Repository navigation
fix: Load Milvus collections once instead of on every query - #6882
Merged
ntkathole merged 2 commits intoSep 29, 2026
Merged
ntkathole merged 2 commits into
ntkathole merged 2 commits into
Conversation
Copy link
Copy Markdown
Contributor
Sorry, something went wrong.
Copy link
Copy Markdown
|
⚠️ Please install the Codecov Report❌ Patch coverage is 94.11765% with 1 line in your changes missing coverage. Please review.
@@ Coverage Diff @@
## master #6882 +/- ##
==========================================
+ Coverage 47.86% 47.87% +0.01%
==========================================
Files 422 422
Lines 52408 52414 +6
Branches 7607 7608 +1
==========================================
+ Hits 25084 25095 +11
+ Misses 25512 25509 -3
+ Partials 1812 1810 -2
Continue to review full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Sorry, something went wrong.
simonhearne
force-pushed
the
fix/milvus-load-once
branch
from
92238fd to
e88bb51
Compare
September 28, 2026 14:34
ntkathole
approved these changes
Sep 29, 2026
Feature views without a vector field get a placeholder vector because Milvus requires one per collection. The placeholder was 1-dimensional, filled with NaN and left unindexed. Milvus Lite accepts all three, but Milvus servers and Zilliz Cloud reject dim < 2 and non-finite values, and refuse to load a collection with an unindexed vector field, so these feature views could not be created or read. The placeholder is now 2-dimensional, zero-filled and FLAT-indexed. Vector fields without vector_index=True also get a FLAT index so the collection can be loaded. Existing collections keep working because the placeholder is filled to the dimension recorded in the collection. Also fixes the Milvus docs page title and example config. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Simon Hearne <simon.hearne@gmail.com>
online_read and retrieve_online_documents_v2 called load_collection on every request, adding a round-trip to each read. The call also hid the fact that newly created collections were never loaded on Milvus servers, because indexes were created after the collection. Collections are now created with their index params, which makes Milvus load them straight away. Existing collections are loaded only if their load state isn't Loaded, and only the first time a store accesses them. The per-query load_collection calls are removed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Simon Hearne <simon.hearne@gmail.com>
ntkathole
force-pushed
the
fix/milvus-load-once
branch
from
e88bb51 to
f75c444
Compare
September 29, 2026 09:10
This was referenced Oct 1, 2026
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
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.
What this PR does / why we need it:
online_read and retrieve_online_documents_v2 called load_collection on every request.
That call also hid a bug: collections were created, then indexed with a separate create_index,
which leaves them unloaded on Milvus servers.
only called if the collection isn't loaded. The result is cached per store instance.
Depends on #6881: every vector field must be indexed for the collection to load when it's created. Until #6881 merges this PR also shows its commit; only the last commit (fix: Load Milvus collections once instead of on every query) is new here.
Which issue(s) this PR fixes:
N/A
Checks
Testing Strategy
Unit tests
Integration tests
Manual tests
Testing is not required for this change
Unit (mocked): an existing collection is loaded 0 times if already loaded and once if not,
across 5 reads; new collections are created with index params and no separate load.
Unit (Milvus Lite): spy confirms load_collection isn't called by reads or searches.
Server: no load_collection per query; a released collection is loaded exactly once by a new store.
Unit tests run on Milvus Lite 3.2.1 (pymilvus 3.0.2). Server tests in sdk/python/tests/integration/online_store/test_milvus_remote.py are marked integration and skip unless ZILLIZ_URI and ZILLIZ_TOKEN are set; they passed against a local Milvus 2.6.0 server and against Zilliz Cloud. The existing Milvus unit and universal integration tests pass unchanged.
Misc
Part of a series of Milvus online store improvements for Zilliz Cloud and production Milvus.
🤖 Generated with Claude Code