a
    h                     @  s   d dl mZ d dlmZ d dlmZ d dlmZ d dlm	  m
Z d dlmZm	Z	 d dlmZ G dd	 d	eZG d
d de	jZdS )    )annotations)Iterable)Enum)AnyN)Tensornn)SentenceTransformerc                   @  s(   e Zd ZdZdd Zdd Zdd ZdS )SiameseDistanceMetricz#The metric for the contrastive lossc                 C  s   t j| |ddS )N   pFZpairwise_distancexy r   h/var/www/html/assistant/venv/lib/python3.9/site-packages/sentence_transformers/losses/ContrastiveLoss.py<lambda>       zSiameseDistanceMetric.<lambda>c                 C  s   t j| |ddS )N   r   r   r   r   r   r   r      r   c                 C  s   dt | | S )Nr   )r   Zcosine_similarityr   r   r   r   r      r   N)__name__
__module____qualname____doc__Z	EUCLIDEANZ	MANHATTANCOSINE_DISTANCEr   r   r   r   r	      s   r	   c                      sd   e Zd Zejddfddddd fdd	Zd
dddZddddddZeddddZ	  Z
S )ContrastiveLoss      ?Tr   floatboolNone)modelmarginsize_averagereturnc                   s&   t    || _|| _|| _|| _dS )a	  
        Contrastive loss. Expects as input two texts and a label of either 0 or 1. If the label == 1, then the distance between the
        two embeddings is reduced. If the label == 0, then the distance between the embeddings is increased.

        Args:
            model: SentenceTransformer model
            distance_metric: Function that returns a distance between
                two embeddings. The class SiameseDistanceMetric contains
                pre-defined metrices that can be used
            margin: Negative samples (label == 0) should have a distance
                of at least the margin value.
            size_average: Average by the size of the mini-batch.

        References:
            * Further information: https://www.researchgate.net/publication/4246277_Dimensionality_Reduction_by_Learning_an_Invariant_Mapping
            * `Training Examples > Quora Duplicate Questions <../../../examples/sentence_transformer/training/quora_duplicate_questions/README.html>`_

        Requirements:
            1. (anchor, positive/negative) pairs

        Inputs:
            +-----------------------------------------------+------------------------------+
            | Texts                                         | Labels                       |
            +===============================================+==============================+
            | (anchor, positive/negative) pairs             | 1 if positive, 0 if negative |
            +-----------------------------------------------+------------------------------+

        Relations:
            - :class:`OnlineContrastiveLoss` is similar, but uses hard positive and hard negative pairs.
              It often yields better results.

        Example:
            ::

                from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses
                from datasets import Dataset

                model = SentenceTransformer("microsoft/mpnet-base")
                train_dataset = Dataset.from_dict({
                    "sentence1": ["It's nice weather outside today.", "He drove to work."],
                    "sentence2": ["It's so sunny.", "She walked to the store."],
                    "label": [1, 0],
                })
                loss = losses.ContrastiveLoss(model)

                trainer = SentenceTransformerTrainer(
                    model=model,
                    train_dataset=train_dataset,
                    loss=loss,
                )
                trainer.train()
        N)super__init__distance_metricr"   r!   r#   )selfr!   r'   r"   r#   	__class__r   r   r&      s
    ;
zContrastiveLoss.__init__zdict[str, Any])r$   c                 C  sF   | j j}tt D ] \}}|| j krd| } q6q|| j| jdS )NzSiameseDistanceMetric.)r'   r"   r#   )r'   r   varsr	   itemsr"   r#   )r(   Zdistance_metric_namenamevaluer   r   r   get_config_dictW   s    

zContrastiveLoss.get_config_dictzIterable[dict[str, Tensor]]r   )sentence_featureslabelsr$   c                   s    fdd|D }t |dks"J |\}} ||}d| |d d|  t j| d   } jr|| S |	 S )Nc                   s   g | ]}  |d  qS )Zsentence_embedding)r!   ).0Zsentence_featurer(   r   r   
<listcomp>a   r   z+ContrastiveLoss.forward.<locals>.<listcomp>r
   r   r   )
lenr'   r   powr   Zrelur"   r#   meansum)r(   r0   r1   ZrepsZ
rep_anchorZ	rep_otherZ	distancesZlossesr   r3   r   forward`   s    2zContrastiveLoss.forwardstrc                 C  s   dS )Na~  
@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}
r   r3   r   r   r   citationj   s    zContrastiveLoss.citation)r   r   r   r	   r   r&   r/   r9   propertyr;   __classcell__r   r   r)   r   r      s   A	
r   )
__future__r   collections.abcr   enumr   typingr   Ztorch.nn.functionalr   Z
functionalr   Ztorchr   Z)sentence_transformers.SentenceTransformerr   r	   Moduler   r   r   r   r   <module>   s   