* Fix merge of vector operations, don't drop earlier updates on same point
* Add unit test for vector struct merging
* Add integration test for fix, also covering bug report
* Merge serde attributes
* Remove obsolete conversion
* Add integer type with parameters
* Make integer lookup and range parameters non-optional
* Add parameterized integer index types test
Co-authored-by: Di Zhao <diz@twitter.com>
* Cleanup
---------
Co-authored-by: Di Zhao <diz@twitter.com>
* Set high/low priority for consensus and HNSW threads
* Make setting thread priority Linux specific
* Fix compilation on non-Linux platforms
* Remove unused dependencies from Cargo.toml
* Rename function
* Add warning that setting lower nice is likely to fail
* fix missing indexing values on set-payload operation
* Update function documentation, use conventional warning
* Don't deep match statements
* test: Update of payload on already indexed payload should work (#3253)
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Kumar Shivendu <kshivendu1@gmail.com>
* sparse vectors with large indices support
* fix unit tests
* add tracker file to snapshot
* fix unit tests
* are you happy clippy
* fix config loading
* test with max value
* fix python tests
* fix consensus tests
* review remarks; acc test for inverted index
* remove quantization update from hnsw index
* test that hnsw was builded with presented quantization
* are you happy codespell
* prefer method over public field
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* Optimizer detects on_disk update sparse vector index
* Rename sparse vector index on disk check function to remove ambiguity
* Appendable segments always have sparse index in memory
Don't try to force these segments to have their index on disk if
our collection configuration tells us to do it that way.
* Fix compilation warning
* Resolve merge conflict
* In indexing optimizer, only put sparse vectors on disk if big
* fix mutable->immutable optimization
* fix negation
* Disable config mismatch for sparse now, update sparse vector storage decision tree
* Fix compilation error due to TODO
* Fix flipped boolean
* simplify config mismatch logic
* simplify logic further
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: generall <andrey@vasnetsov.com>
* internal sparse vector segment configs
update openapi
fix build
provide correct index type to fixtures
internal sparse vector segment configs
update openapi
fix build
load ram sparse index from file
fix spelling
add test
spelling error
use appendable flag to decide load or not
fix conflict
dont flush mmap when file is empty
* fix build
* set list of files for snapshot
* fix snapshots test
* fix codespell
* simple save-load unit test
* refactor InvertedIndex::files
* fix unit tests
* add debug_assert
* test all persistence loading cases
* sparse vectors query scorer
plain search test without internals
fix sparse_vector_index_plain_search
fix async scorer build
fix unit tests
are you happy fmt
sparse index with full query support
fix benches, use exact flag to force plain search
add alias and comment to exact flag
fix tests
recommendations TODOs fix
add simple test
add todo
refactor index
test vs comparison dense and sparse discovery
are you happy fmt
propogate error from avg negatives
reuse filtered points list
rollback api changes
better discovery test
are you happy fmt
rollback openapi
fix build
fix tests
review remark recommendations
review remarks
review remarks
codespell
integrate plain search
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
fix comment of plain search
Update lib/collection/src/recommendations.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
fix tests
* simplify search query function
* Estimate sparse vector dimension for optimizer (#3142)
* Estimate sparse vector dimension for optimizer
* add hack explanation + todo
Fix optimizer change sparse index on disk
fix index to disk
is appendable fix
add index files if necessary
fix test
* fix tests
---------
Co-authored-by: Ivan Pleshkov <pleshkov.ivan@gmail.com>
* Prevent another division by zero in geo index
* Set default `max_values_per_point` to zero
* Extend empty cardinality test
* Add unit tests for empty index types with cardinality
* Shortcut cardinality estimation, zero if no values per point
* Use const functions for cardinality type
* Remove redundant checked division, we do a rhs zero check above
* Increased visited-list pool size to 128
* Set visited-list pool limit to CPU count, clamp between 16 and 128
* Preallocate visited list pool vector with full capacity
---------
Co-authored-by: timvisee <tim@visee.me>
