U
    9%eC                      @   s<   d Z ddlmZ ddlmZ dZeeG dd deZdS )z RAG model configuration   )PretrainedConfig)add_start_docstringsa)  
    [`RagConfig`] stores the configuration of a *RagModel*. Configuration objects inherit from [`PretrainedConfig`] and
    can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information.

    Args:
        title_sep (`str`, *optional*, defaults to  `" / "`):
            Separator inserted between the title and the text of the retrieved document when calling [`RagRetriever`].
        doc_sep (`str`, *optional*, defaults to  `" // "`):
            Separator inserted between the text of the retrieved document and the original input when calling
            [`RagRetriever`].
        n_docs (`int`, *optional*, defaults to 5):
            Number of documents to retrieve.
        max_combined_length (`int`, *optional*, defaults to 300):
            Max length of contextualized input returned by [`~RagRetriever.__call__`].
        retrieval_vector_size (`int`, *optional*, defaults to 768):
            Dimensionality of the document embeddings indexed by [`RagRetriever`].
        retrieval_batch_size (`int`, *optional*, defaults to 8):
            Retrieval batch size, defined as the number of queries issues concurrently to the faiss index encapsulated
            [`RagRetriever`].
        dataset (`str`, *optional*, defaults to `"wiki_dpr"`):
            A dataset identifier of the indexed dataset in HuggingFace Datasets (list all available datasets and ids
            using `datasets.list_datasets()`).
        dataset_split (`str`, *optional*, defaults to `"train"`)
            Which split of the `dataset` to load.
        index_name (`str`, *optional*, defaults to `"compressed"`)
            The index name of the index associated with the `dataset`. One can choose between `"legacy"`, `"exact"` and
            `"compressed"`.
        index_path (`str`, *optional*)
            The path to the serialized faiss index on disk.
        passages_path (`str`, *optional*):
            A path to text passages compatible with the faiss index. Required if using
            [`~models.rag.retrieval_rag.LegacyIndex`]
        use_dummy_dataset (`bool`, *optional*, defaults to `False`)
            Whether to load a "dummy" variant of the dataset specified by `dataset`.
        label_smoothing (`float`, *optional*, defaults to 0.0):
            Only relevant if `return_loss` is set to `True`. Controls the `epsilon` parameter value for label smoothing
            in the loss calculation. If set to 0, no label smoothing is performed.
        do_marginalize (`bool`, *optional*, defaults to `False`):
            If `True`, the logits are marginalized over all documents by making use of
            `torch.nn.functional.log_softmax`.
        reduce_loss (`bool`, *optional*, defaults to `False`):
            Whether or not to reduce the NLL loss using the `torch.Tensor.sum` operation.
        do_deduplication (`bool`, *optional*, defaults to `True`):
            Whether or not to deduplicate the generations from different context documents for a given input. Has to be
            set to `False` if used while training with distributed backend.
        exclude_bos_score (`bool`, *optional*, defaults to `False`):
            Whether or not to disregard the BOS token when computing the loss.
        output_retrieved(`bool`, *optional*, defaults to `False`):
            If set to `True`, `retrieved_doc_embeds`, `retrieved_doc_ids`, `context_input_ids` and
            `context_attention_mask` are returned. See returned tensors for more detail.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        forced_eos_token_id (`int`, *optional*):
            The id of the token to force as the last generated token when `max_length` is reached. Usually set to
            `eos_token_id`.
c                       s<   e Zd ZdZdZd fdd	ZeeeedddZ  Z	S )	RagConfigZragTN /  //    ,        wiki_dprtrain
compressedF        c           "         s"  t  jf ||||||||d| d|kr4d|ks<td|d}|d}|d}|d} ddlm}! |!j|f|| _|!j| f|| _|| _	|| _
|| _|| _|| _|	| _|
| _|| _|| _|| _|| _|| _|| _|| _|| _|| _|| _|| _|| _| jd krt| jdd | _d S )	N)bos_token_idpad_token_ideos_token_iddecoder_start_token_idforced_eos_token_idis_encoder_decoderprefix
vocab_sizequestion_encoder	generatorzGConfig has to be initialized with question_encoder and generator config
model_type   )
AutoConfigr   )super__init__AssertionErrorpopZauto.configuration_autor   Z	for_modelr   r   reduce_losslabel_smoothingexclude_bos_scoredo_marginalize	title_sepdoc_sepn_docsmax_combined_lengthdatasetdataset_split
index_nameretrieval_vector_sizeretrieval_batch_sizepassages_path
index_pathuse_dummy_datasetoutput_retrieveddo_deduplication	use_cacher   getattr)"selfr   r   r   r   r   r   r   r$   r%   r&   r'   r+   r,   r(   r)   r*   r.   r-   r/   r    r!   r1   r"   r#   r0   r2   r   kwargsquestion_encoder_configZquestion_encoder_model_typeZdecoder_configZdecoder_model_typer   	__class__ h/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/rag/configuration_rag.pyr   U   s\    	



zRagConfig.__init__)r6   generator_configreturnc                 K   s   | f |  |  d|S )a  
        Instantiate a [`EncoderDecoderConfig`] (or a derived class) from a pre-trained encoder model configuration and
        decoder model configuration.

        Returns:
            [`EncoderDecoderConfig`]: An instance of a configuration object
        )r   r   )to_dict)clsr6   r;   r5   r9   r9   r:   'from_question_encoder_generator_configs   s    z1RagConfig.from_question_encoder_generator_configs)NTNNNNNr   r   r   r   r	   r
   r   r   r   NNFFr   TFFFTN)
__name__
__module____qualname__r   Zis_compositionr   classmethodr   r?   __classcell__r9   r9   r7   r:   r   P   sF                              T r   N)__doc__Zconfiguration_utilsr   utilsr   ZRAG_CONFIG_DOCr   r9   r9   r9   r:   <module>   s
   :