feat: emb_list (ArrayOfVector) and sparse AnnIterators for streaming retrieval#1668
Draft
DashUmEr wants to merge 1 commit into
Draft
feat: emb_list (ArrayOfVector) and sparse AnnIterators for streaming retrieval#1668DashUmEr wants to merge 1 commit into
DashUmEr wants to merge 1 commit into
Conversation
Collaborator
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: DashUmEr The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
Collaborator
|
Welcome @DashUmEr! It looks like this is your first PR to zilliztech/knowhere 🎉 |
…retrieval Adds knowhere AnnIterator support enabling bounded-memory streaming (search_iterator) over two index families: - emb_list / ArrayOfVector (EMB_LIST_HNSW, MAX_SIM): a chunk-level streaming iterator with one sub-iterator per query vector, aggregating MAX_SIM per row. - sparse inverted index: a streaming bounded-WAND AnnIterator. Engine-level support for milvus search_iterator over emb_list / hybrid / sparse (milvus-io/milvus#49906). Tests: tests/ut/test_emb_list.cc, test_sparse.cc. Signed-off-by: David <david@41zero.com>
DashUmEr
force-pushed
the
upstream-pr/emblist-anniterator
branch
from
3e980ea to
0419817
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds knowhere AnnIterator support for bounded-memory streaming (search_iterator) over:
one sub-iterator per query vector, aggregating MAX_SIM per row.
Engine-level foundation for search_iterator() over emb_list / hybrid / sparse in Milvus
— design in milvus-io/milvus#49906 (stateless Iterator-v2, no delegator/session). The
Milvus, pymilvus and milvus-sdk-node changes build on this.
Tests: tests/ut/test_emb_list.cc, test_sparse.cc (full UT green: 84 cases / 141.6M asserts).
Targets 2.6 (where native struct-array/emb_list search lives); can retarget main. Draft
for early visibility alongside #49906.