Update Dockerfile

Dockerfile

@@ -1,13 +1,20 @@
 # Dockerfile
-FROM python:3.11-slim AS builder
+FROM python:3.11-slim
 
-# Set environment variables for Python optimization
+# Set environment variables for Python optimization and Ollama
 ENV PYTHONUNBUFFERED=1 \
     PYTHONDONTWRITEBYTECODE=1 \
-    OLLAMA_MODELS=/home/ollama/.ollama \
-    OLLAMA_HOST=0.0.0.0
+    OLLAMA_HOST=0.0.0.0 \
+    OLLAMA_MODELS=/data/ollama
+
+# Create a non-root user
+RUN useradd -m -u 1000 ollama && \
+    mkdir -p /data/ollama && \
+    chown -R ollama:ollama /data
 
-# Install build dependencies
+WORKDIR /app
+
+# Install system dependencies
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
     curl \
@@ -16,31 +23,14 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/*
 
 # Install Ollama
-RUN curl -fsSL https://ollama.ai/install.sh | sh
-
-# Final stage
-FROM python:3.11-slim
-
-# Create a non-root user
-RUN useradd -m -u 1000 ollama && \
-    mkdir -p /home/ollama/.ollama && \
-    chown -R ollama:ollama /home/ollama
-
-WORKDIR /app
-
-# Create logs directory
-RUN mkdir -p /app/logs && \
-    chown -R ollama:ollama /app/logs
-
-# Copy Ollama binaries from builder stage
-COPY --from=builder /usr/local/bin/ollama /usr/local/bin/ollama
+RUN curl -fsSL https://ollama.com/install.sh | sh
 
 # Copy requirements and install Python dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application code
-COPY . .
+COPY app.py .
 
 # Set proper ownership and permissions
 RUN chown -R ollama:ollama /app && \
@@ -49,15 +39,15 @@ RUN chown -R ollama:ollama /app && \
 # Switch to ollama user
 USER ollama
 
-# Create a startup script with configurable model pulling and enhanced logging
+# Create a startup script with configurable model pulling and logging
 RUN echo '#!/bin/bash\n\
 set -e\n\
-LOG_FILE=/app/logs/startup.log\n\
-mkdir -p /app/logs\n\
+LOG_FILE=/data/startup.log\n\
+mkdir -p /data && touch $LOG_FILE && chmod 644 $LOG_FILE\n\
 echo "Starting Ollama server at $(date)" >> $LOG_FILE\n\
 ollama serve >> $LOG_FILE 2>&1 &\n\
 sleep 15\n\
-MODELS_TO_PULL="${MODELS_TO_PULL:-hf.co/gguf-org/gemma-3-270m-gguf:Q5_K_S}"\n\
+MODELS_TO_PULL="${MODELS_TO_PULL:-gemma-3-270m}"\n\
 echo "Pulling models: $MODELS_TO_PULL" | tee -a $LOG_FILE\n\
 IFS=',' read -ra MODEL_ARRAY <<< "$MODELS_TO_PULL"\n\
 for model in "${MODEL_ARRAY[@]}"; do\n\
@@ -77,13 +67,13 @@ for model in "${MODEL_ARRAY[@]}"; do\n\
     done\n\
 done\n\
 echo "Starting Gunicorn server at $(date)" | tee -a $LOG_FILE\n\
-exec python3 -m gunicorn --bind 0.0.0.0:7860 --workers 1 --timeout 120 --log-level info app:app >> $LOG_FILE 2>&1' > /app/start.sh && \
+exec gunicorn --bind 0.0.0.0:7860 --workers 1 --timeout 120 --log-level info app:app >> $LOG_FILE 2>&1' > /app/start.sh && \
     chmod +x /app/start.sh
 
 # Expose port
 EXPOSE 7860
 
-# Health check with optimized parameters
+# Health check
 HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
     CMD curl -f http://localhost:7860/health || exit 1