* 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>
* Use `IdTrackerEnum` type instead of `dyn IdTracker`
It would allow to be more flexible on the IdTracker trait, making it
dyn-incompatible eventually.
Coauthored with Claude Code.
* Review fixes
* Unify parking_lot/arc_lock feature
* Move lib/common/{io,memory}/* -> lib/common/common/*
- Mmap-related items are grouped into `common::mmap` sub-module:
- `memory/src/chunked_utils.rs` -> `common/src/mmap/chunked.rs`
- `memory/src/madvise.rs` -> `common/src/mmap/advice.rs`
- `memory/src/mmap_ops.rs` -> `common/src/mmap/ops.rs`
- `memory/src/mmap_type_readonly.rs` -> `common/src/mmap/mmap_readonly.rs`
- `memory/src/mmap_type.rs` -> `common/src/mmap/mmap_rw.rs`
- Filesystem-related items are grouped into `common::fs` sub-module:
- `common/src/fs.rs` -> `common/src/fs/sync.rs`
- `io/src/file_operations.rs` -> `common/src/fs/ops.rs`
- `io/src/move_files.rs` -> `common/src/fs/move.rs`
- `io/src/safe_delete.rs` -> `common/src/fs/safe_delete.rs`
- `memory/src/checkfs.rs` -> `common/src/fs/check.rs`
- `memory/src/fadvise.rs` -> `common/src/fs/fadvise.rs`
- Rest is moved straight into `common`:
- `io/src/storage_version.rs` -> `common/src/storage_version.rs`
The old `io` and `memory` are now hollow crates that re-export items
from `common`. These hollow crates will be removed in next commits.
* Replace uses of `io` and `memory` with new paths in `common`
Since `io` and `memory` are just re-exports of `common`, these
replacements are no-op.
* Remove `io` and `memory` crates
* 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>
* download tar
* compute sha256 for stream download
* wip: propagate unpacking into down to the logic, todo: validation
* unpacked snapshot validation
* Minor tweaks
* Fix typo
* validation during unpack
* cancellation token
* update docstring
* remove redundant dep
* Rearrange unpack functions
- Rename `safe_unpack.rs` into `tar_unpack.rs` so it would be listed
near `tar_ext.rs` in IDEs.
- Replace calls like `ar = open_snapshot_archive(…); safe_unpack(ar, …);`
with a single call to `tar_unpack_file(…)`.
- Put calls to `Archive::new(); Archive::set_overwrite(false);` inside
`tar_unpack_reader` (was `safe_unpack`). So, now it is the only place
that does `set_overwrite`.
* Let clippy complain if tar::Archive::unpack used
* Mock snapshot download URL
Instead of downloading from storage.googleapis.com every time the test
runs, put small snapshot file to the repo.
The snapshot file is created using this command:
curl -s \
https://storage.googleapis.com/qdrant-benchmark-snapshots/test-shard.snapshot \
| tar \
--delete segments/4ea958d8-0b64-4312-9a53-0cd857e93535.tar \
--delete segments/65ac6276-8cca-4f5c-b767-9722190cee8b.tar \
> lib/storage/src/content_manager/snapshots/test-shard.snapshot
File contents:
$ tar tf lib/storage/src/content_manager/snapshots/test-shard.snapshot
wal/
wal/closed-255
newest_clocks.json
replica_state.json
shard_config.json
$ du -sh lib/storage/src/content_manager/snapshots/test-shard.snapshot
12K lib/storage/src/content_manager/snapshots/test-shard.snapshot
$ sha256sum < lib/storage/src/content_manager/snapshots/test-shard.snapshot
5d94eac5c1ede3994a28bc406120046c37370d5d45b489a0d2252531b4e3e1f2 -
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: xzfc <xzfcpw@gmail.com>
* WIP: introduce new vector store type
* handling of InRamMmap
* fmt
* feature-flag
* fmt
* Use if else
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
* Update lib/common/common/src/flags.rs
Co-authored-by: Tim Visée <tim+github@visee.me>
* also choose madvise for single-file in-ram-mmap
* simplify generics
* gpu fix
* fix bug
---------
Co-authored-by: Tim Visée <tim+github@visee.me>
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
* feat: Add enable_hnsw option for payload field indexes
Add optional enable_hnsw parameter to all payload index types to control
whether additional HNSW graph links are built for each indexed field.
- Add enable_hnsw field to all 8 payload index param types
- Update gRPC proto definitions and conversions
- Update OpenAPI schema
- Modify HNSW graph builder to respect enable_hnsw flag
- Add enable_hnsw() helper methods to PayloadSchemaParams and PayloadFieldSchema
- Update all tests to include new field (default: None)
When enable_hnsw is true and payload_M > 0, additional HNSW links will
be built for the payload field. Default value is true for backward compatibility.
* Fix Some format problems
* fix: address comment problem
---------
Co-authored-by: EC2 Default User <ec2-user@ip-10-78-171-148.ec2.internal>
* Replace `Option<Segment>` with `enum LoadSegmentOutcome`
* Replace some Path/PathBuf with str/String
* Rename field Segment::{current_path -> segment_path}
* safe_delete
* Add progress_tracker.rs
* Pass progress tracker around
* Populate progress tracker with actual data
* Expose progress on `/collections/{name}/optimizations` endpoint
* add stopflag check into query_points of payload index
* propagate stopflag more
* fmt
* bench: compare better against no atomic
* use stoppable iter with IteratorExt
* clippy
* Add cancelled error helper
---------
Co-authored-by: Luis Cossío <luis.cossio@outlook.com>
Co-authored-by: timvisee <tim@visee.me>
* flush all segments in one thread sequentially
* bonus: move flush-related functions into dedicated file
* Minor comment tweaks
* await for flush on segment holder level
* fmt
* Minor improvement, preallocate vector for payload index flushers
* Remove invalid comment
---------
Co-authored-by: timvisee <tim@visee.me>
* WIP: make proxy segment non-appendable
* make deleted points and index changes private to Proxy Segment
* consistently remove empty unused segment from holder on unproxifying and the end of optimization
* remove/fix obsolete test
* Fix comment, some general adjustments
* Also don't remove non-original segments
* Use ahash for map of proxy index changes
* Inline format arguments
* Simplify has point branching
* Assert that proxy flushes to latest wrapped segment version
* make vector deletetion a CoW operation
* relax debug assertions
* Update lib/shard/src/proxy_segment/mod.rs
* fix test_partial_snapshot_empty
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Tim Visée <tim+github@visee.me>
* Create and load for an appendable quantization
remove feature flag
more todo
review remarks
review remarks
* fix after rebase
* Rename is_appendable to supports_appendable
---------
Co-authored-by: timvisee <tim@visee.me>
* Enable Gridstore payload index storage, rename storage types
* Respect payload_index_skip_mutable_rocksdb feature flag
* Minor cleanup
* Fix map payload index Gridstore semantics, only create files if desired
The semantics of backing storages in payload indices are inconsistent.
This aligns the Gridstore backing storage to our RocksDB backing
storage, matching the create/open/load behavior. Now, it will only
create Gridstore files on disk if we request it to do so.
This commit only implements it on the map index. In following comments
the same will be implemented in all other payload indices too.
* Apply same Gridstore semantics to other payload index types
* Rename create parameter to create_if_missing
* Fix bench compilation errors
* bq encodings
* are you happy clippy
* are you happy clippy
* are you happy clippy
* are you happy clippy
* gpu tests
* update models
* are you happy fmt
* move additional bits to the end
* fix tests
* Welford's Algorithm
* review remarks
* are you happy clippy
* remove debug println in test
* coderabit nitpicks
* remove unnecessary clone and partialeq
* Use f64 for Welford's Algorithm
* try fix ci
* revert cargo-nextest
* add debug assertions
* Use sparse vector storage fixture without RocksDB
* Fix some tests
* Replace RocksDB sparse storage with Gristore in mutable text index tests
* Use in-memory vector storage in multivector HNSW test
* Flag many more RocksDB specifics in tests
* Use database placeholder type without RocksDB flag
* Flag more tests
* Flag even more tests
* Fix imports, fix typo, and repair base test build
* Initialize dummy database if RocksDB flag is disabled
* Assert correct storage types
* Don't use old vector storage type when RocksDB is disabled
* Expos default for vector storage type only in tests
* Only expose simple segment constructor in tests
* Don't derive Default
* Fix inverted appendable flag
* Add function to open all multi dense vector storage types
* Move list files function into common crate
* Add function to find appendable multi dense storage files without opening it
* Actively migrate away from RocksDB based multi dense vector storage
* Add test for simple multi dense vector storage migration
* Also migrate vector deletes for multi dense storage
* take max_point_offset into consideration
* add null index even if index selector is for rocksdb
* fmt
* better cardinality estimation, check deleted inside filtered iter
* fix count indexed points, add primary conditions to estimator
* use len for count_indexed_points, adjust test
* remove deleted check from filtered iter
* cleaner removal
* Pass FeatureFlags into VectorIndexBuildArgs
* Incremental HNSW index building: append-only case
* Use debug_assert
* first_few_ids
* Check deleted_point_count
* Drop unused method
* Add in rest and grpc
* add to QueryEnum
* implement Query trait
* connect to scorer creation
* upd tests
* additional changes
* fmt
* gen openapi and grpc docs
* coderabbit fix
* add changes in async scorer
* test sum_scores in more places, refactor to remove repetition
* Cardinality estimation measurements
* Apply hw measurements to latest changes from dev
* Clippy
* Also measure cardinality estimation for geo index
* Make measured units 'bytes'
* Use PointOffsetType instead of u32 for size calculation
* fix memory cost for check_values_any in mmap index
* fix double counting for value reading in mmap, remove hw_counter from mmap hashmap
* fmt
* fix hw measurement for text index
* Remove non necessary lifetime annotations
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* create initial strucutres
* clippy
* start field-query refactoring
* start field-query refactoring (2/N)
* start field-query refactoring (3/N): duplicate is_empty/null condiftions as field condition
* start field-query refactoring (4/N): re-instate is_empty fallback in case new index is not built yet
* filter for is_empty/is_null
* implement add/remove point
* upd schema
* open and create of null-index
* create null-index
* fix test
* Update lib/segment/src/index/query_optimization/condition_converter.rs
Co-authored-by: Tim Visée <tim+github@visee.me>
* unit test for null-index
* more unit tests
* add openapi tests
* fmt
* fix for integartion tests
* rabbit review fix
* make [null] non-empty
---------
Co-authored-by: Tim Visée <tim+github@visee.me>
