fix: add websocket in handlerToken

Dockerfile

@@ -3,7 +3,6 @@
 # Run as `docker run -it --mount src="$HOME/.cache",target=/root/.cache,type=bind --gpus=all localgpt`, requires Nvidia container toolkit.
 FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
 
-
 RUN apt-get update && apt-get upgrade -y \
     && apt-get install -y git build-essential libpq-dev gcc \
     wget ocl-icd-opencl-dev opencl-headers clinfo \
@@ -11,16 +10,11 @@ RUN apt-get update && apt-get upgrade -y \
     g++-11 make python3 python-is-python3 pip redis \
     && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
 
-WORKDIR /app
-
-RUN mkdir "./cache"
-
 COPY . .
 
 # setting build related env vars
 ENV CUDA_DOCKER_ARCH=all
 ENV LLAMA_CUBLAS=1
-ENV TRANSFORMERS_CACHE="./cache"
 
 # Install depencencies
 RUN python -m pip install --upgrade pip pytest cmake \
@@ -31,16 +25,12 @@ RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
 RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 PIP_ROOT_USER_ACTION=ignore pip install --ignore-installed --timeout 100 -r requirements.txt
 RUN pip install uvicorn
 
+RUN useradd -m -u 1000 user
+USER user
 
+WORKDIR $HOME/app
 
-
-
-# RUN useradd -m -u 1000 user
-# USER user
-
-# WORKDIR $HOME/app
-
-# COPY --chown=user . $HOME/app
+COPY --chown=user . $HOME/app
 
 RUN chmod +x ./run.sh
 

run.sh

@@ -1,5 +1,5 @@
 redis-cli --version
 
-service redis-server start
+nohup redis-server &
 
 uvicorn "main:app" --port 7860 --host 0.0.0.0