Update Dockerfile

Dockerfile

@@ -58,7 +58,7 @@ COPY --chown=1000 . ${APPDIR}
 
 # RUN python3.10 -m venv .venv 
 # RUN . .venv/bin/activate
-
+ENV PYTHONPATH=${HOME}/.local/bin:${PYTHONPATH}
 RUN python -m pip install --no-cache-dir -U pip setuptools wheel
 RUN python -m pip install "huggingface-hub" "hf-transfer" "gradio[oauth]>=4.28.0" "gradio_huggingfacehub_search==0.0.7" "APScheduler"
 # RUN deactivate
@@ -68,7 +68,6 @@ RUN python -m pip install "huggingface-hub" "hf-transfer" "gradio[oauth]>=4.28.0
 # RUN OLLAMA_CUSTOM_CPU_DEFS="-DGGML_AVX=on -DGGML_AVX2=on -DGGML_F16C=on -DGGML_FMA=on" go generate ./... --verbose \
     # go build . --verbose \
     # go install . --verbose
-    
 
 RUN git clone https://github.com/ggerganov/llama.cpp
 COPY groups_merged.txt llama.cpp/.
@@ -77,7 +76,6 @@ RUN git pull
 RUN python -m pip install -r requirements.txt
 RUN GGML_CUDA=1 make -j llama-quantize
     
-ENV PYTHONPATH=${HOME}/.local/bin \
 ENV PYTHONUNBUFFERED=1 \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
     GRADIO_ALLOW_FLAGGING=never \