Add cuda support.

Dockerfile

@@ -12,6 +12,15 @@ FROM python:3.11.5
 
 RUN echo "\n\n############################################# Dockerfile ######################################\n\n"
 
+## Install CUDA Toolkit (Includes drivers and SDK needed for building llama-cpp-python with CUDA support)
+RUN apt-get update && apt-get install -y software-properties-common && \
+    wget https://developer.download.nvidia.com/compute/cuda/12.3.1/local_installers/cuda-repo-debian12-12-3-local_12.3.1-545.23.08-1_amd64.deb && \
+    dpkg -i cuda-repo-debian12-12-3-local_12.3.1-545.23.08-1_amd64.deb && \
+    cp /var/cuda-repo-debian12-12-3-local/cuda-*-keyring.gpg /usr/share/keyrings/ && \
+    add-apt-repository contrib && \
+    apt-get update && \
+    apt-get -y install cuda-toolkit-12-3 
+
 #ENTRYPOINT ["/app/startup.sh"]
 #RUN apt-get update && \
 #    apt-get install -y libc6 && \
@@ -42,7 +51,12 @@ RUN pip install https://files.pythonhosted.org/packages/13/87/e0cb08c2d4bd7d38ab
 RUN pip show semantic-text-splitter
 
 #RUN pip install llama_cpp_python
-RUN FORCE_CMAKE=1 CMAKE_SYSTEM_PROCESSOR=AMD64 pip install --verbose --no-cache-dir llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+#RUN FORCE_CMAKE=1 CMAKE_SYSTEM_PROCESSOR=AMD64 pip install --verbose --no-cache-dir llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+
+## Install llama-cpp-python with CUDA Support
+RUN CUDACXX=/usr/local/cuda-12/bin/nvcc CMAKE_ARGS="-DGGML_CUDA=on -DCMAKE_CUDA_ARCHITECTURES=all-major" FORCE_CMAKE=1 \
+ pip install llama-cpp-python --no-cache-dir --force-reinstall --upgrade
+#    pip install jupyterlab llama-cpp-python --no-cache-dir --force-reinstall --upgrade
 
 ##############################################################################
 # Install Weaviate