Update start.sh

start.sh

@@ -1,10 +1,34 @@
 #!/bin/bash
-echo "Starting Ollama..."
+
+# Set environment variables for optimization
+export OMP_NUM_THREADS=4
+export MKL_NUM_THREADS=4
+export CUDA_VISIBLE_DEVICES=0
+
+# Start Ollama in the background
 ollama serve &
-echo "Waiting for Ollama to be ready..."
-until curl -s http://localhost:11434 > /dev/null; do
-  echo "Ollama not ready yet, waiting..."
-  sleep 1
+
+# Pull the model if not already present
+if ! ollama list | grep -q "tinyllama"; then
+    ollama pull tinyllama
+fi
+
+# Wait for Ollama to start up
+max_attempts=30
+attempt=0
+while ! curl -s http://localhost:11434/api/tags >/dev/null; do
+    sleep 1
+    attempt=$((attempt + 1))
+    if [ $attempt -eq $max_attempts ]; then
+        echo "Ollama failed to start within 30 seconds. Exiting."
+        exit 1
+    fi
 done
-echo "Ollama is ready, starting app.py..."
-python3 app.py
+
+echo "Ollama is ready."
+
+# Print the API URL
+echo "API is running on: http://0.0.0.0:7860"
+
+# Start the FastAPI server
+uvicorn app:app --host 0.0.0.0 --port 7860 --workers 4 --limit-concurrency 20