qdrant_client.local.qdrant_local module

class QdrantLocal(location: str, force_disable_check_same_thread: bool = False)

Bases: QdrantBase

Everything Qdrant server can do, but locally.

Use this implementation to run vector search without running a Qdrant server. Everything that works with local Qdrant will work with server Qdrant as well.

Use for small-scale data, demos, and tests. If you need more speed or size, use Qdrant server.

batch_update_points(collection_name: str, update_operations: Sequence[Union[UpsertOperation, DeleteOperation, SetPayloadOperation, OverwritePayloadOperation, DeletePayloadOperation, ClearPayloadOperation, UpdateVectorsOperation, DeleteVectorsOperation]], **kwargs: Any) → List[UpdateResult]

clear_payload(collection_name: str, points_selector: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], **kwargs: Any) → UpdateResult

close(**kwargs: Any) → None

collection_exists(collection_name: str, **kwargs: Any) → bool

count(collection_name: str, count_filter: Optional[Union[Filter, Filter]] = None, exact: bool = True, **kwargs: Any) → CountResult

create_collection(collection_name: str, vectors_config: Union[VectorParams, Mapping[str, VectorParams]], init_from: Optional[Union[InitFrom, str]] = None, sparse_vectors_config: Optional[Mapping[str, SparseVectorParams]] = None, **kwargs: Any) → bool

create_full_snapshot(**kwargs: Any) → SnapshotDescription

create_payload_index(collection_name: str, field_name: str, field_schema: Optional[Union[PayloadSchemaType, KeywordIndexParams, IntegerIndexParams, FloatIndexParams, GeoIndexParams, TextIndexParams, BoolIndexParams, DatetimeIndexParams, UuidIndexParams, int, PayloadIndexParams]] = None, field_type: Optional[Union[PayloadSchemaType, KeywordIndexParams, IntegerIndexParams, FloatIndexParams, GeoIndexParams, TextIndexParams, BoolIndexParams, DatetimeIndexParams, UuidIndexParams, int, PayloadIndexParams]] = None, **kwargs: Any) → UpdateResult

create_shard_key(collection_name: str, shard_key: Union[int[int], str[str]], shards_number: Optional[int] = None, replication_factor: Optional[int] = None, placement: Optional[List[int]] = None, **kwargs: Any) → bool

create_shard_snapshot(collection_name: str, shard_id: int, **kwargs: Any) → Optional[SnapshotDescription]

create_snapshot(collection_name: str, **kwargs: Any) → Optional[SnapshotDescription]

delete(collection_name: str, points_selector: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], **kwargs: Any) → UpdateResult

delete_collection(collection_name: str, **kwargs: Any) → bool

delete_full_snapshot(snapshot_name: str, **kwargs: Any) → bool

delete_payload(collection_name: str, keys: Sequence[str], points: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], **kwargs: Any) → UpdateResult

delete_payload_index(collection_name: str, field_name: str, **kwargs: Any) → UpdateResult

delete_shard_key(collection_name: str, shard_key: Union[int[int], str[str]], **kwargs: Any) → bool

delete_shard_snapshot(collection_name: str, shard_id: int, snapshot_name: str, **kwargs: Any) → bool

delete_snapshot(collection_name: str, snapshot_name: str, **kwargs: Any) → bool

delete_vectors(collection_name: str, vectors: Sequence[str], points: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], **kwargs: Any) → UpdateResult

discover(collection_name: str, target: Optional[Union[int[int], str[str], List[float[float]], SparseVector, TargetVector]] = None, context: Optional[Sequence[Union[ContextExamplePair, ContextExamplePair]]] = None, query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, offset: int = 0, with_payload: Union[bool, List[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, List[str]] = False, using: Optional[str] = None, lookup_from: Optional[Union[LookupLocation, LookupLocation]] = None, consistency: Optional[Union[int[int], ReadConsistencyType]] = None, timeout: Optional[int] = None, **kwargs: Any) → List[ScoredPoint]

discover_batch(collection_name: str, requests: Sequence[Union[DiscoverRequest, DiscoverPoints]], **kwargs: Any) → List[List[ScoredPoint]]

facet(collection_name: str, key: str, facet_filter: Optional[Union[Filter, Filter]] = None, limit: int = 10, exact: bool = False, **kwargs: Any) → FacetResponse

get_aliases(**kwargs: Any) → CollectionsAliasesResponse

get_collection(collection_name: str, **kwargs: Any) → CollectionInfo

get_collection_aliases(collection_name: str, **kwargs: Any) → CollectionsAliasesResponse

get_collections(**kwargs: Any) → CollectionsResponse

get_locks(**kwargs: Any) → LocksOption

info() → VersionInfo

list_full_snapshots(**kwargs: Any) → List[SnapshotDescription]

list_shard_snapshots(collection_name: str, shard_id: int, **kwargs: Any) → List[SnapshotDescription]

list_snapshots(collection_name: str, **kwargs: Any) → List[SnapshotDescription]

lock_storage(reason: str, **kwargs: Any) → LocksOption

overwrite_payload(collection_name: str, payload: Dict[str, Any], points: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], **kwargs: Any) → UpdateResult

query_batch_points(collection_name: str, requests: Sequence[Union[QueryRequest, QueryPoints]], **kwargs: Any) → List[QueryResponse]

query_points(collection_name: str, query: Optional[Union[NearestQuery, RecommendQuery, DiscoverQuery, ContextQuery, OrderByQuery, FusionQuery, SampleQuery]] = None, using: Optional[str] = None, prefetch: Optional[Union[Prefetch, List[Prefetch]]] = None, query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, offset: Optional[int] = None, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, score_threshold: Optional[float] = None, lookup_from: Optional[Union[LookupLocation, LookupLocation]] = None, **kwargs: Any) → QueryResponse

query_points_groups(collection_name: str, group_by: str, query: Optional[Union[int, str, PointId, List[float], List[List[float]], SparseVector, NearestQuery, RecommendQuery, DiscoverQuery, ContextQuery, OrderByQuery, FusionQuery, SampleQuery, ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], Document]] = None, using: Optional[str] = None, prefetch: Optional[Union[Prefetch, List[Prefetch]]] = None, query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, group_size: int = 3, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, score_threshold: Optional[float] = None, with_lookup: Optional[Union[str[str], WithLookup]] = None, lookup_from: Optional[Union[LookupLocation, LookupLocation]] = None, **kwargs: Any) → GroupsResult

recommend(collection_name: str, positive: Optional[Sequence[Union[int[int], str[str], List[float[float]], SparseVector]]] = None, negative: Optional[Sequence[Union[int[int], str[str], List[float[float]], SparseVector]]] = None, query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, offset: int = 0, with_payload: Union[bool, List[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, List[str]] = False, score_threshold: Optional[float] = None, using: Optional[str] = None, lookup_from: Optional[Union[LookupLocation, LookupLocation]] = None, strategy: Optional[RecommendStrategy] = None, **kwargs: Any) → List[ScoredPoint]

recommend_batch(collection_name: str, requests: Sequence[Union[RecommendRequest, RecommendPoints]], **kwargs: Any) → List[List[ScoredPoint]]

recommend_groups(collection_name: str, group_by: str, positive: Optional[Sequence[Union[int, str, PointId, List[float]]]] = None, negative: Optional[Sequence[Union[int, str, PointId, List[float]]]] = None, query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, group_size: int = 1, score_threshold: Optional[float] = None, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, using: Optional[str] = None, lookup_from: Optional[Union[LookupLocation, LookupLocation]] = None, with_lookup: Optional[Union[str[str], WithLookup]] = None, strategy: Optional[RecommendStrategy] = None, **kwargs: Any) → GroupsResult

recover_shard_snapshot(collection_name: str, shard_id: int, location: str, **kwargs: Any) → bool

recover_snapshot(collection_name: str, location: str, **kwargs: Any) → bool

recreate_collection(collection_name: str, vectors_config: Union[VectorParams, Mapping[str, VectorParams]], init_from: Optional[Union[InitFrom, str]] = None, sparse_vectors_config: Optional[Mapping[str, SparseVectorParams]] = None, **kwargs: Any) → bool

retrieve(collection_name: str, ids: Sequence[Union[int, str, PointId]], with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, **kwargs: Any) → List[Record]

scroll(collection_name: str, scroll_filter: Optional[Union[Filter, Filter]] = None, limit: int = 10, order_by: Optional[Union[str[str], OrderBy, OrderBy]] = None, offset: Optional[Union[int, str, PointId]] = None, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, **kwargs: Any) → Tuple[List[Record], Optional[Union[int, str, PointId]]]

search(collection_name: str, query_vector: Union[ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], Sequence[float], Tuple[str, List[float]], NamedVector, NamedSparseVector], query_filter: Optional[Union[Filter, Filter]] = None, search_params: Optional[Union[SearchParams, SearchParams]] = None, limit: int = 10, offset: Optional[int] = None, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude, WithPayloadSelector] = True, with_vectors: Union[bool, Sequence[str]] = False, score_threshold: Optional[float] = None, **kwargs: Any) → List[ScoredPoint]

search_batch(collection_name: str, requests: Sequence[Union[SearchRequest, SearchPoints]], **kwargs: Any) → List[List[ScoredPoint]]

search_groups(collection_name: str, query_vector: Union[ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], Sequence[float], Tuple[str, List[float]], NamedVector], group_by: str, query_filter: Optional[Filter] = None, search_params: Optional[SearchParams] = None, limit: int = 10, group_size: int = 1, with_payload: Union[bool, Sequence[str], PayloadSelectorInclude, PayloadSelectorExclude] = True, with_vectors: Union[bool, Sequence[str]] = False, score_threshold: Optional[float] = None, with_lookup: Optional[Union[str[str], WithLookup]] = None, **kwargs: Any) → GroupsResult

search_matrix_offsets(collection_name: str, query_filter: Optional[Union[Filter, Filter]] = None, limit: int = 3, sample: int = 10, using: Optional[str] = None, **kwargs: Any) → SearchMatrixOffsetsResponse

search_matrix_pairs(collection_name: str, query_filter: Optional[Union[Filter, Filter]] = None, limit: int = 3, sample: int = 10, using: Optional[str] = None, **kwargs: Any) → SearchMatrixPairsResponse

set_payload(collection_name: str, payload: Dict[str, Any], points: Union[List[Union[int, str, PointId]], Filter, Filter, PointIdsList, FilterSelector, PointsSelector], key: Optional[str] = None, **kwargs: Any) → UpdateResult

unlock_storage(**kwargs: Any) → LocksOption

update_collection(collection_name: str, sparse_vectors_config: Optional[Mapping[str, SparseVectorParams]] = None, **kwargs: Any) → bool

update_collection_aliases(change_aliases_operations: Sequence[Union[CreateAliasOperation, RenameAliasOperation, DeleteAliasOperation, AliasOperations]], **kwargs: Any) → bool

update_vectors(collection_name: str, points: Sequence[PointVectors], **kwargs: Any) → UpdateResult

upload_collection(collection_name: str, vectors: Union[Dict[str, ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]], ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], Iterable[Union[List[float[float]], List[List[float[float]]], Dict[str[str], Union[List[float[float]], SparseVector, List[List[float[float]]], Document]], Document]]], payload: Optional[Iterable[Dict[Any, Any]]] = None, ids: Optional[Iterable[Union[int, str, PointId]]] = None, **kwargs: Any) → None

upload_points(collection_name: str, points: Iterable[PointStruct], **kwargs: Any) → None

upload_records(collection_name: str, records: Iterable[Record], **kwargs: Any) → None

upsert(collection_name: str, points: Union[Batch, Sequence[Union[PointStruct, PointStruct]]], **kwargs: Any) → UpdateResult

property closed: bool