import os
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams
from app.config import settings

# Initialize Qdrant client
qdrant_client = QdrantClient(
    url=settings.QDRANT_URL,
    api_key=settings.QDRANT_API_KEY,
)

COLLECTION_NAME = "book_embeddings"

def init_qdrant_collection():
    """Initialize Qdrant collection if it doesn't exist"""
    try:
        # Check if collection exists
        collections = qdrant_client.get_collections().collections
        collection_names = [col.name for col in collections]
        
        if COLLECTION_NAME not in collection_names:
            # Create collection with vector configuration
            qdrant_client.create_collection(
                collection_name=COLLECTION_NAME,
                vectors_config=VectorParams(
                    size=1536,  # OpenAI text-embedding-3-small dimension
                    distance=Distance.COSINE
                )
            )
            print(f"✅ Created Qdrant collection: {COLLECTION_NAME}")
        else:
            print(f"✅ Qdrant collection already exists: {COLLECTION_NAME}")
    except Exception as e:
        print(f"⚠️ Warning: Could not initialize Qdrant collection: {e}")

def get_qdrant_client():
    """Dependency to get Qdrant client"""
    return qdrant_client