#!/bin/bash

set -e

echo "Starting Ollama service..."
ollama serve &

# Wait for Ollama to be ready
echo "Waiting for Ollama to start..."
for i in {1..30}; do
    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
        echo "Ollama is ready!"
        break
    fi
    echo "Waiting for Ollama... ($i/30)"
    sleep 2
done

# Check if models exist, if not, show warning
echo "Checking for models..."
ollama list

if ! ollama list | grep -q "qwen3:14b"; then
    echo "WARNING: qwen3:14b model not found!"
    echo "The application requires qwen3:14b to function properly."
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."
fi

echo "Starting FastAPI application..."
exec uvicorn _qwen_xinference_demo.api:app --host 0.0.0.0 --port 8010