Supporting Library , Datatypes , Querytype and Index types #2910
Replies: 3 comments
-
Hi @pauldintel,
Qdrant have custom implementation of HNSW.
By default, it uses 32bit float, but can be compressed with scalar quantization into INT8 and even to bit level with binary quantization.
Yes, we support AVX, as well as Neon instruction set (analog of AVX on ARM processors).
Search - yes
|
Beta Was this translation helpful? Give feedback.
-
thank you @generall for good details ... so only custom HNSW is supported and no other algorithms ? |
Beta Was this translation helpful? Give feedback.
-
we decided that it is better to optimize one algorithm than have rudimentary support to many. Regarding scalar quantization - yes, it is already available |
Beta Was this translation helpful? Give feedback.
-
hi Team ,
Like other vector DB I am looking what Libraries and Index type from below is supported by Qdrant
HNSWlib
DiskANN / Vamana
ScaNN
FAISS-IVFP
NGT
Also are all these datatypes supported ?
FLOAT
INT8 , UINT8
FLOAT16
BFLOAT16
And does Qdrant has support of Intel AVX instructions like AVX512 ?
What are the query types from below it supports ?
Search
Filter + Search
thanks
Beta Was this translation helpful? Give feedback.
All reactions