$j1ddlmZddlmZddlmZddlZddlZddlm Z ddl m Z ddlm Z ddl mZd d lmZmZmZmZejeZddZddZddZddZddZddZddZddZddZd dZ GddeZ!dS)!) annotations)Callable)EnumN)ndarray)pairwise_distances)Tensor)logging)_convert_to_batch_tensor_convert_to_tensornormalize_embeddings to_scipy_cooarbreturnc"t||S) Computes the cosine similarity between two tensors. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Matrix with res[i][j] = cos_sim(a[i], b[j]) )cos_simrrs m/home/rurouni/.hermes/hermes-agent/venv/lib/python3.11/site-packages/sentence_transformers/util/similarity.pypytorch_cos_simrs 1a==list | np.ndarray | Tensorct|}t|}t|}t|}tj||ddS)rrr )r r torchmm transposeto_denserra_normb_norms rrr!sf !##A ##A !! $ $F !! $ $F 8FF,,Q22 3 3 < < > >>rcdt|}t|}|js|jrIt|}t|}||zdSt t|t|S)a Computes the pairwise cosine similarity cos_sim(a[i], b[i]). Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Vector with res[i] = cos_sim(a[i], b[i]) dim)r is_sparser sumrpairwise_dot_scorers rpairwise_cos_simr)4s 1A1A {_ak_%a((%a(($$$,,55777!"6q"9"9;OPQ;R;RSS\\^^^rct|}t|}tj||ddS)a Computes the dot-product dot_prod(a[i], b[j]) for all i and j. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Matrix with res[i][j] = dot_prod(a[i], b[j]) rr )r rrrrrs r dot_scorer+KsJ !##A ##A 8Aq{{1a(( ) ) 2 2 4 44rct|}t|}||zdS)a Computes the pairwise dot-product dot_prod(a[i], b[i]). Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Vector with res[i] = dot_prod(a[i], b[i]) r#r$)r r'rrs rr(r(\sB 1A1A E;;2;   ' ' ) ))rct|}t|}|js|jrtdt |}t |}t ||d}t j|  |j  St j ||d S)a Computes the manhattan similarity (i.e., negative distance) between two tensors. Handles sparse tensors without converting to dense when possible. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Matrix with res[i][j] = -manhattan_distance(a[i], b[j]) z8Using scipy for sparse Manhattan similarity computation. manhattan)metricg?p) r r&logger warning_oncerrr from_numpyfloattodevicercdist)rra_coob_coodists r manhattan_simr<ms !##A ##A{ 4ak 4VWWWQQ!%{CCC&&,,..11!(;;DDFFF AqC(((113333rct|}t|}tjtj||z d S)a< Computes the manhattan similarity (i.e., negative distance) between pairs of tensors. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Vector with res[i] = -manhattan_distance(a[i], b[i]) r#r$)r rr'absrrs rpairwise_manhattan_simr?sP 1A1A IeiA&&B / / / 8 8 : : ::rct|}t|}|jrtj||zdd}tj||zdd}tj||}|d|zz |z}tj |d}tj | Stj ||d S) a Computes the euclidean similarity (i.e., negative distance) between two tensors. Handles sparse tensors without converting to dense when possible. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Matrix with res[i][j] = -euclidean_distance(a[i], b[j]) r r$rg)ming@r0) r r&rsparser'r unsqueezematmultclampsqrtr8)rr a_norm_sq b_norm_sq dot_product squared_dists r euclidean_simrMs! !##A ##A{ )L$$QU$22;;==GGJJ L$$QU$22;;==GGJJ l1accee,,5577 !1{?2Y> {) rPrQrrcdzreimdzdw norm_angles rpairwise_angle_simrfs {$mnnn JJLL ! ! # # JJLL ! ! # #1A1A wqzA~ H  # #AvJa # H H H  # #AvJa # H H ;q! # # #DAq ;q! # # #DAq !Q$A+1d333A a%!a%-1 B a%!a%-1 B 1a4!Q$;At 4 4 4 ;B 1a4!Q$;At 4 4 4 ;B"r'MB"r'MB5<Ra888a@@@J 9Z  rcneZdZdZdZdZdZdZdZe dd Z e dd Z e dd Z dS)SimilarityFunctiona Enum class for supported similarity functions. The following functions are supported: - ``SimilarityFunction.COSINE`` (``"cosine"``): Cosine similarity - ``SimilarityFunction.DOT_PRODUCT`` (``"dot"``, ``dot_product``): Dot product similarity - ``SimilarityFunction.EUCLIDEAN`` (``"euclidean"``): Euclidean distance - ``SimilarityFunction.MANHATTAN`` (``"manhattan"``): Manhattan distance cosinedot euclideanr.similarity_functionstr | SimilarityFunctionr6Callable[[Tensor | ndarray, Tensor | ndarray], Tensor]c2t|}|tjkrtS|tjkrtS|tjkrt S|tjkrtStd|dt d)a Converts a similarity function name or enum value to the corresponding similarity function. Args: similarity_function (Union[str, SimilarityFunction]): The name or enum value of the similarity function. Returns: Callable[[Union[Tensor, ndarray], Union[Tensor, ndarray]], Tensor]: The corresponding similarity function. Raises: ValueError: If the provided function is not supported. Example: >>> similarity_fn = SimilarityFunction.to_similarity_fn("cosine") >>> similarity_scores = similarity_fn(embeddings1, embeddings2) >>> similarity_scores tensor([[0.3952, 0.0554], [0.0992, 0.1570]]) The provided function 4 is not supported. Use one of the supported values: .) rhCOSINEr DOT_PRODUCTr+ MANHATTANr< EUCLIDEANrM ValueErrorpossible_valuesrls rto_similarity_fnz#SimilarityFunction.to_similarity_fns.11DEE "4"; ; ;N "4"@ @ @  "4"> > > "4"> > >  V%8 V VoAoQoQoSoS V V V   rc2t|}|tjkrtS|tjkrtS|tjkrt S|tjkrtStd|dt d)a Converts a similarity function into a pairwise similarity function. The pairwise similarity function returns the diagonal vector from the similarity matrix, i.e. it only computes the similarity(a[i], b[i]) for each i in the range of the input tensors, rather than computing the similarity between all pairs of a and b. Args: similarity_function (Union[str, SimilarityFunction]): The name or enum value of the similarity function. Returns: Callable[[Union[Tensor, ndarray], Union[Tensor, ndarray]], Tensor]: The pairwise similarity function. Raises: ValueError: If the provided similarity function is not supported. Example: >>> pairwise_fn = SimilarityFunction.to_similarity_pairwise_fn("cosine") >>> similarity_scores = pairwise_fn(embeddings1, embeddings2) >>> similarity_scores tensor([0.3952, 0.1570]) rprqrr) rhrsr)rtr(rur?rvrOrwrxrys rto_similarity_pairwise_fnz,SimilarityFunction.to_similarity_pairwise_fn*s411DEE "4"; ; ;# # "4"@ @ @% % "4"> > >) ) "4"> > >) ) V%8 V VoAoQoQoSoS V V V   r list[str]c$dtDS)ad Returns a list of possible values for the SimilarityFunction enum. Returns: list: A list of possible values for the SimilarityFunction enum. Example: >>> possible_values = SimilarityFunction.possible_values() >>> possible_values ['cosine', 'dot', 'euclidean', 'manhattan'] cg|] }|j S)rU).0ms r z6SimilarityFunction.possible_values..`s444A444r)rhrrrrxz"SimilarityFunction.possible_valuesSs54!34444rN)rlrmrrn)rr}) __name__ __module__ __qualname____doc__rsrtDOTrvru staticmethodrzr|rxrrrrhrhsFK CII# # # \# J& & & \& P 5 5 5\ 5 5 5rrh)rrrrrr)rrrrrr)rPrrQrrr)" __future__rcollections.abcrenumrnumpynprrsklearn.metricsrrtransformers.utilsr tensorr r r r get_loggerrr2rrr)r+r(r<r?rMrOrfrhrrrrs""""""$$$$$$ ......&&&&&&dddddddddddd  H % %    ????&____.5555"****"44446;;;;"))))>CCCC"(!(!(!(!Vl5l5l5l5l5l5l5l5l5l5r