#!/bin/bash

# Start Ollama
ollama serve > /dev/null 2>&1 &

echo "🔴 Waiting for Ollama..."
while ! curl -s http://localhost:11434/api/tags > /dev/null; do
    sleep 1
done

echo "🟢 Ollama Ready."

# ONLY loading one small model to prevent RAM crash
echo "⬇️ Pulling Qwen (Small)..."
ollama pull qwen2.5-coder:0.5b

# If you really need phi3, uncomment the next line, but it might crash the space:
# ollama pull phi3:mini 

echo "🚀 Starting App..."
exec streamlit run app.py \
  --server.port=7860 \
  --server.address=0.0.0.0 \
  --server.headless=true \
  --theme.base="dark" \
  --browser.gatherUsageStats=false