Merge pull request PromtEngineer#549 from marook/add-llama-cpp-to-docker

add llama-cpp-python to Dockerfile

Dockerfile

@@ -8,7 +8,7 @@ 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 --mount=type=cache,target=/root/.cache CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --timeout 100 -r requirements.txt
+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 ./
 # Docker BuildKit does not support GPU during *docker build* time right now, only during *docker run*.