-
Currently, Manticore uses the HNSW index over floats for its KNN search implementation. That might lead to excessive memory consumption, as all HNSW indexes must be loaded into RAM. One way to improve…
-
### Describe the problem
HNSW index growth is unbounded (which is by design as graph removals are expensive). Chroma currently uses the default configuration for `allow_replace_deleted` which is set …
-
### Description
I came across a spooky comment `// we see repeated neighbor nodes?!` in [this `luceneutil` PR](https://github.com/mikemccand/luceneutil/pull/290/files) and discussed with @msokolov an…
-
https://supabase.com/blog/pgvector-performance
https://neon.tech/blog/pg-embedding-extension-for-vector-search
pgvector is currently at 0.4.0; hnsw support is slated for 0.5.0; in theory hnsw can …
-
I would like to request a feature that allows for printing the different levels of an HNSW graph in HNSWlib. This would help users better understand the structure of the graph and visually inspect the…
-
We should implement pre-filtering in HNSW in a way that it does not change the search topology.
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version: master-20241112-b5b00355-amd64
- Deployment mode(standalone …
-
### Environment
docker
image tensorchord/pgvecto-rs:pg16-v0.3.0
image tensorchord/pgvecto-rs: pg16-v0.2.1
### Step
1. create table with embedding vector(3072)
2. create index…
-
Just curious if the HNSW algorithm is amenable to use in this project? Probably not directly because I see you are jitting in the distance metric but curious if it is worth a look into that algorithm …
-
### Bug Description:
if create index without float vector then add in later with ALTER daemon failed to save disk chunk or create invalid index
```bash
create table test ( title text );
insert int…