§
    æ˜ºhr  ã                   ól   — d dl Z d dl mZmZ d dlmZmZ ddlmZ d dlm	Z	  G d„ dej
        ¦  «        ZdS )	é    N)ÚnnÚTensor)ÚIterableÚDicté   )Ú$BatchHardTripletLossDistanceFunction)ÚSentenceTransformerc                   ó¬   ‡ — e Zd ZdZej        dfdedefˆ fd„Zde	e
eef                  defd„Zded	ed
efd„Zedd„¦   «         Zedd„¦   «         Zˆ xZS )ÚBatchSemiHardTripletLossaž  
    BatchSemiHardTripletLoss takes a batch with (label, sentence) pairs and computes the loss for all possible, valid
    triplets, i.e., anchor and positive must have the same label, anchor and negative a different label. It then looks
    for the semi hard positives and negatives.
    The labels must be integers, with same label indicating sentences from the same class. You train dataset
    must contain at least 2 examples per label class. The margin is computed automatically.

    Source: https://github.com/NegatioN/OnlineMiningTripletLoss/blob/master/online_triplet_loss/losses.py
    Paper: In Defense of the Triplet Loss for Person Re-Identification, https://arxiv.org/abs/1703.07737
    Blog post: https://omoindrot.github.io/triplet-loss

    :param model: SentenceTransformer model
    :param distance_metric: Function that returns a distance between two emeddings. The class SiameseDistanceMetric contains pre-defined metrices that can be used


    Example::

       from sentence_transformers import SentenceTransformer, SentencesDataset, losses
       from sentence_transformers.readers import InputExample

       model = SentenceTransformer('distilbert-base-nli-mean-tokens')
       train_examples = [InputExample(texts=['Sentence from class 0'], label=0), InputExample(texts=['Another sentence from class 0'], label=0),
           InputExample(texts=['Sentence from class 1'], label=1), InputExample(texts=['Sentence from class 2'], label=2)]
       train_dataset = SentencesDataset(train_examples, model)
       train_dataloader = DataLoader(train_dataset, shuffle=True, batch_size=train_batch_size)
       train_loss = losses.BatchSemiHardTripletLoss(model=model)
    é   ÚmodelÚmarginc                 ó€   •— t          t          | ¦  «                             ¦   «          || _        || _        || _        d S )N)Úsuperr   Ú__init__Úsentence_embedderr   Údistance_metric)Úselfr   r   r   Ú	__class__s       €ú}/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/sentence_transformers/losses/BatchSemiHardTripletLoss.pyr   z!BatchSemiHardTripletLoss.__init__%   s?   ø€ õ 	Õ&¨Ñ-Ô-×6Ò6Ñ8Ô8Ð8Ø!&ˆÔØˆŒØ.ˆÔÐÐó    Úsentence_featuresÚlabelsc                 óp   — |                       |d         ¦  «        d         }|                      ||¦  «        S )Nr   Úsentence_embedding)r   Úbatch_semi_hard_triplet_loss)r   r   r   Úreps       r   Úforwardz BatchSemiHardTripletLoss.forward0   s7   € Ø×$Ò$Ð%6°qÔ%9Ñ:Ô:Ð;OÔPˆØ×0Ò0°¸Ñ=Ô=Ð=r   Ú
embeddingsÚreturnc           	      ó¤  — |                      d¦  «        }|                      |¦  «        }||                     ¦   «         k    }| }t          j        |¦  «        }|                     |dg¦  «        }|                     |dg¦  «        |t          j        |                     ¦   «         ddg¦  «        k    z  }t          j        t          j        |dd¬¦  «        dk    ||g¦  «        }	|	                     ¦   «         }	t          j        t           	                    ||¦  «        ||g¦  «        }
|
                     ¦   «         }
t           
                    ||¦  «        }|                     d|g¦  «        }t          j        |	|
|¦  «        }||z
  | j        z   }|                     ¦   «                              |j        ¦  «        t          j        ||j        ¬¦  «        z
  }|                     |j        ¦  «        }t          j        |¦  «        }t          j        t          j        ||z  t          j        dg|j        ¬¦  «        ¦  «        ¦  «        |z  }|S )a]  Build the triplet loss over a batch of embeddings.
        We generate all the valid triplets and average the loss over the positive ones.
        Args:
            labels: labels of the batch, of size (batch_size,)
            embeddings: tensor of shape (batch_size, embed_dim)
            margin: margin for triplet loss
            squared: Boolean. If true, output is the pairwise squared euclidean distance matrix.
                     If false, output is the pairwise euclidean distance matrix.
        Returns:
            Label_Sentence_Triplet: scalar tensor containing the triplet loss
        r   éÿÿÿÿT©Úkeepdimsg        )Údevice)Ú	unsqueezer   ÚtÚtorchÚnumelÚrepeatÚreshapeÚsumr   Ú_masked_minimumÚ_masked_maximumÚwherer   ÚfloatÚtor%   ÚeyeÚmaxÚtensor)r   r   r   Úpdist_matrixÚ	adjacencyÚadjacency_notÚ
batch_sizeÚpdist_matrix_tileÚmaskÚ
mask_finalÚnegatives_outsideÚnegatives_insideÚsemi_hard_negativesÚloss_matÚmask_positivesÚnum_positivesÚtriplet_losss                    r   r   z5BatchSemiHardTripletLoss.batch_semi_hard_triplet_loss7   s#  € ð ×!Ò! !Ñ$Ô$ˆà×+Ò+¨JÑ7Ô7ˆà˜fŸhšh™jœjÒ(ˆ	Ø"˜
ˆå”[ Ñ(Ô(ˆ
Ø(×/Ò/°¸Q°Ñ@Ô@Ðà×#Ò# Z° OÑ4Ô4Ð8IÍEÌMÐZf×ZhÒZhÑZjÔZjÐmoÐqrÐlsÑLtÔLtÒ8tÑuˆå”]¥5¤9¨T°1¸tÐ#DÑ#DÔ#DÀsÒ#JÈZÐYcÐLdÑeÔeˆ
Ø—\’\‘^”^ˆ
å!œMÝ$×4Ò4Ð5FÈÑMÔMÐPZÐ\fÐOgñ
ô 
Ðð .×/Ò/Ñ1Ô1Ðå3×CÒCÀLÐR_Ñ`Ô`ÐØ+×2Ò2°A°z°?ÑCÔCÐå#œk¨*Ð6GÐIYÑZÔZÐà Ð#6Ñ6¸$¼+ÑEˆà"ŸšÑ*Ô*×-Ò-¨f¬mÑ<Ô<½u¼yÈÐ\bÔ\iÐ?jÑ?jÔ?jÑjˆØ'×*Ò*¨6¬=Ñ9Ô9ˆÝœ	 .Ñ1Ô1ˆõ ŒI•e”i ¨>Ñ 9½5¼<ÈÈÐV\ÔVcÐ;dÑ;dÔ;dÑeÔeÑfÔfÐivÑvð 	ð Ðr   r   c                 óˆ   — |                       |d¬¦  «        \  }}| |z
  |z  }|                     |d¬¦  «        \  }}||z  }|S ©NTr#   )r3   Úmin)Údatar:   ÚdimÚaxis_maximumsÚ_Úmasked_minimumss         r   r-   z(BatchSemiHardTripletLoss._masked_minimumh   óX   € àŸ8š8 C°$˜8Ñ7Ô7Ñˆ�qØ -Ñ/°4Ñ7ˆØ,×0Ò0°¸tÐ0ÑDÔDÑˆ˜Ø˜=Ñ(ˆàÐr   c                 óˆ   — |                       |d¬¦  «        \  }}| |z
  |z  }|                     |d¬¦  «        \  }}||z  }|S rD   )rE   r3   )rF   r:   rG   Úaxis_minimumsrI   Úmasked_maximumss         r   r.   z(BatchSemiHardTripletLoss._masked_maximumq   rK   r   )r   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__r   Úeucledian_distancer	   r0   r   r   r   Ústrr   r   r   Ústaticmethodr-   r.   Ú__classcell__)r   s   @r   r   r      s  ø€ € € € € ðð ð> =ÔOØð		/ð 	/à"ð	/ð ð		/ð 	/ð 	/ð 	/ð 	/ð 	/ð>¨°$°s¸F°{Ô2CÔ)Dð >Èfð >ð >ð >ð >ð/°6ð /Àvð /ÐRXð /ð /ð /ð /ðb ðð ð ñ „\ðð ðð ð ñ „\ðð ð ð ð r   r   )r(   r   r   Útypingr   r   ÚBatchHardTripletLossr   Ú)sentence_transformers.SentenceTransformerr	   ÚModuler   © r   r   ú<module>r\      s¢   ðØ €€€Ø Ð Ð Ð Ð Ð Ð Ð Ø !Ð !Ð !Ð !Ð !Ð !Ð !Ð !Ø FÐ FÐ FÐ FÐ FÐ FØ IÐ IÐ IÐ IÐ IÐ Iðpð pð pð pð p˜rœyñ pô pð pð pð pr   