Update Dockerfile

Dockerfile

@@ -2,40 +2,22 @@
 # 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
-
+FROM nvidia/cuda:11.7.1-runtime-ubuntu22.04
 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
-
+RUN apt-get install -y g++-11 make python3 python-is-python3 pip
 # 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
-
+RUN --mount=type=cache,target=/root/.cache CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --timeout 100 -r requirements.txt llama-cpp-python==0.1.83
 COPY SOURCE_DOCUMENTS ./SOURCE_DOCUMENTS
-
 COPY ingest.py constants.py ./
-
-ARG device_type=cuda
-RUN python3 ingest.py --device_type $device_type
+# Docker BuildKit does not support GPU during *docker build* time right now, only during *docker run*.
+# See <https://github.com/moby/buildkit/issues/1436>.
+# If this changes in the future you can `docker build --build-arg device_type=cuda  . -t localgpt` (+GPU argument to be determined).
+ARG device_type=cpu
+RUN --mount=type=cache,target=/root/.cache python ingest.py --device_type $device_type
 
 COPY . .
 
 ENV device_type=cuda
-CMD python3 run_localGPT.py --device_type $device_type
+CMD python run_localGPT.py --device_type $device_type