#!/bin/bash

export OLLAMA_KEEP_ALIVE=-1
export OLLAMA_MAX_LOADED_MODELS=1
export OLLAMA_NUM_PARALLEL=1
export OLLAMA_MAX_QUEUE=512
export OLLAMA_NUM_THREADS=2
export OLLAMA_FLASH_ATTENTION=1

ollama serve &
OLLAMA_PID=$!

echo "Waiting for Ollama..."
for i in {1..60}; do
    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
        echo "Ollama is ready!"
        break
    fi
    echo "Attempt $i/60..."
    sleep 2
done

# ═══ Abliterated + Q4_K_M ═══
echo "Pulling model..."
ollama pull hf.co/mradermacher/gemma-3-4b-persian-v0-abliterated-GGUF:Q4_K_M

echo "Model ready. Starting FastAPI..."
uvicorn app:app --host 0.0.0.0 --port 7860