qdrant_client.local.distances 模块

类 ContextPair(positive: list[float], negative: list[float])

基类: object

类 ContextQuery(context_pairs: list[ContextPair])

基类: object

类 DiscoveryQuery(target: list[float], context: list[ContextPair])

基类: object

类 DistanceOrder(value)

基类: str, Enum

一个枚举。

BIGGER_IS_BETTER = 'bigger_is_better'

SMALLER_IS_BETTER = 'smaller_is_better'

类 RecoQuery(positive: Optional[list[list[float]]] = None, negative: Optional[list[list[float]]] = None, strategy: Optional[RecommendStrategy] = None)

基类: object

calculate_context_scores(query: ContextQuery, vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

calculate_discovery_ranks(context: list[ContextPair], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

calculate_discovery_scores(query: DiscoveryQuery, vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

calculate_distance(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

calculate_distance_core(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

计算与核心相同的内部距离，而不是最终显示的距离

calculate_recommend_best_scores(query: RecoQuery, vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

calculate_recommend_sum_scores(query: RecoQuery, vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], distance_type: Distance) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

cosine_similarity(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

计算查询向量与一组向量之间的余弦距离 :param query: 查询向量 :param vectors: 用于计算距离的向量组

返回:

距离数组

distance_to_order(distance: Distance) → DistanceOrder

将距离转换为排序顺序 :param distance: 要转换的距离

返回:

排序顺序

dot_product(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

计算查询向量与一组向量之间的点积 :param query: 查询向量。 :param vectors: 用于计算距离的向量组

返回:

距离数组

euclidean_distance(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

计算查询向量与一组向量之间的欧氏距离 :param query: 查询向量。 :param vectors: 用于计算距离的向量组

返回:

距离数组

fast_sigmoid(x: float32) → float32

manhattan_distance(query: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]], vectors: ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]) → ndarray[tuple[int, ...], dtype[Union[bool, int8, int16, int32, int64, uint8, uint16, uint32, uint64, float16, float32, float64, longdouble]]]

计算查询向量与一组向量之间的曼哈顿距离 :param query: 查询向量。 :param vectors: 用于计算距离的向量组

返回:

距离数组

scaled_fast_sigmoid(x: float32) → float32