George

> out of curiosity, how much faster is this? @agourlay I am about to post a note here on it But as of now some of the common responses can...

I benchmarked it on scroll queries with with_vectors=True and with_payload=True for a limit of 5, 10, 20 and 30 records I used randomly generated vectors with dim = 512 and...

Going to add benchmarking results with limit = 100, 1_000 and 10_000

```json { "decode": { "512": { "100": { "json": 0.002053125004749745, "orjson": 0.0008660830208100379 }, "1000": { "json": 0.016057875007390976, "orjson": 0.0042370830196887255 }, "10000": { "json": 0.23768579197349027, "orjson": 0.1923259579925798 } }, "1024": {...

Hi @paluigi Methods like `add` and `query` are just convenience methods, which provide some default configurations. The only workaround to use them with another metric is to create a collection...

I am not super sure about this update, it doubles the time we need for these tests This is the time for query tests on `universal-search-query-group-api` branch (0:01:48) On this...

closing in favour of #726

Hi @Amrutha2018 , yes Instead you can use a combination of `collection_exists`, `create_collection`, `delete_collection` (depends on what you'd like to achieve)

hi @GDegrove just to be sure, could you also provide the version of pydantic you're using?

We'll try to look into it, thanks for pointing it out