entrypoint.sh

#!/bin/bash
set -e

export OLLAMA_HOST=127.0.0.1:11434
export OLLAMA_MODELS=/home/user/.ollama/models
export OLLAMA_NUM_PARALLEL=2
export OLLAMA_MAX_LOADED_MODELS=2
export OLLAMA_KEEP_ALIVE=-1

echo "==> Starting Ollama..."
ollama serve &

echo "==> Waiting for Ollama to be ready..."
MAX_RETRIES=30
COUNT=0
until curl -s http://127.0.0.1:11434/api/version > /dev/null 2>&1; do
    COUNT=$((COUNT + 1))
    if [ $COUNT -ge $MAX_RETRIES ]; then
        echo "ERROR: Ollama did not start."
        exit 1
    fi
    echo "  ... attempt $COUNT/$MAX_RETRIES"
    sleep 2
done
echo "==> Ollama ready!"

echo "==> Pulling lfm2.5-thinking:latest..."
ollama pull lfm2.5-thinking:latest

echo "==> Pulling qwen2.5vl:7b..."
ollama pull qwen2.5vl:7b

echo "==> Models loaded:"
ollama list

echo "==> Starting proxy on :7860..."
exec uvicorn proxy:app --host 0.0.0.0 --port 7860 --workers 4