qdrant_client.local.distances module

class ContextPair(positive: List[float], negative: List[float])

Bases: object

class ContextQuery(context_pairs: List[ContextPair])

Bases: object

class DiscoveryQuery(target: List[float], context: List[ContextPair])

Bases: object

class DistanceOrder(value)

Bases: str, Enum

An enumeration.

BIGGER_IS_BETTER = 'bigger_is_better'

SMALLER_IS_BETTER = 'smaller_is_better'

class RecoQuery(positive: Optional[List[List[float]]] = None, negative: Optional[List[List[float]]] = None)

Bases: object

calculate_context_scores(query: ContextQuery, vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

calculate_discovery_ranks(context: List[ContextPair], vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

calculate_discovery_scores(query: DiscoveryQuery, vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

calculate_distance(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

calculate_distance_core(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

Calculate same internal distances as in core, rather than the final displayed distance

calculate_recommend_best_scores(query: RecoQuery, vectors: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], distance_type: Distance) → ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]]

cosine_similarity(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: 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]]]

Calculate cosine distance between query and vectors :param query: query vector :param vectors: vectors to calculate distance with

Returns

distances

distance_to_order(distance: Distance) → DistanceOrder

Convert distance to order :param distance: distance to convert

Returns

order

dot_product(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: 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]]]

Calculate dot product between query and vectors :param query: query vector. :param vectors: vectors to calculate distance with

Returns

distances

euclidean_distance(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: 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]]]

Calculate euclidean distance between query and vectors :param query: query vector. :param vectors: vectors to calculate distance with

Returns

distances

fast_sigmoid(x: float32) → float32

manhattan_distance(query: ndarray[Any, dtype[Union[bool_, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, float128]]], vectors: 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]]]

Calculate manhattan distance between query and vectors :param query: query vector. :param vectors: vectors to calculate distance with

Returns

distances

scaled_fast_sigmoid(x: float32) → float32