>:j1SSKJr SSKJr SSKJr SSKrSSKrSSKJ r SSK J r SSKJ r SSK Jr S S KJrJrJrJr \R("\5rSS jrSS jrSS jrSSjrSSjrSSjrSSjrSSjrSSjrSSjr "SS\5r!g)) annotations)Callable)EnumN)ndarray)pairwise_distances)Tensor)logging)_convert_to_batch_tensor_convert_to_tensornormalize_embeddings to_scipy_cooc[X5$) Computes the cosine similarity between two tensors. Args: a (Union[list, np.ndarray, Tensor]): The first tensor. b (Union[list, np.ndarray, Tensor]): The second tensor. Returns: Tensor: Matrix with res[i][j] = cos_sim(a[i], b[j]) )cos_simabs b/home/mande/repo/quber/.venv/lib/python3.13/site-packages/sentence_transformers/util/similarity.pypytorch_cos_simrs 1=c[U5n[U5n[U5n[U5n[R"X#R SS55R 5$)rrr )r r torchmm transposeto_denserra_normb_norms rrr!sQ !#A #A !! $F !! $F 88F,,Q2 3 < < >>rc4[U5n[U5nUR(dUR(a5[U5n[U5nX#-RSS9R 5$[ [U5[U55R 5$)z 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\\^^rc[U5n[U5n[R"XRSS55R 5$)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 88A{{1a( ) 2 2 44rcl[U5n[U5nX-RSS9R5$)z 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&\s4 1A1A E;;2;  ' ' ))rc[U5n[U5nUR(dUR(a[RS5 [ U5n[ U5n[ X#SS9n[ R"U*5R5RUR5R5$[ R"XSS9R5*$)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 AC(11333rc[U5n[U5n[R"[R"X- 5SS9R 5*$)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=s@ 1A1A IIeii&B / 8 8 : ::rc^[U5n[U5nUR(a[RR X-SS9R 5R S5n[RR X-SS9R 5R S5n[R"XR55R 5nUSU-- U-n[R"USS9n[R"U5R 5*$[R"XSS9*$) 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 ll1cce,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_fn#SimilarityFunction.to_similarity_fns.11DE "4";"; ;N "4"@"@ @  "4">"> > "4">"> > $%8$99moAoQoQoSnTTU V  rc0[U5nU[R:Xa[$U[R:Xa[$U[R :Xa[ $U[R:Xa[$[SUS[R5S35e)aH 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]) rlrmrn) rfror'rpr&rqr=rrrMrsrtrus rto_similarity_pairwise_fn,SimilarityFunction.to_similarity_pairwise_fn*s411DE "4";"; ;# # "4"@"@ @% % "4">"> >) ) "4">"> >) )$%8$99moAoQoQoSnTTU V  rcL[Vs/sHoRPM sn$s snf)a$ 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 rrt"SimilarityFunction.possible_valuesSs "44!3A!3444s!N)rvzstr | SimilarityFunctionreturnz6Callable[[Tensor | ndarray, Tensor | ndarray], Tensor])rz list[str])__name__ __module__ __qualname____firstlineno____doc__rorpDOTrrrq staticmethodrwrzrt__static_attributes__rrrrfrfs~FK CII# 5# ?# # J& 5& ?& & P 5 5rrf)rrrrrr)rlist | np.ndarray | Tensorrrrr)rZrr[rrr)" __future__rcollections.abcrenumrnumpynprrsklearn.metricsrrtransformers.utilsr tensorr r r r get_loggerrr0rrr'r)r&r:r=rKrMrdrfrrrrs{"$ .&dd   H % ?&_.5"*"46;")>C"(!Vl5l5r