opro_demo/docker-entrypoint.sh

#!/bin/bash

set -e

echo "=========================================="
echo "System Prompt Optimizer - Starting Up"
echo "=========================================="
echo ""

# Check if Ollama binary exists
if ! command -v ollama &> /dev/null; then
    echo "ERROR: Ollama binary not found!"
    echo "Expected location: /usr/bin/ollama or /usr/local/bin/ollama"
    ls -la /usr/bin/ollama* 2>/dev/null || echo "No ollama in /usr/bin/"
    ls -la /usr/local/bin/ollama* 2>/dev/null || echo "No ollama in /usr/local/bin/"
    exit 1
fi

echo "✓ Ollama binary found: $(which ollama)"
echo ""

# Check if model files exist
echo "Checking model files..."
if [ ! -d "/root/.ollama/models" ]; then
    echo "ERROR: /root/.ollama/models directory not found!"
    exit 1
fi

MANIFEST_COUNT=$(find /root/.ollama/models/manifests -type f 2>/dev/null | wc -l)
BLOB_COUNT=$(find /root/.ollama/models/blobs -type f 2>/dev/null | wc -l)

echo "✓ Found $MANIFEST_COUNT manifest files"
echo "✓ Found $BLOB_COUNT blob files"

if [ "$BLOB_COUNT" -lt 10 ]; then
    echo "WARNING: Very few blob files found. Models may not be complete."
fi
echo ""

echo "Starting Ollama service..."
ollama serve > /tmp/ollama.log 2>&1 &
OLLAMA_PID=$!

# Wait for Ollama to be ready
echo "Waiting for Ollama to start..."
OLLAMA_READY=false
for i in {1..60}; do
    if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
        echo "Ollama is ready!"
        OLLAMA_READY=true
        break
    fi
    echo "Waiting for Ollama... ($i/60)"
    sleep 3
done

if [ "$OLLAMA_READY" = false ]; then
    echo ""
    echo "ERROR: Ollama failed to start within 3 minutes!"
    echo ""
    echo "Ollama logs:"
    cat /tmp/ollama.log
    echo ""
    echo "Check full logs with: docker logs system-prompt-optimizer"
    exit 1
fi

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

echo ""
if ! ollama list | grep -q "qwen3:14b"; then
    echo "ERROR: qwen3:14b model not found!"
    echo "The application requires qwen3:14b to function properly."
    echo ""
    echo "Available models:"
    ollama list
    echo ""
    exit 1
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."
    echo "Continuing anyway, but embeddings may not work."
fi

echo ""
echo "✓ All required models are available"
echo ""
echo "=========================================="
echo "Starting FastAPI application..."
echo "=========================================="
echo "Application will be available at:"
echo "  - Web UI: http://localhost:8010/ui/opro.html"
echo "  - API Docs: http://localhost:8010/docs"
echo "  - Ollama: http://localhost:11434"
echo ""

exec uvicorn _qwen_xinference_demo.api:app --host 0.0.0.0 --port 8010