Backport "sandboxed de-duplicating HNSW vector format" to 10.x - #16493
Open
kaivalnp wants to merge 2 commits into
Open
Backport "sandboxed de-duplicating HNSW vector format" to 10.x#16493kaivalnp wants to merge 2 commits into
kaivalnp wants to merge 2 commits into
Conversation
Add a sandboxed de-duplicating HNSW vector format (`DedupHnswVectorsFormat`) that stores each distinct full-precision vector once, shared across all documents and fields that reference it. This format enables building and searching of multiple HNSW graphs backed by the same vectors, without duplicating them on disk. For example: a subset of vectors identified by a filter can be indexed into a dedicated HNSW graph for performant filtered vector search. Fields are grouped by `(dimension, encoding)` and all vectors within a group are de-duplicated during flush and merge. Each field maintains an off-heap mapping from `field ordinal -> ordinal in group` to reference to the shared vector, and vector operations like scoring and lookup are indirected to it. (cherry picked from commit 4a3ed97)
- Remove float16 functions - Workarounds for unsupported Java language features - Use equivalent 10.x patterns for missing functions
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Backport #15979 to
branch_10x