Details
-
New Feature
-
Status: In Progress (View Workflow)
-
Major
-
Resolution: Unresolved
Description
A common operation for multi-dimensional vectors is to find k nearest vectors to the given one.
This task is about implementing indexes that allow to do it fast.
- ideally they'll be engine independent
- indexes should be update-able
- in this task we'll only do Euclidean distance
- we'll benchmark it on real multi-million-rows data sets
- what algorithm, exactly, to use is still unclear
Attachments
Issue Links
- relates to
-
MDEV-32886 VEC_FromText() and VEC_AsText() functions
- Open
-
MDEV-33404 Engine-independent indexes: subtable method
- Stalled
-
MDEV-33405 Engine-independent indexes: low-level API method
- Open
-
MDEV-33406 basic optimizer support for k-NN searches
- In Testing
-
MDEV-33407 Parser support for vector indexes
- In Testing
-
MDEV-33408 HNSW for k-ANN vector searches
- In Progress
-
MDEV-33410 VECTOR data type
- Open
-
MDEV-33411 OPTIMIZE for graph indexes
- Open
-
MDEV-33413 cache k-ANN graph in memory
- Open
-
MDEV-33414 benchmark vector indexes
- In Progress
-
MDEV-33415 graph index search: heuristical edge choice
- Open
-
MDEV-33417 vector distance: add more metrics
- Open
-
MDEV-33419 graph index insert: consider more neighbors
- Open
-
MDEV-32885 VEC_DISTANCE() function
- In Testing
-
MDEV-33409 Index Condition Pushdown for k-ANN graph searches
- Open
-
MDEV-33412 cost-based optimizer choice for k-NN indexes
- Open
-
MDEV-33416 graph index: use smaller floating point numbers
- Open
-
MDEV-33418 graph index insert: stronger selection of neighbors
- Open
- links to