fix(ruvector-router-core): rebuild HNSW index from storage on open + fix result heap orientation#460
Open
CoolDude1969 wants to merge 1 commit into
Conversation
…NSW result heap
- VectorDB::new() now loads all persisted vectors into the HNSW index
on startup, fixing search() always returning 0 results after restart
(closes ruvnet#430)
- Fix result heap in search_knn_internal: was min-heap, must be max-heap
so peek() returns the furthest result for correct pruning at scale
- Remove ef_construction.min(m*2) beam clamp in insert() so the full
candidate pool is used during graph construction
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
Two bugs causing search() to always return 0 results after restart:
VectorDB::new() never rebuilt the index from storage — a fresh empty
HnswIndex was created every time, so all persisted vectors were
invisible to search. Closes ruvector-router-core HNSW: search returns 0 results from inserted vectors at scale (recall@1 << 1.0) #430.
search_knn_internal used a min-heap for
result— it must be amax-heap so peek() returns the furthest candidate for correct pruning.
With a min-heap, valid candidates were silently discarded at scale.
Changes
get_all_ids() + insert_batch(); fix total_vectors stat initial value
fix termination and replacement conditions
Before / After
Before: ruvector search ... → Found 0 results
After: 1. 1 (score: 0.0000)
2. 2 (score: 0.0061)