feat: support prefilter

[cutecutecat]

Feat

• Enable rerank_in_table=true with read_stream(pg17) and prefetch_buffer(not pg17)

Optimization

• Remove redundant matrix multiply in both heap / non-heap query/insert, accerate most searches

Chore

• Rename vchordrq.prererank_filtering into vchordrq.prefilter

Test

• Add specialized tests for pg16(prefetch_buffer) and pg17(read_stream)

[Copilot]

Pull Request Overview

This PR introduces support for prefiltering by renaming the configuration option from prererank_filtering to prefilter and updating related code throughout the codebase. It also optimizes query/insert operations by eliminating redundant matrix multiplications and refactors insertion logic to use new helper functions.

• Renames the configuration setting and updates its usage across modules.
• Adds a new filter method to the SearchFetcher trait and updates its implementations.
• Refactors vector insertion logic and adjusts test workflows to cover pg16 and pg17 features.

Reviewed Changes

Copilot reviewed 28 out of 28 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
tests/general/*.slt	Added DROP TABLE cleanup commands in test setups
src/index/scanners/mod.rs	Adds new filter method to SearchFetcher trait
src/index/scanners/maxsim.rs	Refactors vector handling with clearer naming and cloning
src/index/scanners/default.rs	Introduces rerank_wrapper and uses seq_filter for prefilter
src/index/gucs.rs, src/index/am/mod.rs	Adjusts configuration accesses from prererank_filtering to prefilter
src/index/algorithm.rs, crates/algorithm/*	Updates insertion logic to use new helper functions, improves prefetcher traits
.github/workflows/check.yml	Updates test file patterns and adds version-specific test jobs

Comments suppressed due to low confidence (2)

.github/workflows/check.yml:176

• [nitpick] Please verify that the updated test file glob pattern covers all intended test cases and that no tests are unintentionally omitted from the CI runs.

sqllogictest --db $USER --user $USER './tests/general/*.slt'

src/index/scanners/default.rs:133

• Using BinaryHeap::from(results) for filtering could incur additional overhead if the results are large; verify that this conversion meets performance targets under heavy load.

let seq = seq_filter(BinaryHeap::from(results), |key| {

[usamoi]

记得改回来

[cutecutecat]

Fixed