Add GPU support and improve Docker deployment

- Add GPU deployment support with NVIDIA runtime
  - Update Dockerfile.allinone with GPU environment variables
  - Add comprehensive GPU_DEPLOYMENT.md guide

- Make port 11434 (Ollama) optional for security
  - Update DEPLOYMENT.md with CPU and GPU deployment options
  - Simplify default docker run commands
  - Update healthcheck to only check web application

- Add memory requirements documentation
  - Create MEMORY_REQUIREMENTS.md with model comparison
  - Add build-8b.sh script for lower memory usage
  - Document OOM troubleshooting steps

- Improve Docker build process
  - Add BUILD_TROUBLESHOOTING.md for common issues
  - Add DISTRIBUTION.md for image distribution methods
  - Update .gitignore to exclude large binary files
  - Improve docker-entrypoint.sh with better diagnostics

- Update .dockerignore to include ollama-linux-amd64.tgz
- Add backup file exclusions to .gitignore

docker-entrypoint.sh

@@ -2,34 +2,102 @@
 
 set -e
 
+echo "=========================================="
+echo "System Prompt Optimizer - Starting Up"
+echo "=========================================="
+echo ""
+
+# Check if Ollama binary exists
+if ! command -v ollama &> /dev/null; then
+    echo "ERROR: Ollama binary not found!"
+    echo "Expected location: /usr/bin/ollama or /usr/local/bin/ollama"
+    ls -la /usr/bin/ollama* 2>/dev/null || echo "No ollama in /usr/bin/"
+    ls -la /usr/local/bin/ollama* 2>/dev/null || echo "No ollama in /usr/local/bin/"
+    exit 1
+fi
+
+echo "✓ Ollama binary found: $(which ollama)"
+echo ""
+
+# Check if model files exist
+echo "Checking model files..."
+if [ ! -d "/root/.ollama/models" ]; then
+    echo "ERROR: /root/.ollama/models directory not found!"
+    exit 1
+fi
+
+MANIFEST_COUNT=$(find /root/.ollama/models/manifests -type f 2>/dev/null | wc -l)
+BLOB_COUNT=$(find /root/.ollama/models/blobs -type f 2>/dev/null | wc -l)
+
+echo "✓ Found $MANIFEST_COUNT manifest files"
+echo "✓ Found $BLOB_COUNT blob files"
+
+if [ "$BLOB_COUNT" -lt 10 ]; then
+    echo "WARNING: Very few blob files found. Models may not be complete."
+fi
+echo ""
+
 echo "Starting Ollama service..."
-ollama serve &
+ollama serve > /tmp/ollama.log 2>&1 &
+OLLAMA_PID=$!
 
 # Wait for Ollama to be ready
 echo "Waiting for Ollama to start..."
-for i in {1..30}; do
+OLLAMA_READY=false
+for i in {1..60}; do
     if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
         echo "Ollama is ready!"
+        OLLAMA_READY=true
         break
     fi
-    echo "Waiting for Ollama... ($i/30)"
-    sleep 2
+    echo "Waiting for Ollama... ($i/60)"
+    sleep 3
 done
 
+if [ "$OLLAMA_READY" = false ]; then
+    echo ""
+    echo "ERROR: Ollama failed to start within 3 minutes!"
+    echo ""
+    echo "Ollama logs:"
+    cat /tmp/ollama.log
+    echo ""
+    echo "Check full logs with: docker logs system-prompt-optimizer"
+    exit 1
+fi
+
 # Check if models exist, if not, show warning
+echo ""
 echo "Checking for models..."
 ollama list
 
+echo ""
 if ! ollama list | grep -q "qwen3:14b"; then
-    echo "WARNING: qwen3:14b model not found!"
+    echo "ERROR: qwen3:14b model not found!"
     echo "The application requires qwen3:14b to function properly."
+    echo ""
+    echo "Available models:"
+    ollama list
+    echo ""
+    exit 1
 fi
 
 if ! ollama list | grep -q "qwen3-embedding"; then
     echo "WARNING: qwen3-embedding model not found!"
     echo "The application requires qwen3-embedding:4b for embeddings."
+    echo "Continuing anyway, but embeddings may not work."
 fi
 
+echo ""
+echo "✓ All required models are available"
+echo ""
+echo "=========================================="
 echo "Starting FastAPI application..."
+echo "=========================================="
+echo "Application will be available at:"
+echo "  - Web UI: http://localhost:8010/ui/opro.html"
+echo "  - API Docs: http://localhost:8010/docs"
+echo "  - Ollama: http://localhost:11434"
+echo ""
+
 exec uvicorn _qwen_xinference_demo.api:app --host 0.0.0.0 --port 8010