Changes made to Docker

Dockerfile

@@ -4,12 +4,6 @@ WORKDIR /code
 
 COPY . .
 
-# Install necessary build tools and dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    cmake \
-    && rm -rf /var/lib/apt/lists/*
-
 RUN pip install --no-cache-dir -r requirements_docker.txt
 
 CMD ["python", "-u", "-m", "server.server", "--host", "0.0.0.0", "--port", "4444", "--reload"]

concept_linking/requirements.txt

@@ -1,9 +1,9 @@
 # Tools
 #Requirements for LlamaServer
--r tools/LlamaServer/requirements.txt
+#-r tools/LlamaServer/requirements.txt
 
 #Requirements for OntologyGraphBuilder
--r tools/OntologyGraphBuilder/requirements.txt
+#-r tools/OntologyGraphBuilder/requirements.txt
 
 # Solutions
 #Requirements for MachineLearning

concept_linking/tools/LlamaServer/Dockerfile

@@ -1,22 +1,26 @@
 # Use python as base image
-FROM python
-
+FROM python:3.11-slim
 # Set the working directory in the container
 WORKDIR /app
 
 # Copy only the necessary files
 COPY llama_cpu_server.py .
 COPY requirements.txt .
 
+#Install necessary build tools and dependencies for running C++(llama_cpp)
+# This can be removed when app is in production and remote llama api server is reliable and used instead of local llama
+# Install dependencies and curl
+RUN apt-get update && apt-get install -y build-essential cmake curl && rm -rf /var/lib/apt/lists/*
+
+
 # Install dependencies
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Check if the model file exists, and if not, download it using the provided function
-RUN python -c "from llama_cpu_server import download_model; download_model('llama-2-7b-chat.Q2_K.gguf', 'https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q2_K.gguf?download=true')"
-
+# Download the model file from the URL if it doesn't exist
+RUN test -e /app/llama-2-7b-chat.Q2_K.gguf || curl -o llama-2-7b-chat.Q2_K.gguf -LJO 'https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q2_K.gguf?download=true'
 
 # Expose port 5000 outside of the container
 EXPOSE 5000
 
 # Run llama_cpu_server.py when the container launches
-CMD ["python", "llama_cpu_server.py"]
+CMD ["python", "-u", "-m", "llama_cpu_server", "--host", "0.0.0.0", "--port", "5000", "--reload"]

concept_linking/tools/LlamaServer/docker-compose.yml

@@ -1,11 +1,9 @@
-version: '3'
-
 services:
   llama-cpu-server:
-    build:
-      context: .
-      dockerfile: Dockerfile
-    ports:
-      - "5000:5000"
+    build: .
+    container_name: llama-server
+    command: python -u -m llama_cpu_server --host 0.0.0.0 --port 5000 --reload
     volumes:
       - ./concept_linking/tools/LlamaServer/llama-2-7b-chat.Q2_K.gguf:/app/concept_linking/tools/LlamaServer/llama-2-7b-chat.Q2_K.gguf
+    ports:
+      - "5000:5000"