Qdrant is a vector similarity engine & vector database. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
MIT License
93
stars
21
forks
source link
The value of the HNSW configuration parameter M can be zero #52
I tried to implement the configuration trick from the documentation and realized that when I set M to 0 in the HNSW configuration, in the new collection I get the default M value (16 in my case).
Hi!
I tried to implement the configuration trick from the documentation and realized that when I set M to 0 in the HNSW configuration, in the new collection I get the default M value (16 in my case).
PR will fix it