xzfc
3dcf69dacd
GraphLinksMmap: remove Option ( #5374 )
...
* Introduce GraphLayerData
* trait GraphLinks: do not require Default
2024-11-07 10:54:14 +00:00
Jojii
7b677fb7fa
Hardware counting for quantization ( #5369 )
...
* add cpu measurement for quantization
* clippy
* fix tests
* discard hardware counters in benchmarks
* Forwarding hardware counter in distributed setup (#5371 )
* make hardware counter available in distributed setup
* clippy
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-11-06 16:23:02 +01:00
Arnaud Gourlay
a5c9ce49aa
Do not sort sparse vector before remapping it ( #5351 )
...
* Do not clone sparse vector to remap it
* sort only once
* remove unwrap_or_else change
2024-11-06 12:51:23 +01:00
dependabot[bot]
d0cbd40b0f
build(deps): bump geo from 0.28.0 to 0.29.1 ( #5355 )
...
* build(deps): bump geo from 0.28.0 to 0.29.1
Bumps [geo](https://github.com/georust/geo ) from 0.28.0 to 0.29.1.
- [Changelog](https://github.com/georust/geo/blob/main/CHANGES.md )
- [Commits](https://github.com/georust/geo/compare/geo-0.28.0...geo-0.29.1 )
---
updated-dependencies:
- dependency-name: geo
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
* migrate the new trait system
* fix clippy in tests
---------
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com >
2024-11-06 11:21:47 +01:00
Andrey Vasnetsov
f843ab6610
detailed is_on_disk ( #5373 )
2024-11-06 11:04:30 +01:00
xzfc
978c4bdd99
Fixups for VistedPool ( #5365 )
2024-11-05 10:52:00 +01:00
Tim Visée
fedebbbf0e
Fix immutable map index mishandling point deletions ( #5346 )
...
* Fix search and delete using subslice index, rather than container intex
* Add sanity checks in debug assertions
* test
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-11-01 19:57:22 +01:00
xzfc
59c2dedcaa
VisitedList: Vec<usize> -> Vec<u8> ( #5336 )
...
* Do not use VisitedListHandle::count_visits_since()
* VisitedList: use u8 instead of usize
* Test VisitedList
2024-10-31 18:26:25 +01:00
dependabot[bot]
95219292ae
build(deps): bump smol_str from 0.3.1 to 0.3.2 ( #5325 )
...
Bumps [smol_str](https://github.com/rust-analyzer/smol_str ) from 0.3.1 to 0.3.2.
- [Changelog](https://github.com/rust-analyzer/smol_str/blob/master/CHANGELOG.md )
- [Commits](https://github.com/rust-analyzer/smol_str/compare/v0.3.1...v0.3.2 )
---
updated-dependencies:
- dependency-name: smol_str
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-29 10:54:04 +01:00
Arnaud Gourlay
d06e8d0e89
Distance matrix leverages HasVector condition ( #5317 )
2024-10-27 10:17:42 +01:00
Andrey Vasnetsov
633d996e61
HasVector filtering condition ( #5303 )
...
* include vector storage into struct vector index
* implement has_vector
* generate schemas
* refactor query filter optimizer so avoid too many function arguments
* test + fix for sparse vectors
* Update lib/segment/src/index/struct_payload_index.rs
Co-authored-by: Jojii <15957865+JojiiOfficial@users.noreply.github.com >
* Update lib/segment/src/index/query_optimization/optimizer.rs
Co-authored-by: Jojii <15957865+JojiiOfficial@users.noreply.github.com >
* fmt
---------
Co-authored-by: Jojii <15957865+JojiiOfficial@users.noreply.github.com >
2024-10-25 18:47:03 +02:00
Kumar Shivendu
31ce928fcf
Track vector storage usage in bytes for each of the segments ( #5292 )
...
* Track disk usage for each of the vectors and segments
* Dont extend vector_data field
* Remove comment and improve var name
* Introduce vectors_size_bytes and rename available_size_in_bytes
* Introduce vectors_size_bytes and rename available_size_in_bytes
* fix linter
* Avoid converting to u64
* calculate vectors_size_bytes for proxy segments
* Fix OpenAPI spec
* fix typo
2024-10-25 15:09:31 +05:30
Jojii
98ef428878
Hw counter utilization checks ( #5288 )
...
* Enforce usage of hardware counter values
* improve comments
* log a warning in release mode
* some minor improvements
* avoid cloning for hardware counter
* fmt
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-10-25 09:52:18 +02:00
Arnaud Gourlay
fb2b6a116d
Allocate less rocksdb options ( #5309 )
2024-10-24 16:40:56 +02:00
Arnaud Gourlay
e55abe662d
[perf] No backtrace on sparse vector index version mismatch ( #5305 )
2024-10-24 12:31:48 +02:00
Arnaud Gourlay
c1ce1ab6ef
[perf] Do not reallocate RocksDB write_options ( #5301 )
2024-10-23 20:00:03 +02:00
Arnaud Gourlay
6f1ef42907
Promote criterion to workspace ( #5291 )
2024-10-22 16:29:23 +02:00
Jojii
669cc4f895
Cpu measurements for dense vector + custom sparse scorer ( #5261 )
...
* add measurements for dense vector and custom sparse scorer
* adjust sparse vector scoring cpu measurement
* review suggestions
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-10-22 14:46:17 +02:00
Arnaud Gourlay
90cd35a196
Promote ordered-float to workspace ( #5285 )
2024-10-22 10:45:38 +02:00
dependabot[bot]
6905cf2b4e
build(deps): bump io-uring from 0.7.0 to 0.7.1 ( #5273 )
...
Bumps [io-uring](https://github.com/tokio-rs/io-uring ) from 0.7.0 to 0.7.1.
- [Commits](https://github.com/tokio-rs/io-uring/commits )
---
updated-dependencies:
- dependency-name: io-uring
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-22 09:04:30 +02:00
dependabot[bot]
1558e7dfcd
build(deps): bump ordered-float from 4.3.0 to 4.4.0 ( #5277 )
...
Bumps [ordered-float](https://github.com/reem/rust-ordered-float ) from 4.3.0 to 4.4.0.
- [Release notes](https://github.com/reem/rust-ordered-float/releases )
- [Commits](https://github.com/reem/rust-ordered-float/compare/v4.3.0...v4.4.0 )
---
updated-dependencies:
- dependency-name: ordered-float
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-22 08:52:40 +02:00
Arnaud Gourlay
a822b4bb31
Remove forgotten eprintln ( #5262 )
2024-10-18 16:31:53 +02:00
Jojii
5696543123
Add CPU measurement for multivectors ( #5241 )
...
* Add CPU measurement for multivectors
* add further test sparse vector search
* make updating vector_query_context consistent
* review fix + take element type into consideration
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-10-18 09:58:02 +02:00
Jojii
73a785f145
Add HardwareCounterCell + CPU measurement for sparse vector search ( #5239 )
...
* Add HardwareCounterCell and counting for sparse plain search
* Add measurement for indexed sparse vector
* add tests for calculations
* move SegmentQueryContent higher in the call stack
* move hardware counters inside the query context
* fix clippy
* Fix applying hardware measurements and add test for this
---------
Co-authored-by: generall <andrey@vasnetsov.com >
2024-10-17 16:24:13 +02:00
Arnaud Gourlay
4d83c198c0
Do not create errors eagerly ( #5254 )
2024-10-17 12:28:48 +02:00
Arnaud Gourlay
e85a336b79
Remove unused dependencies ( #5247 )
2024-10-16 11:23:08 +02:00
Arnaud Gourlay
90d3d57483
[perf] Do not capture backtrace on get_sparse_vector_opt ( #5219 )
...
* Do not capture backtrace on get_sparse_vector_opt
* clean import
2024-10-15 11:07:01 +02:00
Arnaud Gourlay
3de4e107d4
fix lints for Clippy 1.82 ( #5229 )
...
* fix lints for Clippy 1.82
* regen openapi
2024-10-14 13:13:58 +02:00
Arnaud Gourlay
2e0f72364f
Payload storage can include files in snapshots ( #5214 )
2024-10-14 09:26:19 +02:00
Andrey Vasnetsov
a74b7807bc
handle the case of empty geo hashes ( #5222 )
2024-10-11 21:05:27 +02:00
Arnaud Gourlay
aa6dbbfb82
Promote iter function to payload storage interface ( #5205 )
2024-10-10 13:38:48 +02:00
Arnaud Gourlay
29df805470
Fix typo in RocksDB wrapper type ( #5207 )
2024-10-09 14:18:32 +02:00
Andrey Vasnetsov
e0d507dac7
Inference interface in REST and gRPC ( #5165 )
...
* include document & image objects into grpc API
* introduce image and object to rest api
* minor refactoring
* rename Vector -> VectorInternal
* decompose vector data structures
* add schema
* fmt
* grpc docs
* fix conversion
* fix clippy
* fix another conversion
* rename VectorInput -> VectorInputInternal
* replace grpc TryFrom with async functions
* fmt
* replace rest TryFrom with async functions
* add image and object into query rest
* separate inference related conversions
* move json-related conversions into a separate file
* move vector-related transformations into a separate file
* move more vector related-conversions into dedicated module
2024-10-09 10:15:46 +02:00
dependabot[bot]
e0b5968677
build(deps): bump sysinfo from 0.31.4 to 0.32.0 ( #5197 )
...
Bumps [sysinfo](https://github.com/GuillaumeGomez/sysinfo ) from 0.31.4 to 0.32.0.
- [Changelog](https://github.com/GuillaumeGomez/sysinfo/blob/master/CHANGELOG.md )
- [Commits](https://github.com/GuillaumeGomez/sysinfo/compare/v0.31.4...v0.32.0 )
---
updated-dependencies:
- dependency-name: sysinfo
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-08 09:31:32 +02:00
dependabot[bot]
42eecc3ac4
build(deps): bump procfs from 0.16.0 to 0.17.0 ( #5193 )
...
Bumps [procfs](https://github.com/eminence/procfs ) from 0.16.0 to 0.17.0.
- [Release notes](https://github.com/eminence/procfs/releases )
- [Commits](https://github.com/eminence/procfs/compare/v0.16.0...v0.17.0 )
---
updated-dependencies:
- dependency-name: procfs
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-08 09:30:07 +02:00
Ivan Pleshkov
080352cc56
mmap geo index api ( #5163 )
...
* define mmap geo index
fix compilation
deleted flags
load new mmap
geo index tests
fix tests
fix build after rebase
add files list
* refactor get_stored_sub_regions output type
* review remanings
* mmap geo index api
* fix after rebase
2024-10-07 14:35:17 +02:00
Ivan Pleshkov
e00bd70f9c
Mmap geo index ( #4841 )
...
* define mmap geo index
fix compilation
deleted flags
load new mmap
geo index tests
fix tests
fix build after rebase
add files list
* are you happy fmt
* refactor get_stored_sub_regions output type
* repr(C) for geohash
* Replace manual flattening with flat map iterator
* review remanings
* remove panics
* add files for snapshot
* rename Dynamic into InMemory
* are you happy fmt
* review renames
* Use copied rather than cloned
* minor review refactoring + comments
---------
Co-authored-by: timvisee <tim@visee.me >
Co-authored-by: generall <andrey@vasnetsov.com >
2024-10-07 12:08:58 +02:00
xzfc
761069bc0a
Restore SnapshotFormat::Streamable snapshots ( #5179 )
2024-10-04 16:39:56 +00:00
xzfc
98c4e605ae
Support SnapshotFormat::Streamable, add REST endpoint ( #5178 )
2024-10-04 16:36:19 +00:00
xzfc
bc2104604c
Introduce SnapshotFormat ( #5175 )
2024-10-04 16:09:30 +00:00
xzfc
7932286709
Update tar_ext::BuilderExt ( #5112 )
...
* tar_ext::BuilderExt: generalize and add drop workaround
- Generalize: instead of taking `std::fs::File`, take
`impl Write + Seek`.
- Add a workaround for drop: `tar::Builder<W>::drop` might panic if the
underlying writer panics when using in async context.
* Drop unnecessary write_fn usage
* tar_ext::BuilderExt: support both seekable and streaming variants
* tar_ext::BuilderExt: support both owned/borrowed variants
2024-10-04 14:10:09 +00:00
Luis Cossío
045779233a
Facets: Support for bool payload ( #5100 )
...
* enable faceting with boolean index
* test and fix
* also test uuid
2024-10-01 09:17:50 -03:00
dependabot[bot]
3b2110fe6c
build(deps): bump io-uring from 0.6.4 to 0.7.0 ( #5158 )
...
Bumps [io-uring](https://github.com/tokio-rs/io-uring ) from 0.6.4 to 0.7.0.
- [Commits](https://github.com/tokio-rs/io-uring/commits )
---
updated-dependencies:
- dependency-name: io-uring
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-01 10:15:34 +02:00
dependabot[bot]
a5cebd8eef
build(deps): bump rstest from 0.22.0 to 0.23.0 ( #5159 )
...
Bumps [rstest](https://github.com/la10736/rstest ) from 0.22.0 to 0.23.0.
- [Release notes](https://github.com/la10736/rstest/releases )
- [Changelog](https://github.com/la10736/rstest/blob/master/CHANGELOG.md )
- [Commits](https://github.com/la10736/rstest/compare/v0.22.0...v0.23.0 )
---
updated-dependencies:
- dependency-name: rstest
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-01 10:13:09 +02:00
dependabot[bot]
52db80a292
build(deps): bump ordered-float from 4.2.2 to 4.3.0 ( #5154 )
...
Bumps [ordered-float](https://github.com/reem/rust-ordered-float ) from 4.2.2 to 4.3.0.
- [Release notes](https://github.com/reem/rust-ordered-float/releases )
- [Commits](https://github.com/reem/rust-ordered-float/compare/v4.2.2...v4.3.0 )
---
updated-dependencies:
- dependency-name: ordered-float
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-01 09:19:46 +02:00
Jojii
8980483416
[Strict mode] Merge StrictMode config types ( #5137 )
...
* merge StrictModeConfig and StrictModeConfigDiff into one type
* review remarks
2024-09-26 12:36:39 +02:00
Jojii
791d064bde
[Strict mode] default config ( #5037 )
...
* add default config for strict mode
* add default values as example to config/config.yaml
* improve implementation
* update grpc docs
2024-09-25 14:22:36 +02:00
Arnaud Gourlay
d527ab9cd0
Promote atomicwrites to workspace ( #5135 )
2024-09-24 09:44:12 +02:00
dependabot[bot]
6b73ac1791
build(deps): bump charabia from 0.9.0 to 0.9.1 ( #5125 )
...
Bumps [charabia](https://github.com/meilisearch/charabia ) from 0.9.0 to 0.9.1.
- [Release notes](https://github.com/meilisearch/charabia/releases )
- [Commits](https://github.com/meilisearch/charabia/compare/v0.9.0...v0.9.1 )
---
updated-dependencies:
- dependency-name: charabia
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-09-23 21:27:12 +02:00
dependabot[bot]
f6246b0e44
build(deps): bump atomicwrites from 0.4.3 to 0.4.4 ( #5130 )
...
Bumps [atomicwrites](https://github.com/untitaker/rust-atomicwrites ) from 0.4.3 to 0.4.4.
- [Commits](https://github.com/untitaker/rust-atomicwrites/compare/0.4.3...0.4.4 )
---
updated-dependencies:
- dependency-name: atomicwrites
dependency-type: direct:production
update-type: version-update:semver-patch
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-09-23 21:24:50 +02:00