from qdrant_client import QdrantClient, models client = QdrantClient(url="http://localhost:6333") client.create_collection( collection_name="{collection_name}", vectors_config=models.VectorParams(size=768, distance=models.Distance.COSINE, on_disk=True), quantization_config=models.ScalarQuantization( scalar=models.ScalarQuantizationConfig( type=models.ScalarType.INT8, always_ram=True, ), ), )