#i1 ddlmZddlmZddlmZddlZddlZddlm Z ddl m Z ddlm Z ddl mZd d lmZmZmZmZej(eZdd Zdd Zdd ZddZddZddZddZddZddZddZ GddeZ!y)) annotations)Callable)EnumN)ndarray)pairwise_distances)Tensor)logging)_convert_to_batch_tensor_convert_to_tensornormalize_embeddings to_scipy_cooct||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_simabs v/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/sentence_transformers/util/similarity.pypytorch_cos_simrs 1a=ct|}t|}t|}t|}tj||j ddj S)rrr )r r torchmm transposeto_denserra_normb_norms rrr!sS !#A #A !! $F !! $F 88FF,,Q2 3 < < >>rc(t|}t|}|js |jr9t|}t|}||zjdj St t|t|j 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 {{akk%a(%a($$$,5577!"6q"9;OPQ;RS\\^^rct|}t|}tj||jddj S)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)Ks= !#A #A 88Aq{{1a( ) 2 2 44rctt|}t|}||zjdjS)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&\s6 1A1A E;;2;  ' ' ))rct|}t|}|js |jrtjdt |}t |}t ||d}t j| jj|jjSt j||dj 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{{akkVWQQ!%{C&,,.11!((;DDFF AqC(11333rct|}t|}tjtj||z dj 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=sB 1A1A IIeiiA&B / 8 8 : ::rclt|}t|}|jrtjj ||zdj j d}tjj ||zdj j d}tj||jj }|d|zz |z}tj|d}tj|j 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@r.) r r$rsparser%r unsqueezematmultclampsqrtr6)rr a_norm_sq b_norm_sq dot_product squared_dists r euclidean_simrKs !#A #A{{LL$$QU$2;;=GGJ LL$$QU$2;;=GGJ ll1acce,557 !1{?2Y> {{>> 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: .) rfCOSINEr DOT_PRODUCTr) MANHATTANr: EUCLIDEANrK ValueErrorpossible_valuessimilarity_functions rto_similarity_fnz#SimilarityFunction.to_similarity_fns.11DE "4";"; ;N "4"@"@ @  "4">"> > "4">"> > $%8$99moAoQoQoSnTTU V  rc(t|}|tjk(rtS|tjk(rtS|tj k(rt S|tjk(rtStd|dtjd)a Converts a similarity function into a pairwise similarity function. The pairwise similarity function returns the diagonal vector from the similarity matrix, i.e. it only computes the similarity(a[i], b[i]) for each i in the range of the input tensors, rather than computing the similarity between all pairs of a and b. Args: similarity_function (Union[str, SimilarityFunction]): The name or enum value of the similarity function. Returns: Callable[[Union[Tensor, ndarray], Union[Tensor, ndarray]], Tensor]: The pairwise similarity function. Raises: ValueError: If the provided similarity function is not supported. Example: >>> pairwise_fn = SimilarityFunction.to_similarity_pairwise_fn("cosine") >>> similarity_scores = pairwise_fn(embeddings1, embeddings2) >>> similarity_scores tensor([0.3952, 0.1570]) rkrlrm) rfrnr'ror&rpr=rqrMrrrsrts rto_similarity_pairwise_fnz,SimilarityFunction.to_similarity_pairwise_fn*s411DE "4";"; ;# # "4"@"@ @% % "4">"> >) ) "4">"> >) )$%8$99moAoQoQoSnTTU V  rcHtDcgc]}|jc}Scc}w)ad Returns a list of possible values for the SimilarityFunction enum. Returns: list: A list of possible values for the SimilarityFunction enum. Example: >>> possible_values = SimilarityFunction.possible_values() >>> possible_values ['cosine', 'dot', 'euclidean', 'manhattan'] )rfrQ)ms rrsz"SimilarityFunction.possible_valuesSs"44A444sN)ruzstr | SimilarityFunctionreturnz6Callable[[Tensor | ndarray, Tensor | ndarray], Tensor])r{z list[str]) __name__ __module__ __qualname____doc__rnroDOTrqrp staticmethodrvrxrsrrrfrfs~FK CII# 5# ?# # J& 5& ?& & P 5 5rrf)rrrrr{r)rlist | np.ndarray | Tensorrrr{r)rZrr[rr{r)" __future__rcollections.abcrenumrnumpynprrsklearn.metricsrrtransformers.utilsr tensorr r r r get_loggerr|r0rrr'r)r&r:r=rKrMrdrfrrrrs}"$ .&dd   H % ?&_.5"*"46;")>C"(!Vl5l5r