txt .

# use BuildKit cache mount to drastically reduce redownloading from pip on repeated builds
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install requirements.txt llama-cpp-python

COPY SOURCE_DOCUMENTS ./SOURCE_DOCUMENTS

COPY ingest.py constants.py ./

ARG device_type=cuda
RUN python3 ingest.py --device_type $device_type

COPY . .

ENV device_type=cuda
CMD python3 run_localGPT.py --device_type $device_type