from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance
import os

# Embedding-Modell
model = SentenceTransformer("all-MiniLM-L6-v2")

# Qdrant-Client
qdrant = QdrantClient(
    host=os.getenv("QDRANT_HOST", "localhost"),
    port=int(os.getenv("QDRANT_PORT", 6333))
)

# Collections initialisieren
for coll in ["exercises", "training_plans"]:
    if not qdrant.collection_exists(coll):
        qdrant.recreate_collection(
            collection_name=coll,
            vectors_config=VectorParams(
                size=model.get_sentence_embedding_dimension(),
                distance=Distance.COSINE
            )
        )