Details
-
Task
-
Status: In Testing (View Workflow)
-
Critical
-
Resolution: Unresolved
-
None
-
None
Description
Let's keep the graph in memory. Like, in TABLE_SHARE.
Add nodes there as they're read from the table, e.g. on searches.
Update on inserts.
When it'll grow beyond some (configurable) limit, start removing nodes that are close to each other. Or remove the bottom level in HNSW. The goal is to still keep enough in memory to find any row with no more than one table access.
Not clear how to do transaction isolation.
Attachments
Issue Links
- is blocked by
-
MDEV-33414 benchmark vector indexes
- In Testing
- is part of
-
MDEV-34939 vector search in 11.7
- In Testing
- relates to
-
MDEV-32887 k-ANN indexes for vectors
- In Progress