* Introduce EdgeShardConfig for edge shard
- Add EdgeShardConfig and EdgeOptimizersConfig in lib/edge/src/config.rs
- Segment config (vector_data, sparse_vector_data, payload_storage_type)
- Global hnsw_config and per-vector HNSW in segment config
- Optimizer params: deleted_threshold, vacuum_min_vector_number,
default_segment_number, max_segment_size, indexing_threshold,
prevent_unoptimized (excludes memmap_threshold, flush_interval_sec,
max_optimization_threads)
- Persist/load as edge_config.json in shard path
- EdgeShard uses RwLock<EdgeShardConfig>; load() accepts Option<EdgeShardConfig>,
falls back to file or infer from segments; compatibility checked on load
- load_with_segment_config() for backward compatibility (SegmentConfig -> EdgeShardConfig)
- optimize() uses EdgeShardConfig for hnsw and optimizer thresholds
- Public methods: set_hnsw_config(), set_vector_hnsw_config(), set_optimizers_config()
(update and persist)
- Python and examples use load_with_segment_config with existing config API
Made-with: Cursor
* Refactor EdgeShardConfig: user-facing params only, config module
- Replace SegmentConfig inside EdgeShardConfig with user-facing fields:
- on_disk_payload (bool) instead of payload_storage_type
- vectors: HashMap<VectorNameBuf, EdgeVectorParams> with on_disk per vector,
no per-vector quantization; global quantization_config only
- sparse_vectors: HashMap<VectorNameBuf, EdgeSparseVectorParams> with on_disk
- EdgeVectorParams / EdgeSparseVectorParams use on_disk (bool) instead of
storage_type; conversion to VectorDataConfig/SparseVectorDataConfig in
to_segment_config()
- Add config module: mod.rs, optimizers.rs, vectors.rs, shard.rs
- from_segment_config(&SegmentConfig) fills all inferrable params
- to_segment_config() builds SegmentConfig for segments and optimize()
- load_with_segment_config takes Option<SegmentConfig>, uses from_segment_config
Made-with: Cursor
* Move optimizer threshold helpers to shard crate
- Add get_number_segments, get_indexing_threshold_kb, get_max_segment_size_kb,
get_deferred_points_threshold_bytes in shard::optimizers::config
- Collection OptimizersConfig and edge EdgeOptimizersConfig delegate to these
- Single place for threshold logic; collection and edge use shard helpers
Made-with: Cursor
* Use destructuring in config conversions to avoid missing new fields
- EdgeVectorParams: destructure VectorDataConfig in from_*, destructure self in to_vector_data_config
- EdgeSparseVectorParams: destructure SparseVectorDataConfig and SparseIndexConfig in from_*, destructure self in to_sparse_vector_data_config
- EdgeShardConfig: destructure SegmentConfig in from_segment_config, destructure self in to_segment_config
Adding new fields to source structs will now cause compile errors until conversions are updated.
Made-with: Cursor
* refactor: centralize on_disk_payload→payload_storage_type, on_disk→storage_type, and appendable quantization logic
- PayloadStorageType::from_on_disk_payload(bool) in segment (Mmap/InRamMmap)
- VectorStorageType::from_on_disk(bool) in segment (ChunkedMmap/InRamChunkedMmap)
- QuantizationConfig::for_appendable_segment(Option<&Self>) in segment (feature flag + supports_appendable)
- collection: use from_on_disk_payload in non-rocksdb branch
- edge shard/vectors: use new helpers; remove duplicated conditionals
- shard optimizers: use from_on_disk and for_appendable_segment
Made-with: Cursor
* refactor(edge): use EdgeShardConfig directly, drop segment_config
- Add plain_segment_config() for create_appendable_segment (no HNSW)
- Add segment_optimizer_config() built from EdgeShardConfig for blocking optimizers
- Add vector_data_config(name) for query/MMR
- build_blocking_optimizers: use segment_optimizer_config() instead of SegmentConfig
- create_appendable_segment: use plain_segment_config()
- search/query: use config().vectors and vector_data_config() instead of segment_config()
- Remove segment_config() from EdgeShardConfig and EdgeShard
- Add to_plain_vector_data_config on EdgeVectorParams
Made-with: Cursor
* [manual] review changes
* refactor(edge-py): wrap EdgeShardConfig, add EdgeVectorParams/EdgeSparseVectorParams
- PyEdgeConfig now wraps EdgeShardConfig (vectors, sparse_vectors, on_disk_payload, etc.)
- PyEdgeVectorParams / PyEdgeSparseVectorParams wrap edge config types
- PyEdgeOptimizersConfig for optional optimizer settings
- EdgeShard.load() uses EdgeShardConfig; edge::config made pub for Python crate
- cargo fmt + clippy (remove map_identity)
Made-with: Cursor
* refactor(edge-py): simplify config API, remove unused Py* types, add EdgeConfig
- Remove unused PyPayloadStorageType, PyVectorDataConfig, PyVectorStorageType,
PySparseVectorDataConfig, PySparseVectorStorageType from Python bindings
- Move PyEdgeOptimizersConfig to lib/edge/python/src/config/optimizers.rs
- Update qdrant_edge.pyi: EdgeConfig with vectors/sparse_vectors,
EdgeVectorParams, EdgeSparseVectorParams, EdgeOptimizersConfig
- Update examples (common.py, repr.py) to use new config API
- Run cargo fmt
Made-with: Cursor
* [manual] review changes
* [manual] review changes
* [manual] fix test
* Address CodeRabbit review comments for PR 8322 (#8324)
* Address CodeRabbit review comments for PR 8322
- Python examples: explicit imports (repr.py, common.py) and new EdgeConfig API
- HnswIndexConfig: add max_indexing_threads param and property in .pyi and Rust bindings
- EdgeConfig: make vectors optional for sparse-only configs; validate at least one of vectors/sparse_vectors
- EdgeShardConfig::load: use try_exists(), propagate I/O errors
- from_segment_config: infer hnsw_config from per-vector HNSW when all agree
- EdgeShard setters: atomic clone-mutate-save-then-replace; persist config save errors
- Segment compat: prefix vector name in error messages; resolve None datatype to Float32
- max_indexing_threads: preserve 0 (auto) sentinel in trait default; remove per-optimizer overrides
- SegmentOptimizerConfig:🆕 build plain and optimizer maps in single pass
- config_mismatch_optimizer tests: use VectorNameBuf::from() instead of .into()
- vectors.rs: doc updates for per-vector quantization
Made-with: Cursor
* Address @generall review: SaveOnDisk for config, resolve num_rayon_threads in optimizer
- Use SaveOnDisk<EdgeShardConfig> for EdgeShard config (generall: 'We have SaveOnDisk struct for this')
- Create via SaveOnDisk::new() after resolving config; setters use .write() for atomic persist
- set_vector_hnsw_config: clone then mutate then write (fallible setter)
- max_indexing_threads: resolve 0 (auto) via num_rayon_threads inside impl (generall: 'proper solution would be to resolve num_rayon_threads inside the optimizer impl')
- max_indexing_threads_sentinel_aware() now returns Some(num_rayon_threads(raw)) so callers get actual thread count
Made-with: Cursor
* [manual] reorganize num_rayon_threads -> get_num_indexing_threads to better account per-vector configuration
---------
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: generall <andrey@vasnetsov.com>
* update docstring and pyi
* fmt
* fmt
* clipy
---------
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: generall <andrey@vasnetsov.com>
* Split `SegmentEntry`
Add `ImmutableSegmentEntry` for operations that can be applied to
immutable segments, and make the `SegmentEntry` as it subtrait.
* Rename to `NonAppendableSegmentEntry`
It differs semantically from `ImmutableSegmentEntry` by allowing point
deletion. Move point deletion to the trait too.
* Fix docstring
* use NonAppendableSegmentEntry where possible
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* Add progress_tracker.rs
* Pass progress tracker around
* Populate progress tracker with actual data
* Expose progress on `/collections/{name}/optimizations` endpoint
* Pass FeatureFlags into VectorIndexBuildArgs
* Incremental HNSW index building: append-only case
* Use debug_assert
* first_few_ids
* Check deleted_point_count
* Drop unused method
* Bump Rust edition to 2024
* gen is a reserved keyword now
* Remove ref mut on references
* Mark extern C as unsafe
* Wrap unsafe function bodies in unsafe block
* Geo hash implements Copy, don't reference but pass by value instead
* Replace secluded self import with parent
* Update execute_cluster_read_operation with new match semantics
* Fix lifetime issue
* Replace map_or with is_none_or
* set_var is unsafe now
* Reformat
* rename cpu_budget -> resource_budget
* clippy
* add io budget to resources
* fmt
* move budget structures into a separate file
* add extend permit function
* dont extend existing permit
* switch from IO to CPU permit
* do not release resource before aquiring an extension
* fmt
* Review remarks
* Improve resource permit number assertion
* Make resource permit replace_with only acquire extra needed permits
* Remove obsolete drop implementation
* allocate IO budget same as CPU
* review fixes
---------
Co-authored-by: timvisee <tim@visee.me>
* Measure read io for payload storage
* Add Hardware Counter to update functions
* Fix tests and benches
* Rename (some) *_measured functions back to original
* 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>
* drop some code
* Drop JsonPathString
* Fix test_remove_key
Drop failing tests:
- Deleting array indices is not idempotent, so we don't support it.
- Empty JSONPath is not supported.
* Make json_path::path() non-generic
* Remove references to JsonPathV2
* Drop JsonPathInterface
* Move json_path::v2 code into json_path
* Drop validate_not_empty
* Drop JsonPath::head() as being unused
* Replace path() with JsonPath::new()
* Restore comments
* Move tests to json_path
* Use json() consistently in tests
* Replace many into calls with Into trait
---------
Co-authored-by: timvisee <tim@visee.me>
* Move build_index out of VectorIndex
* Build index in HNSWIndex::open()
* Introduce HnswIndexOpenArgs
* Proper deletion
* Improve tests
* HNSW::open(): add warn, comment and assert
* Revert to making up the config if it does not exist
* introduce QueryContext, which accumulates runtime info needed for executing search
* fmt
* propagate query context into segment internals
* [WIP] prepare idf stats for search query context
* Split SparseVector and RemmapedSparseVector to guarantee we will not mix them up on the type level
* implement filling of the query context with IDF statistics
* implement re-weighting of the sparse query with idf
* fmt
* update idf param only if explicitly specified (more consistent with diff param update
* replace idf bool with modifier enum, improve further extensibility
* test and fixes
* Update lib/collection/src/operations/types.rs
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* review fixes
* fmt
---------
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* byte storage with quantization
raw scorer integration
config and test
are you happy fmt
fn renamings
cow refactor
use quantization branch
quantization update
* are you happy clippy
* don't use distance in quantized scorers
* fix build
* add fn quantization_preprocess
* apply preprocessing for only cosine float metric
* fix sparse vectors tests
* update openapi
* more complicated integration test
* update openapi comment
* mmap byte storages support
* fix async test
* move .unwrap closer to the actual check of the vector presence
* fmt
* remove distance similarity function
* avoid copying data while working with cow
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* move check for unindexed segment size inside the segment to allow proxy shard decide where to search better
* fmt
* move indexed_only check inside the plain index
* Multivec knob for SegmentConfig
* regen openapi
* add TODO for next step
* introduce multivecconfig to support more similarity aggregation
* update openapi
* Move CPU count function to common, fix wrong CPU count in visited list
* Change default number of rayon threads to 8
* Use CPU budget and CPU permits for optimizer tasks to limit utilization
* Respect configured thread limits, use new sane defaults in config
* Fix spelling issues
* Fix test compilation error
* Improve breaking if there is no CPU budget
* Block optimizations until CPU budget, fix potentially getting stuck
Our optimization worker now blocks until CPU budget is available to
perform the task.
Fix potential issue where optimization worker could get stuck. This
would happen if no optimization task is started because there's no
available CPU budget. This ensures the worker is woken up again to
retry.
* Utilize n-1 CPUs with optimization tasks
* Better handle situations where CPU budget is drained
* Dynamically scale rayon CPU count based on CPU size
* Fix incorrect default for max_indexing_threads conversion
* Respect max_indexing_threads for collection
* Make max_indexing_threads optional, use none to set no limit
* Update property documentation and comments
* Property max_optimization_threads is per shard, not per collection
* If we reached shard optimization limit, skip further checks
* Add remaining TODOs
* Fix spelling mistake
* Align gRPC comment blocks
* Fix compilation errors since last rebase
* Make tests aware of CPU budget
* Use new CPU budget calculation function everywhere
* Make CPU budget configurable in settings, move static budget to common
* Do not use static CPU budget, instance it and pass it through
* Update CPU budget description
* Move heuristic into defaults
* Fix spelling issues
* Move cpu_budget property to a better place
* Move some things around
* Minor review improvements
* Use range match statement for CPU count heuristics
* Systems with 1 or 2 CPUs do not keep cores unallocated by default
* Fix compilation errors since last rebase
* Update lib/segment/src/types.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Update lib/storage/src/content_manager/toc/transfer.rs
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Rename cpu_budget to optimizer_cpu_budget
* Update OpenAPI specification
* Require at least half of the desired CPUs for optimizers
This prevents running optimizations with just one CPU, which could be
very slow.
* Don't use wildcard in CPU heuristic match statements
* Rename cpu_budget setting to optimizer_cpu_budget
* Update CPU budget comments
* Spell acquire correctly
* Change if-else into match
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
* Rename max_rayon_threads to num_rayon_threads, add explanation
* Explain limit in update handler
* Remove numbers for automatic selection of indexing threads
* Inline max_workers variable
* Remove CPU budget from ShardTransferConsensus trait, it is in collection
* small allow(dead_code) => cfg(test)
* Remove now obsolete lazy_static
* Fix incorrect CPU calculation in CPU saturation test
* Make waiting for CPU budget async, don't block current thread
* Prevent deadlock on optimizer signal channel
Do not block the optimization worker task anymore to wait for CPU budget
to be available. That prevents our optimizer signal channel from being
drained, blocking incoming updates because the cannot send another
optimizer signal. Now, prevent blocking this task all together and
retrigger the optimizers separately when CPU budget is available again.
* Fix incorrect CPU calculation in optimization cancel test
* Rename CPU budget wait function to notify
* Detach API changes from CPU saturation internals
This allows us to merge into a patch version of Qdrant. We can
reintroduce the API changes in the upcoming minor release to make all of
it fully functional.
---------
Co-authored-by: Luis Cossío <luis.cossio@qdrant.com>
Co-authored-by: Luis Cossío <luis.cossio@outlook.com>
* add enum for vector query on segment search
* rename newly introduced types
* fix: handle QueryVector on async scorer
* handle QueryVector in QuantizedVectors impl
* fix async scorer test after refactor
* rebase + refactor on queue_proxy_shard.rs
* constrain refactor propagation to segment_searcher
* fmt
* fix after rebase
* 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
