Fix docker-compose implementation

Dockerfile

@@ -1,5 +1,5 @@
 # Use Python slim image as base
-FROM python:3.10-slim AS builder
+FROM python:3.10-slim
 
 # Set environment variables
 ENV PYTHONUNBUFFERED=1 \
@@ -9,36 +9,32 @@ ENV PYTHONUNBUFFERED=1 \
 # Create and set working directory
 WORKDIR /app
 
-# Install system dependencies
+# Create non-root user first
+RUN useradd -m -u 1000 appuser
+
+# Install system dependencies including build tools
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential \
     curl \
-    git \
+    build-essential \
     cmake \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy project files
-COPY . .
-
-# Install project in editable mode
-RUN pip install -e .
+# Install pdm
+RUN pip install --no-cache-dir pdm
 
-# Create non-root user
-RUN useradd -m -u 1000 appuser && \
-    chown -R appuser:appuser /app
+# Copy project files and set permissions
+COPY . .
+RUN chown -R appuser:appuser /app && \
+    chmod -R 755 /app
 
 # Switch to non-root user
 USER appuser
 
+# Install dependencies in a virtual environment
+RUN pdm install --prod --no-lock
+
 # Expose Gradio port
 EXPOSE 7860
 
-# Set default environment variables for configuration
-ENV MODEL="meta-llama/Llama-3.1-8B-Instruct" \
-    MAGPIE_PRE_QUERY_TEMPLATE="llama3" \
-    MAX_NUM_TOKENS=2048 \
-    MAX_NUM_ROWS=1000 \
-    DEFAULT_BATCH_SIZE=5
-
-# Start command
-CMD ["python", "-m", "synthetic_dataset_generator"] 
+# Start command using pdm run to use the virtual environment
+CMD ["pdm", "run", "python", "-m", "synthetic_dataset_generator"] 

docker-compose.yml

@@ -5,20 +5,78 @@ services:
     build: .
     ports:
       - "7860:7860"
-    env_file:
-      - .env
-    #volumes:
-    #  - nltk_data:/app/nltk_data
+    env_file: .env
+    networks:
+      - app-network
+    depends_on:
+      ollama:
+        condition: service_healthy
+        required: false
+      argilla:
+        condition: service_healthy
+        required: false
+
+  ollama:
+    image: ollama/ollama:${OLLAMA_HARDWARE:-latest}
+    profiles:
+      - with-ollama
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama_data:/root/.ollama
+    networks:
+      - app-network
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11434/api/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    command: ollama serve
+
+  elasticsearch:
+    image: docker.elastic.co/elasticsearch/elasticsearch:7.17.13
+    environment:
+      - discovery.type=single-node
+      - xpack.security.enabled=false
+    volumes:
+      - es_data:/usr/share/elasticsearch/data
+    networks:
+      - app-network
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9200"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
+  argilla:
+    image: argilla/argilla-server:latest
+    profiles:
+      - with-argilla
+    ports:
+      - "6900:6900"
+    env_file: .env
+    environment:
+      - USERNAME=${ARGILLA_USERNAME}
+      - PASSWORD=${ARGILLA_PASSWORD}
+      - API_KEY=${ARGILLA_API_KEY}
+      - ELASTICSEARCH_URL=http://elasticsearch:9200
+    volumes:
+      - argilla_data:/argilla
+    networks:
+      - app-network
+    depends_on:
+      elasticsearch:
+        condition: service_healthy
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:7860/"]
+      test: ["CMD", "curl", "-f", "http://localhost:6900/api/health"]
       interval: 30s
       timeout: 10s
       retries: 3
-      start_period: 40s
-    restart: unless-stopped
 
 volumes:
-  nltk_data:
+  ollama_data:
+  argilla_data:
+  es_data:
 
 networks:
   app-network: