Update Dockerfile

Dockerfile

@@ -1,5 +1,7 @@
-FROM ghcr.io/abetlen/llama-cpp-python:latest
+# Using the specified base image that's suited for llama-cpp-python
+FROM ghcr.io/abetlen/llama-cpp-python:latest@sha256:b6d21ff8c4d9baad65e1fa741a0f8c898d68735fff3f3cd777e3f0c6a1839dd4
 
+# Environment variables for model details
 ENV MODEL_NAME="llava-1.6-mistral-7b-gguf"
 ENV DEFAULT_MODEL_FILE="llava-v1.6-mistral-7b.Q3_K_XS.gguf"
 ENV MODEL_USER="cjpais"
@@ -8,42 +10,22 @@ ENV DEFAULT_CLIP_MODEL_FILE="mmproj-model-f16.gguf"
 ENV MODEL_URL="https://huggingface.co/${MODEL_USER}/${MODEL_NAME}/resolve/${DEFAULT_MODEL_BRANCH}/${DEFAULT_MODEL_FILE}"
 ENV CLIP_MODEL_URL="https://huggingface.co/${MODEL_USER}/${MODEL_NAME}/resolve/${DEFAULT_MODEL_BRANCH}/${DEFAULT_CLIP_MODEL_FILE}"
 
-ENV DEBIAN_FRONTEND=noninteractive
-
-RUN apt update && \
-    apt install --no-install-recommends -y build-essential python3 python3-pip wget curl git && \
-    apt clean && rm -rf /var/lib/apt/lists/*
-
+# Set up the working directory
 WORKDIR /app
 
-COPY requirements.txt ./
-
-RUN python3 -m pip install --upgrade pip && \
-    pip install -r requirements.txt
-
-# Downloading the models
-RUN echo ${MODEL_URL} && \
-    wget -O /app/${DEFAULT_MODEL_FILE} ${MODEL_URL} && \
-    echo ${CLIP_MODEL_URL} && \
-    wget -O /app/${DEFAULT_CLIP_MODEL_FILE} ${CLIP_MODEL_URL}
-
-# Creating a non-root user
-#RUN mkdir -p /home/user/app && \
-#    mv /app/${DEFAULT_MODEL_FILE} /home/user/app && \
-#    mv /app/${DEFAULT_CLIP_MODEL_FILE} /home/user/app && \
-#    chown -R user:user /home/user/app
-
-#USER user
-#ENV HOME=/home/user \
-#    PATH=/home/user/.local/bin:$PATH
-
-#WORKDIR $HOME/app
+# Ensure curl is available for downloading the models
+RUN apt-get update && apt-get install -y curl && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
 
-# Copying the rest of your application
-# COPY --chown=user . .
+# Create a directory for the models
+RUN mkdir -p /models
 
-RUN ls -al
+# Download the models
+RUN curl -L "${MODEL_URL}" -o /models/${DEFAULT_MODEL_FILE} && \
+    curl -L "${CLIP_MODEL_URL}" -o /models/${DEFAULT_CLIP_MODEL_FILE}
 
+# Expose the port the server will run on
 EXPOSE 8000
 
-CMD ["python3", "-m", "llama_cpp.server", "--model", "llava-v1.6-mistral-7b.Q3_K_XS.gguf", "--clip_model_path", "mmproj-model-f16.gguf", "--chat_format", "llava-1-5"]
+# Command to run the server, using environment variables for model paths
+CMD ["python3", "-m", "llama_cpp.server", "--model", "/models/llava-v1.6-mistral-7b.Q3_K_XS.gguf", "--clip_model_path", "/models/mmproj-model-f16.gguf", "--chat_format", "llava-1-5"]