Update Dockerfile

Dockerfile

@@ -17,20 +17,21 @@ RUN python3 -m pip install --upgrade pip pytest cmake \
     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 make python3 python-is-python3 pip
+RUN apt-get install -y g++-11
 
 # 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 --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
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install requirements.txt llama-cpp-python
+
 COPY SOURCE_DOCUMENTS ./SOURCE_DOCUMENTS
+
 COPY ingest.py constants.py ./
-# 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=cuda
-RUN --mount=type=cache,target=/root/.cache python ingest.py --device_type $device_type
+RUN python3 ingest.py --device_type $device_type
+
 COPY . .
 ENV device_type=cuda
-CMD python run_localGPT.py --device_type $device_type
+CMD python3 run_localGPT.py --device_type $device_type