quantization_config and optimizers_config not applied

[Hosseinberg]

I'm experiencing an issue with the QdrantClient where the quantization_config and optimizers_config settings do not seem to be applied when creating a collection. I'm following the instruction given here: https://qdrant.tech/documentation/guides/optimize/ Below is the code I'm using:

  from qdrant_client import QdrantClient, models
  
  client = QdrantClient(":memory:")
  
  client.create_collection(
      collection_name="test-collection",
      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,
          ),
      ),
      optimizers_config=models.OptimizersConfigDiff(default_segment_number=2, max_optimization_threads=4)
  )
  
  test_collection = client.get_collection(collection_name="test-collection")
  print(test_collection.model_dump())

And here is the result:

{'status': <CollectionStatus.GREEN: 'green'>,
 'optimizer_status': <OptimizersStatusOneOf.OK: 'ok'>,
 'vectors_count': None,
 'indexed_vectors_count': 0,
 'points_count': 0,
 'segments_count': 1,
 'config': {'params': {'vectors': {'size': 768,
    'distance': <Distance.COSINE: 'Cosine'>,
    'hnsw_config': None,
    'quantization_config': None,
    'on_disk': True,
    'datatype': None,
    'multivector_config': None},
   'shard_number': None,
   'sharding_method': None,
   'replication_factor': None,
   'write_consistency_factor': None,
   'read_fan_out_factor': None,
   'on_disk_payload': None,
   'sparse_vectors': None},
  'hnsw_config': {'m': 16,
   'ef_construct': 100,
   'full_scan_threshold': 10000,
   'max_indexing_threads': 0,
   'on_disk': None,
   'payload_m': None},
  'optimizer_config': {'deleted_threshold': 0.2,
   'vacuum_min_vector_number': 1000,
   'default_segment_number': 0,
   'max_segment_size': None,
   'memmap_threshold': None,
   'indexing_threshold': 20000,
   'flush_interval_sec': 5,
   'max_optimization_threads': 1},
  'wal_config': {'wal_capacity_mb': 32, 'wal_segments_ahead': 0},
  'quantization_config': None},
 'payload_schema': {}}

As shown, the quantization_config and optimizers_config settings are not reflected in the collection configuration. I got the same result when using the same config on an on-disk collection. Could you please advise if this is a limitation of the in-memory and on-disk modes or if there is a workaround?

Thank you!

[generall]

client = QdrantClient(":memory:")

You are running "local mode". It doesn't have any optimizations and is only suitable for experiments and CI. If you want to scale you need to either run in docker or on cloud

[Hosseinberg]

Thanks for your quick response. Is it documented somewhere? Just curious to know if there's any other limitations.