local_llms_fix

Dockerfile

@@ -13,7 +13,7 @@ ENV PATH="/opt/venv/bin:$PATH"
 COPY requirements.txt .
 RUN pip install --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt
-RUN python3 -m pip install llama-cpp-python
+RUN python3 -m pip install llama-cpp-python==0.2.7 --force-reinstall --upgrade --no-cache-dir
 
 RUN python3.10 -c "import nltk; nltk.download('punkt')" && \
   python3.10 -c "import nltk; nltk.download('averaged_perceptron_tagger')"

Dockerfile-gpu

@@ -32,7 +32,7 @@ COPY . .
 ENV CUDA_DOCKER_ARCH=all
 ENV LLAMA_CUBLAS=1
 
-RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python==0.2.7 --force-reinstall --upgrade --no-cache-dir
 
 # Make necessary scripts executable
 RUN chmod +x ./entrypoint.sh ./wait-for-it.sh ./install_tool_dependencies.sh ./entrypoint_celery.sh

docker-compose-gpu.yml

@@ -38,7 +38,7 @@ services:
         reservations:
           devices:
             - driver: nvidia
-              count: 1
+              count: all
               capabilities: [gpu]
   gui:
     build:

requirements.txt

@@ -158,3 +158,4 @@ google-generativeai==0.1.0
 unstructured==0.8.1
 ai21==1.2.6
 typing-extensions==4.5.0
+llama_cpp_python==0.2.7