Update Dockerfile

Dockerfile

@@ -17,15 +17,20 @@ RUN apt-get install -y g++-11
 
 ENV TRANSFORMERS_CACHE=/root/.cache
 
-# 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
-COPY SOURCE_DOCUMENTS ./SOURCE_DOCUMENTS
-COPY ingest.py constants.py ./
-
 COPY . .
 
-RUN chmod 777 ./run.sh
+# setting build related env vars
+ENV CUDA_DOCKER_ARCH=all
+ENV LLAMA_CUBLAS=1
+
+# Install depencencies
+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 CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install --timeout 100 -r requirements.txt
+
+RUN chmod +x ./run.sh
 
 CMD ./run.sh