* Add `match: { substring }` filter condition
Unindexed `text` and `text_any` matching became token-aware in #10341 and
#10593. Users who relied on the old raw substring behaviour get it back as
an explicit condition: `match: { "substring": "..." }` selects points with a
string value containing the given string, byte-wise and case-sensitive,
consistent with exact keyword and prefix matching.
Execution: a keyword index (with or without the `prefix` option) serves the
condition by scanning its value dictionary and uniting the postings of the
matching keys; cardinality reuses the prefix estimator, generalised into
`keys_union_cardinality`. The per-point checker goes through the forward
index. Without a keyword index the condition falls back to reading the
payload. Text, bool, integer and uuid indexes decline it.
Strict mode: the condition requires the `KeywordMatch` capability, so with
`unindexed_filtering_retrieve: false` it is rejected on unindexed and on
text-indexed fields and allowed on any keyword index.
API: `MatchSubstring` in the REST `Match` union with regenerated OpenAPI,
gRPC `Match.substring = 12`, edge python `MatchSubstring`, edge ffi
`Match::Substring`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* Test substring fallback on a text-indexed field, document estimator params
A text index cannot serve `substring`, so on a field that has only a text
index the condition runs through the payload fallback; only strict mode may
reject it. Pin that in the OpenAPI suite and reword the strict-mode unit
test comment, which read as if the text index itself blocked the query.
Also spell out what `keys` and `postings` mean in `keys_union_cardinality`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* Serve `match: { substring }` from the keyword key dictionary
The condition used to enumerate keys through `MapIndexRead::for_each_value`,
which on the on-disk variant drags the whole `value_to_points` file through
`for_each_entry`, plus one random read per matching key for its postings
count. Query planning paid that scan in full, before deciding whether to use
the clause at all.
Route it through the `prefix_index.bin` key dictionary instead: front-coded
keys with their postings counts inline, no postings. Estimation now reads
keys only and never touches `value_to_points`; filtering takes the matched
key list and resolves postings in one batched read, as prefix matching
already does.
This makes the `prefix` option a requirement: a keyword index without it has
no key dictionary, so it declines the condition and falls back to the payload
scan, the same as a text index. Strict mode follows — substring now infers
`KeywordPrefix`, so `unindexed_filtering_retrieve: false` names
`keyword (with prefix: true)` as the index to create.
`PrefixIndex::for_each_key` reads blocks in ~1 MiB chunks rather than the
whole key section at once: a substring cannot be pruned by the block index,
so the one-shot read would grow with the dictionary.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Sync MatchSubstring OpenAPI description with Rust docs
After routing substring matching through the prefix key dictionary,
the schema docstring required regenerating so OpenAPI stays consistent.
* Scan the map index keys for substring match without a dictionary
Without the keyword dictionary a substring condition was declined by the
field index and left to the per-point condition checker, which reads the
forward index for every candidate point. Enumerate the distinct keys of
`values_to_points` instead: the same one-pass-over-distinct-values shape as
the dictionary scan, only over a structure that interleaves keys with their
postings. Filtering and cardinality estimation are then always served, so
the condition can act as a primary clause on a plain keyword index.
Prefix matching keeps its per-point fallback: an ordered dictionary is what
makes a prefix a bounded range, and enumerating every key to answer one is
not a trade worth making implicitly.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Reject substring matching in strict mode
A substring condition is answered by looking at every distinct value of the
field: no index gives it a bounded access path, so there is no index a user
could create to make it affordable. Reject it under strict mode instead,
wherever a filter reaches verification — read and write filters, nested
sub-filters, and prefetch filters.
Filter limits are now checked before the unindexed-field check, so the
rejection is not reported as "create an index for this key", advice that
would lead to the same rejection afterwards.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Update the strict mode substring test to the new rejection
The test asserted that substring filtering under strict mode asks for a
keyword index with the `prefix` option. It is now rejected whatever index
the field carries, so every case in the test gets the same answer.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Estimate a substring condition without scanning
Counting the keys a substring matches costs the same scan as answering the
condition, and `filter` then repeats it to collect those keys. Report the
uninformed estimate instead — the one an unindexed condition has always
reported — and keep the primary clause, so the scan happens once, in
`filter`, and only when the planner picks the condition to drive iteration.
With no counts to collect, `substring_scan` collapses into `substring_keys`:
the in-RAM variants no longer look up a posting count per matched key.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Don't to parse everything as UTF-8
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: qdrant-cloud-bot <111755117+qdrant-cloud-bot@users.noreply.github.com>
Co-authored-by: timvisee <tim@visee.me>
Follow-up to #10287, which added `max`. Expressing a minimum still
required spelling out `(a + b - |a - b|) / 2`, the sign flip of the max
identity — drop the `neg` and you silently get a maximum instead. It also
only works for two operands and mentions each one twice, so the scorer
walks every sub-tree twice per candidate point.
The pair is what makes clamping expressible:
{"max": [0.0, {"min": [1.0, "$score"]}]}
`min` mirrors `max` throughout, and both guard helpers introduced in
#10287 already took an `operator: &str`, so they are reused unchanged: an
empty operand list is rejected at parse time rather than folding to
+infinity, and the Edge FFI rejects it at construction time. The result
needs no `is_finite` check, since `min` cannot produce a non-finite value
from finite inputs.
The unindexed-field walker shares one arm for `Max | Min` as the bodies
are identical, with a test pinning `min` separately so a later split
cannot silently drop it.
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: add a dedicated max operator to score formulas
Expressing a maximum in a score formula required spelling out the
arithmetic identity `(a + b + |a - b|) / 2`. That is easy to get wrong
(the `/ 2` is load-bearing), only works for two operands, and mentions
each operand twice, so the scorer evaluates every sub-tree twice per
candidate point.
`max` is variadic, mirroring `sum` and `mult`:
{"max": ["$score", {"mult": [0.5, "popularity"]}]}
Unlike `sum` and `mult`, `max` has no identity element for the empty
case, so an empty operand list is rejected at parse time rather than
folding to -infinity and scoring every point with a non-finite value.
The check lives in `ExpressionInternal::parse_and_convert`, which every
entry point passes through, and the Edge FFI additionally rejects it at
construction time to match how that crate validates elsewhere.
The result needs no `is_finite` check: unlike `log10`, `exp`, `div`,
`sqrt` and `pow`, `max` cannot produce a non-finite value from finite
inputs, so it follows the existing `sum` convention.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: cover max error propagation and datetime operands
An operand that fails must fail the whole expression rather than being
passed over in favour of a finite sibling. Covered with the failure both
before and after the finite operand: `mult` short-circuits on zero and
so can skip evaluating later operands, and this pins down that `max`
must not grow a similar shortcut that would swallow an error.
Also covers `max` over datetime operands, which reach the scorer through
a separate conversion to seconds, so that "score by whichever timestamp
is newer" is verified rather than assumed.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Unary inverse hyperbolic cosine, parallel to sqrt/ln/exp/log10, in REST,
gRPC, and edge (FFI + Python) interfaces. Inputs below 1 produce the same
NonFiniteNumber error as an invalid sqrt or ln.
Closes#10186
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feat(edge): add query_batch for batched planned queries
Expose the planned-query batch path as a public API so multiple
independent queries can share one planning pass over leaf searches
and scrolls. Wired through EdgeShardRead, FFI, and Python bindings.
Co-authored-by: Cursor <cursoragent@cursor.com>
* perf(edge): push batched query vectors down to segments
`query_batch` planned the whole batch at once but then executed every leaf
search on its own: one query context, one fan-out over all segments, and one
single-vector `Segment::search_batch` call per leaf.
Execute the batch as a batch instead:
- `EdgeReadView::search_batch` builds the query context once, visits the
segments once, and hands each segment the leaves that agree on everything
but their query vector as a single multi-vector `search_batch` call.
`search` is now a thin wrapper over a one-element batch.
- Move `SearchType`/`BatchSearchParams` from `collection`'s segments searcher
into `shard`, next to `CoreSearchRequest`, and add `group_search_batches`
so both the collection and the edge read path share one grouping
implementation. Edge computes the grouping once and reuses it per segment.
- `search_matrix` now issues its per-sample nearest queries through
`query_batch`; they share filter, limit and vector name, so the whole
sample is scored in one batched search per segment instead of one full
segment pass per sampled point.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: generall <andrey@vasnetsov.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: pin per-shard search pool to a core
* fix: plumb search_pool_core through bindings
* feat: expose search_pool_core in python bindings
* fix: validate search pool core before pinning
* chore: trim comments
* Add per-query IDF corpus for sparse vector search
Let the caller choose, per query, which population sparse IDF statistics
are computed over. `params.idf` is either `"global"` (default, unchanged
behavior) or `{"corpus": <filter>}`, where the corpus filter is
independent of - and usually broader than - the retrieval filter.
Decoupling the two keeps the score scale stable when the retrieval
filter tightens: term importance is measured against a population the
user names, not against whatever subset the filter happens to select.
Design decisions:
- Corpus grammar is restricted to a conjunction (`must`) of `match`
conditions on payload fields; loosening later is backward compatible.
- Strict mode validates the corpus filter like a read filter
(unindexed fields rejected).
- `idf` on a vector without the IDF modifier is a validation error,
never silently ignored.
- An empty corpus yields degenerate but corpus-scoped scores (smoothed
IDF over N=0), never a fallback to global statistics - in multi-tenant
collections a fallback would leak term statistics across tenants.
Implementation:
- QueryContext IDF stats are keyed by corpus, so one batch can mix
requests with different corpora.
- Statistics come from the sparse index: df(term) is counted over the
query terms' posting lists only, never by scanning stored vectors.
Small corpora (under ~1/32 of the segment, by cardinality estimate)
are kept as a sorted id list galloping through posting lists via
skip_to; large ones as a dense membership mask filled streaming from
the filtered-points iterator. A misestimated small corpus degrades
into the mask.
- Exposed uniformly: REST (`params.idf`), gRPC (`IdfParams` message),
edge python bindings; OpenAPI schema regenerated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Apply rustfmt
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix clippy manual_is_multiple_of in sparse IDF corpus test.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Allow any filter as IDF corpus
Drop the must+match grammar restriction on the corpus filter. A
restriction enforced only as a validation step over the full Filter
type buys nothing; if a narrower corpus syntax is ever wanted, it
should be a dedicated API-level type instead.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix build: add memory field to SparseIndexConfig in idf corpus test
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: root <111755117+qdrant-cloud-bot@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Tunable EdgeConfig parameters (on_disk_payload, hnsw_config, optimizers)
are now Option, and every tunable resolves through the fallback chain
provided -> persisted -> derived from segments -> default when loading
an existing shard. Leaving a parameter unspecified keeps the shard as it
is; an explicit value overwrites it and existing segments converge to it
through the optimizers.
vectors/sparse_vectors are excluded from overwrite semantics: an empty
map inherits the persisted/segment-derived definitions, a non-empty map
is validated for compatibility against the loaded segments (size,
distance, multivector, datatype, sparse modifier) and fails the load on
mismatch.
The derived layer folds over all segments in UUID order instead of
taking an arbitrary first segment, so a plain appendable segment (which
carries no HNSW parameters) can never mask an indexed segment's actual
build parameters. Previously a lost edge_config.json could resolve
unspecified HNSW params to compiled-in defaults and silently trigger a
full re-index via ConfigMismatchOptimizer.
The read-only follower accepts an optional config on open: provided
tunables are applied once over the segment-derived config (vectors
always come from the segments), and refresh re-derives from segments
alone.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Add prefix matching option to keyword index
Introduce an opt-in `prefix` option for the keyword payload index and a
new `match: { "prefix": ... }` filter condition, enabling efficient
byte-wise prefix filtering over keyword values (e.g. URL prefixes,
web-ui value autocompletion via facet + prefix filter).
Index side: a new `prefix_index.bin` file stores a sorted, front-coded
key dictionary with a resident block index (cumulative counts per
block); it is an ordered view over the keys of `values_to_points.bin`
and stores no postings. Presence of the file signals prefix support at
load time, so legacy segments load unchanged and enabling the option
goes through the standard incompatible-schema rebuild. The mutable
variant keeps an in-RAM ordered key set (not persisted), the immutable
variant builds a sorted key vector at load, and the on-disk variant
reads the dictionary lazily (block index resident, 1-2 block reads per
prefix lookup; reader is generic over UniversalRead).
Query side: prefix conditions are served from the dictionary when
available (filter + cardinality estimation from per-block aggregates),
from the forward index as per-point checks, and degrade to the payload
full-scan fallback otherwise - same execution model as other match
conditions. Strict mode (`unindexed_filtering_*`) rejects prefix
queries on fields without a prefix-enabled keyword index via a new
KeywordPrefix capability.
HNSW payload blocks: prefix-enabled indexes additionally emit prefix
blocks for heavy branching trie nodes (single-child chains collapsed to
their longest common prefix, one block per distinct point set, emitted
largest-first) so filtered search with prefix conditions gets navigable
subgraphs without rebuilding the same subset repeatedly.
API: `prefix` flag on KeywordIndexParams (REST bool, gRPC empty
message for extensibility), `prefix` variant in the Match oneof, edge
python bindings, regenerated OpenAPI spec.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Split prefix index into a dedicated module, fix clippy in tests
Reorganize the flat prefix_index.rs / prefix_read.rs into a
map_index/prefix_index/ module: format.rs (on-disk layout primitives),
writer.rs, reader.rs (PrefixIndex), map_read.rs (StrMapIndexPrefixRead
with per-variant impls) and tests.rs, with a file-format diagram and a
read-path walkthrough in the module docs. No logic changes.
Also fix clippy --all-targets complaints in test code: replace a
wildcard Match arm with an exhaustive list and a field-reassign-with-
default with a struct literal.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Add OpenAPI test for prefix match and snapshot file-tracking test
- tests/openapi/test_prefix_match.py: index-less fallback, prefix index
creation with schema echo, scroll/count parity against ground truth,
facet + prefix filter (the autocompletion flow), strict-mode rejection
without the prefix capability.
- test_prefix_index_file_tracking: `prefix_index.bin` is listed in
`files()` / `immutable_files()` exactly when built with the option.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Replace hand-rolled varint parsing with bytemuck Pod records
Per review: the prefix index format now uses fixed-size little-endian
Pod records (BlockEntry 24 B, KeyEntry 12 B, Header 40 B) written with
bytemuck::bytes_of and read back by copy via pod_read_unaligned — no
manual varint encode/decode, no alignment requirement, one shared
read_record helper. Costs ~9 bytes per key on disk versus LEB128; the
raw key bytes dominate dictionary size, so the simplification wins.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Fetch the whole candidate block range with a single storage read
Candidate key blocks of a prefix lookup are contiguous in the file, so
enumerate them from one ranged read instead of one read per block; the
over-read versus the exact key range is bounded by the two boundary
blocks. Block decoding is split into a storage-free helper reused by
the per-block path of stats estimation.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Align prefix payload blocks with the geo index granularity principle
Geo's large_hashes emits only the smallest geohash regions above the
threshold — a disjoint antichain, never a parent nested with its
children. Prefix payload blocks now follow the same rule: a heavy
collapsed trie node is emitted only if nothing heavy is nested inside
it, counting both deeper qualifying prefixes and single heavy values
(which already get their own exact-match blocks). Emitted blocks are
therefore mutually disjoint and disjoint from exact-value blocks; no
near-collection-sized ancestor subgraphs, no reliance on the HNSW
connectivity check to skip nested duplicates.
Implemented as a `covered` flag propagated through the existing
LCP-interval scan, still one O(total key bytes) pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Document block wire format and unaligned-read rationale in decode_block
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* perf(edge): load ReadOnlyEdgeShard segments in parallel
Open each segment on a dedicated thread during initial open and refresh,
reducing follower startup time for shards with many segments.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(edge): resolve clippy type_complexity in parallel segment load
Co-authored-by: Cursor <cursoragent@cursor.com>
* perf(edge): run per-segment reads on a configurable thread pool
Replace the per-segment sequential read loops and the spawn-a-thread-per-segment
loader with a single fixed-size rayon thread pool owned by each shard.
- Add EdgeConfig::max_search_threads (Option<usize>, None = CPU-derived default
matching the core search runtime via common::defaults::search_thread_count).
- Build a long-lived pool in EdgeShard and ReadOnlyEdgeShard; reuse it for
parallel segment loading on open/refresh instead of std::thread::spawn.
- Add EdgeReadView::par_map_segments as the single seam that runs per-segment
work on the pool; use it in search, scroll, count, facet and rescore-formula.
Each task mints its own HardwareCounterCell from the shared accumulator.
- Expose max_search_threads through the builder and the Python binding (+ stub).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(edge): return error instead of panicking on search pool creation
ThreadPoolBuilder::build() can fail (e.g. thread spawn / resource exhaustion).
This runs during EdgeShard open/load and ReadOnlyEdgeShard follower open, so a
transient failure must not abort the process. Propagate it as an OperationError
through the existing OperationResult-returning constructors.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: generall <andrey@vasnetsov.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(bm25): add explicit Disabled stemmer; deprecate language hack
Adds a `Disabled` variant to `StemmingAlgorithm` (`stemmer: {"type": "none"}`)
so stemming can be turned off explicitly in both the main engine and Edge,
instead of relying on the undocumented `language: "none"` footgun that
silently disabled both stemming and stopwords.
For language-neutral text processing the supported setup is now:
1. set the stemmer to disabled, and
2. configure an empty stopword set.
The main engine still tolerates unsupported languages (so existing
`language: "none"` configs keep working on upgrade) but now logs a
deprecation warning pointing users to the explicit setup. Edge continues
to reject unsupported languages, and now has a real way to disable stemming.
Refs: https://github.com/qdrant/qdrant/issues/9289
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(edge-py): handle Disabled stemmer in python bindings; fix openapi schema
- Handle the new StemmingAlgorithm::Disabled variant in the qdrant-edge-py
bindings (FromPyObject/IntoPyObject/Repr) and add a DisabledStemmer pyclass
plus its .pyi stub entry.
- Match generator output for the StemmingAlgorithm OpenAPI schema (plain $ref
in anyOf) so docs/redoc/master/openapi.json stays consistent.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(openapi): regenerate StemmingAlgorithm schema with generator output
Ran tools/generate_openapi_models.sh so docs/redoc/master/openapi.json
exactly matches generator output: DisabledStemmerParams/NoStemmer are placed
after SnowballLanguage, and the StemmingAlgorithm anyOf entry is a plain $ref
(the schema2openapi step flattens the allOf+description wrapper).
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(test): avoid wildcard enum match arm in bm25 sparse_len helper
clippy --all-targets flags `other => panic!()` as wildcard_enum_match_arm;
match the Dense/MultiDense variants explicitly instead.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: issues
* fix: log::warn as call once
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Daniel Boros <dancixx@gmail.com>
The previous description was outdated: it claimed that enabling this
option "blocks updates at the request level" until segments are
re-optimized. In practice the implementation uses "deferred points":
new points written to large unoptimized segments are persisted but
excluded from read/search results until the segments are optimized.
Updates are not blocked; only `wait=true` clients are made to wait for
the deferred points to become visible. Update this in the REST schema
(via `OptimizersConfig` / `OptimizersConfigDiff`), in the gRPC proto,
in the edge config docstrings, and regenerate the OpenAPI bundle via
`tools/generate_openapi_models.sh`.
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add empty placeholder vector storage types for named vector CRUD
Introduce EmptyDenseVectorStorage and EmptySparseVectorStorage as
placeholder storages for newly created named vectors on immutable
segments. These report all vectors as deleted, consume no disk space,
and are reconstructed from segment config on load via the new
VectorStorageType::Empty and SparseVectorStorageType::Empty variants.
Key design decisions:
- is_on_disk is derived from original user config, not hardcoded
- MultiVectorConfig is preserved for multi-vector support
- Config mismatch optimizer skips Empty storage to avoid false rebuilds
- Quantization delegates normally (handles 0 vectors gracefully)
- get_vector includes debug_assert to catch unexpected access
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* [AI] segment-level operations for creating and deleting anmed vectors
* [AI] implement named vector creation and deleting in proxy segment
* [AI] Step 3: Proxy Segment Handling for Named Vector Operations
* [AI] implement for Edge
* [AI] implement consensus operations for named vector operations
* [AI] refactor VectorNameConfig, remove VectorNameConfigInternal
* [AI] handle vector schema inconsistency in raft snapshot recovery
* [AI] rest + grpc API
* [AI] clippy
* [AI] generate openAPI schema
* fmt
* ci fixes
* [AI] fix jwt access test
* [AI] nop operation for awaiting of consensus-commited update ops
* [AI] move vector name operations into points service
* [AI] implement internal api for vector name operations
* [AI] change collection-level config along with segment level operation
* [AI] vector schema reconceliation instead of error
* fmt
* missing compile-time option
* [AI] integration test
* [AI] fix missing JWT tests
* [AI] remove NOP
* [AI] openapi test
* [AI] fix initialization of mutable segment
* [AI] more simple integration tests
* fmt
* [AI] make cluster test a bit harder
* [AI] make test less flacky
* [AI] rabbit comments
* [AI] check params compatibility before writing vector config
* [AI] make sure to register vector storages in structure payload index
* [AI] vector name validation
* lower vector length validation to 200 chars to account for prefix in filename
* [AI] proxy segment: prevent stale data leak through optimization
* fmt
* [AI] filter out removed vectors from proxy response
* [AI] handle vector name in proxy
* fmt
* adjust proxy info based on dropped vectors
* [AI] proxy segment: update filters to correct has_vector condition
* fmt
* clippy
* Fix consensus snapshot applicaiton for vector schema
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(edge): split EdgeShard load into new() and load()
- new(path, config): create edge shard only when path has no existing segments
- load(path, config?): load from existing files; config optional (load from
edge_config.json or infer from segments)
- Helpers: has_existing_segments, ensure_dirs_and_open_wal, resolve_initial_config,
load_segments, ensure_appendable_segment
- Python: EdgeShard.create_new(path, config); __init__ still calls load()
- Examples use new() for creation and load(path, None) for reopen
- Error instead of panic on config mismatch; explicit load/create in Python
- fix: use OptimizerThresholds.deferred_internal_id for dev compatibility
Made-with: Cursor
* rollback threshold changes
* fix(edge): address dancixx review comments
- Persist inferred config in load() when edge_config.json does not exist
(SaveOnDisk::new only saves when file exists)
- Python: add #[new] delegating to load() for backward compatibility
- qdrant_edge.pyi: Optional return types for deleted_threshold,
vacuum_min_vector_number, default_segment_number; add __init__ doc
Made-with: Cursor
* Revert "fix(edge): address dancixx review comments"
This reverts commit 370e21a6c74c41210e1658f89814395cb86ed81c.
* fix: optional returns
* fix: save config it is not exist
* fix: save data on disk always
* fix: python examples
* chore: remove edge.close()
* fix: wal lock
* fix: rename of EdgeShardConfig -> EdgeConfig
---------
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
Co-authored-by: Daniel Boros <dancixx@gmail.com>
* 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>
* weighted rrf implementation
* test
* fmt
* fix edge
* validate number of sources and number of weights
* do not partial match
* upd schema
* review fixes
* update formula
* remove calcualtions from tests
* update comment, because AI have OCD
* fmt
* introduce update_mode parameter for upsert operation to control if we want to insert, update, or upsert
* add test
* upd dockstring
* require resharding once all peers have updated version
* use service error
* fix clippy again
* wait for same version before resharding in tests
* 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>
xzfc