fix(memory): recreate Qdrant collections on vector dimension mismatch#1820
Merged
fix(memory): recreate Qdrant collections on vector dimension mismatch#1820
Conversation
…#1815) ensure_collection() now checks the existing collection's configured vector size via collection_info() before deciding whether to recreate. Previously the check relied on point metadata, which meant empty collections (0 points) were never detected as stale when the embedding model changed. New logic: - collection_info() is queried first (no embedding probe) - If existing size matches the required size, return early - If sizes differ or collection uses named vectors (ParamsMap), delete and recreate with the correct dimensions - embed_fn probe is called at most once per invocation, only when needed
github-actions
bot
added
documentation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
ensure_collection()now queriescollection_info()to compare the existing collection's vector size against the required dimension before deciding to recreatescroll_all()metadata check missed them since there are no points to inspectembed_fn) is called at most once per invocation and only when actually needed (collection absent or size unknown), avoiding unnecessary embedding API round-trips on every syncBehaviour change
Test plan
cargo +nightly fmt --check— cleancargo clippy --workspace --features full -- -D warnings— cleanqwen3-embedding(4096-dim), switch totext-embedding-3-small(1536-dim) — collections must be recreated without errors