* add ignore_plain_index to speed up search
* remove unnecessary & for vectors_batch
* format
* add special handle for proxy segments where the wrapped segment is plain
indexed
* review refactoring
* rollback changes in google.protobuf.rs
---------
Co-authored-by: Di Zhao <diz@twitter.com>
Co-authored-by: generall <andrey@vasnetsov.com>
* pass atomic bool from local shard to raw scorer
* pass atomic bool from local shard to raw scorer
* is_stopped in async scorer
* fmt
* is_stopped in quantized scorer
* terminating scorer if stopped
* enable timeout in local_shard
* allow timeout configuration
* use tokio spawn to ensure timeout handling if request is dropped
* Revert "use tokio spawn to ensure timeout handling if request is dropped"
This reverts commit 1068cf48d4.
* use stopping guard instead of task
* report error if search request is stopped
* fmt
* refactor transient error handelling
* Clone current segment config to deprecated type
* Remove segment level quantization config from segment config
* Also deprecate current VectorDataConfig
* Update old segment migration to work with new refactoring
* Move index into vector data config
* Move vector data config migration logic into segment level
* Remove hnsw_config from vector data config
* Rename collection params to vector data conversions function
* Move storage type into vector data config
* Set appendable flag correctly
* Clean up and reformat
* Make segment on disk flag not optional
* Add appendable flag to segment config to replace storage type
* Remove storage type from segment config
* Deprecate storage type enum
* Use consistent variable naming
* Cleanup
* Add segment config migration for v0.5.0 to current
* Bump segment to 0.6.0
* Remove serde defaults for new storage and vector data config types
These default value configurations are not needed anymore, because these
structs are not used to deserialize old data. All current fields should
always be available in these structs. When new fields are added in new
functions, the serde default annotation must be set again.
* Cleanup
* Update OpenAPI specification
This updates the returned data structure on telemetry endpoints, as a
result of segment configuration refactoring.
* Fix quantization configuration not falling back to collection config
* Fix compiler warning when building in release mode
* Move deprecated type structs into compat module
* Update allow deprecated attributes
* Assign quantization config only in segment optimizer
* Remove unsued parameter
* Add vector storage type enum to vector data config
* Remove appendable and on_disk flags from segment and vector config
* Update OpenAPI specification
* add tests
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* nested object filter
* code review
* add support for must_not in nested
* extract functions
* support and test must_not in SimpleConditionChecker
* add index matching unit test (to be continued)
* remove extra clone
* test with should
* WIP: Nested object filter suggestions (#1855)
* switch to bitvec
* fix clippy
* more tests
* fmt
* fix some tests
* add test with text
* support for nested should
* do not rely on indexes for nested queries & fix test
* use index to make index-aware checks in nested payload
* fix value-count tests
* re-fa-cto-ring
* fmt
---------
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* wip: chunked mmap
* Fix typo
* insert and get methods
* dynamic bitvec
* clippy
* wip: vector storage
* wip: fmt
* wip: mmap chunks
* wip: mmap problems
* Share transmuted mutable reference over mmap
* option to enable appendable mmap vectors
* fmt
* rename storage status file
* update tests
* fix get deleted value range
* add recovery to vector storage tests
* add flush to tests
* fix transmute from immutable to mutable
* make transmuted pointer private
* remove unused unsafe functions
* force WAL flush if wait=true
* move wal flush into updater thread
* remove flush from update api
* Minimize pub visibility for specialized/dangerous functions
* Allocate vector with predefined capacity
* Inline format parameters
* Assert we have multiple chunks while testing, test is useless otherwise
* Remove unnecessary scope
* Remove unnecessary dereference
* Random bool has 0.5 as standard distribution, use iter::repeat_with
* Replace RemovableMmap::new with Default derive
* Rename len to num_flags
* Use Option replace as it is convention alongside take
* Add FileId enum to replace error prone manual ID rotating
* Use debug_assert_eq where applicable
* Refactor drop and set to replace
* Change default chunk size for chunked mmap vectors to 32MB
This change is made as per GitHub review, because allocating a few
storages with 128MB would take a significant amount of time and storage.
See: https://github.com/qdrant/qdrant/pull/1838#discussion_r1187215475
* Replace for-loops with iterators
* Draft: add typed mmap to improve code safety (#1860)
* Add typed mmap
* Replace some crude mmap usages with typed mmap
* Use typed mmap for deleted flags
* Simplify dynamic mmap flags a lot with new typed mmap, remove flags option
* Reformat
* Remove old mmap functions that are now unused
* Reimplement mmap locking for mmap_vectors
* Add MmapBitSlice tests
* Replace MmapChunk with new typed mmap
* Update docs
* Clean-up
* Disable alignment assertions on Windows for now
* Rename mmap lock to mlock to prevent confusion with lockable types
* one more small test
* Some review fixes
* Add aliasing note
* Add basic error handling in typed mmap constructors
* Use typed mmap error handling throughout project
* Move mmap type module to common
* Fix transmute functions being unsound
See https://github.com/qdrant/qdrant/pull/1860#discussion_r1188593854
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Tim Visée <tim+github@visee.me>
* Add segment entry function to update named vectors
* Use already available function to update existing vectors
We already had a segment function to update existing named vectors. This
change ensure we use that instead of separating it separately. As a
bonus, this adds support for setting multiple named vectors at once.
* Update set vectors ourselves, don't drop omitted vectors
* Refactor vector updating functions, separate update and replace
* Add basic vector ops, add update/delete functionality to segment updater
* Add internal and public gRPC types and actions for vectors
* Add gRPC API actions
* Reformat
* Add VectorOperations to vector ops, add basic validation
* Validate gRPC vector types
* Validate vector operation structs
* Construct PointIdsList through From trait
* Update gRPC docs
* Use VectorsSelector for vector deletions in gRPC
* Add support for updating multiple points/vectors in update vectors API
* Update gRPC docs
* Fix incorrect gRPC type numbering
* Return point ID error from vector update/delete functions if not found
* Fix disbalanced vectors test
* Minor collection optimizer cleanup
* Make optimizers better aware of available vs soft deleted points
* Fix incorrect deleted state on proxy segment for double delete
* Rename upsert_vector to upsert_point, because we work with points
* Refactor point methods for more clear and consistent naming
* Replace internal_size in IdTracker with total_point_count
* Keep track of vector deletion count on storage creation
* Add sparse index optimizer, to optimize indexes with high deletion count
* Add minimum vector count threshold to sparse index optimizer
* Add sparse index optimizer test
* Use consistent naming, write vector in full everywhere
* Simplify vacuum optimizer a bit
* Merge sparse index optimizer into vacuum optimizer
* Improve update_from in segment builder by returning early
* More accurately count vectors in segment optimizer
* Remove random from vacuum optimizer tests to make them more reliable
* Don't expose the total points in segment info, use available points
* Process review feedback
* Compare available vectors against indexed ones in vacuum optimizer
This is much better than using the number of soft-deleted vectors when
the segment was created for calculations. Not to mention that value had
other problems as well.
* Remove create_deleted_vector_count field, update vacuum test parameters
* Potentially solve out of bound panic when building index
* Review fixes:
- Propagate deleted flags into payload hnsw building
- Use `total` number of points for building HNSW instead of number of
available points
- minor refactoring of `hnsw_config` copy -> clone
- Better detection of `indexed_points` in HNSW
* fix assert condition
* Optional named vectors optimizer reveiw 2 (#1794)
* review with Ivan
* fmt
* remove available_vector_count from segment entry
* remove total_point_count from segment entry
---------
Co-authored-by: Ivan Pleshkov <pleshkov.ivan@gmail.com>
* rollback changes in deleted count in proxy segment
* improve vector threshold detection logic in optimized_segment_builder
* style changes
* fix propagate deleted points to vectors
* Fix typo in method name
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
Co-authored-by: Ivan Pleshkov <pleshkov.ivan@gmail.com>
* Exclude deleted vectors from HNSW graph building stage
* When estimating query cardinality, use available points as baseline
We should not use the total number of points in a segment, because a
portion of it may be soft deleted. Instead, we use the available
(non-deleted) points as baseline.
* Add plain search check to unfiltered HNSW search due to deleted points
* Cardinality sampling on available points, ignore deleted named vectors
* Estimate available vectors in query planner, now consider deleted points
In the query planner, we want to know the number of available points as
accurately as possible. This isn't possible because we only know the
number of deletions and vectors can be deleted in two places: as point
or as vector. These deletions may overlap. This now estimates the number
of deleted vectors based on the segment state. It assumes that point and
vector deletions have an overlap of 20%. This is an arbitrary
percentage, but reflects an almost-worst scenario.
This improves because the number of deleted points wasn't considered at
all before.
* Remove unused function from trait
* Fix bench compilation error
* Fix typo in docs
* Base whether to do plain search in HNSW upon full scan threshold
* Remove index threshold from HNSW config, only use full scan threshold
* Simplify timer aggregator assignment in HNSW search
* Remove vector storage type from cardinality function parameters
* Propagate point deletes to all its vectors
* Check for deleted vectors first, this makes early return possible
Since point deletes are now propagated to vectors, deleted points are
included in vector deletions. Because of that we can check if the vector
is deleted first so we can return early and skip the point deletion
check.
For integrity we also check if the point is deleted, if the vector was
not. That is because it may happen that point deletions are not properly
propagated to vectors.
* Don't use arbitrary vector count estimation, use vector count directly
Before we had to estimate the number of vectors (for a named vector)
because vectors could be deleted as point or vector. Point deletes are
now propagated to vector deletes, that means we can simply use the
deleted vector count which is now much more accurate.
* When sampling IDs, check deleted vecs before deleted points
* On segment consistency check, delete vectors for deleted points
* Fix vector delete state not being kept when updating storage from other
* Fix segment builder skipping deleted vectors breaking offsets
* update segment to handle optional vectors + add test (#1781)
* update segment to handle optional vectors + add test
* Only update stored record when deleting if it wasn't deleted already
* Reformat comment
---------
Co-authored-by: timvisee <tim@visee.me>
* Fix missed vector name test, these are now marked as deleted
* upd test
* upd test
* Update consensus test
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* Add QuantizationConfigDiff type
* Add quantization config diff to vector parameters
* Prefer vector config over collection config for quantization
* Update OpenAPI specification
* Validate quantization configuration quantile in 0.5-1.0 range
As per https://github.com/qdrant/qdrant/pull/1681
* Add test if check if vector specific quantization config is persisted
* Alias quantization to quantization_config in vector parameters
* Remove quantization config diff, use full vector specific config instead
* Regenerate OpenAPI specification and gRPC docs
* Fix compilation error
* Add error handling to quantization config conversions
* Fix quantization integration test, make HNSW test stricter
* Validate VectorConfig/VectorParams, remove obsolete validation
* Add HNSW config diff to vector parameters
* Validate params in collection config
* Add HNSW config to segment vector data config
* Add VectorsConfig params iterator for more elegant conversions
* Prefer vector HNSW config over collection config for building HNSW index
* Base segment vector param HNSW config on collection config
* General improvements
* Rewrite HNSW ef_construct extract function to also consider vector configs
* Update OpenAPI specification
* Add test to check if vector specific HNSW config is persisted
* review changes
* review changes
* Regenerate gRPC docs
* Fix test on Windows
* Regenerate OpenAPI specification
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* remove deleted flags from vector storage
* remove deleted flags from mmap
* new simple vector storage format
* are you happy clippy
* remove id_tracker from raw_scorer
* revert vector storage format changes
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* integrate quantized data to storages
* revert gitignore
* are you happy clippy
* quantize in optimizer
* provide flag
* fix segfault
* skip quantization flag, update scores
* use quantization flag
* are you happy fmt
* use quantization flag
* quantized search test
* are you happy fmt
* refactor test, refactor scorer choosing
* are you happy fmt
* run quantization on segment builder
* decrease testing parameters
* simplify segment
* update version
* remove use_quantization flag
* provide quantization config
* quantization version up
* euclid dist
* add euclid test
* saveload
* fix initialization bugs
* quantization lib version up
* fix arm build
* refactor scorer selecting
* quant lib version up
* are you happy fmt
* are you happy fmt
* are you happy clippy
* add save/load test for simple storage
* add comments
* quantiles
* quantization mmap
* remove f32
* mmap test
* fix mmap slice
* fix mmap test
* use chunks for quantization storage
* fix build
* are you happy fmt
* update quantization library
* update quantization lib
* update quantization lib
* integrate api changes
* are you happy fmt
* change quantization api
* additional checks in tests
* update quantization version
* fix unit tests
* add quantization to storage config
* use quantization for all cardinality search cases
* Integrate quantization suggestions 2 (#1520)
* review api
* wip: refactor quantization integrations
* wip: refactor quantization integrations
* wip: fmt
* include quantization into snapshot
* fmt
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* add on disk key
* remove obsolete graph initialization
* remove obsolete max level
* update openapi
* graph links trait
* use mmap option
* same format for ram and mmap
* fix segment unit tests
* are you happy fmt
* are you happy clippy
* fix ci and add mmap test
* review fixes
* remove unused try-from
* fix version compatibility
* avoid loading from disk during conversion
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* exact search parameter
* exact search test
* decrease attempts count because of test speed
* minor review fixes
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* many named vectors per point (segment-level)
* operation result for dim function
* beautifulized vector name
* fix naming bug
* segment version migration
* fmt
* add segment tests
* are you happy clippy
* fix build
* [WIP] many named vectors per point (collection-level) (#975)
* config and search
* fix placeholders for proxy segment move
* remove VectorType from collection
* are you happy fmt
* vectors in grps messages
* create collections with vectors
* segment holder fixes
* are you happy fmt
* remove default vector name placeholders
* are you happy fmt
* are you happy clippy
* fix build
* fix web api
* are you happy clippy
* are you happy fmt
* record vector&vectors
* openapi update
* fix openapi integration tests
* segment builder fix todo
* vector names for update from segment
* remove unwrap
* backward compatibility
* upd openapi
* backward compatible PointStruct
* upd openapi
* fix record back-comp
* fmt
* vector configuration backward compatibility
* fix vetor storage size estimation
* fmt
* multi-vec segment test + index test
* fmt
* api integration tests
* [WIP] Named vectors struct (#1002)
* move to separate file
* named vectors as struct
* use cow
* fix build
* keys iterator
* avoid copy in PointStruct -> get_vectors
* avoid another copy
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* allow additional params for payload field index
* fmt
* wip: full text index building
* fmt
* text search request
* text search request
* full text index persitance and loading
* fmt
* enable fts index in mapping
* clippy
* fix tests + add integration test
* review fixes: extend payload index test
* revert incedental change
