% &h >ddlmZmZmZmZddlmZmZmZddl m Z ddl m Z m Z mZddlmZmZddlmZmZddlmZmZerdd lZej2eZGd d ed ZGddeZdgZy ))ClassVarListOptionalUnion) IMAGE_TOKENPaliGemmaProcessorbuild_string_from_input) BatchFeature) ImageInputis_valid_imagemake_flat_list_of_images)ProcessingKwargsUnpack)PreTokenizedInput TextInput)is_torch_availableloggingNc&eZdZddidddddidZy ) ColPaliProcessorKwargspaddinglongestchannels_firstT) data_formatdo_convert_rgbreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname__ _defaults/var/www/pru.catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/colpali/modular_colpali.pyrr0s, y ," +D1 Ir&rF)totalc 2eZdZUdZdZeeed<dZeeed<e defdZ dd e d e e eee eefd eedefd Z dd e d eedefd Zd e e ee fd eedefdZ dde dedfde dedfdededde defddf dZy)ColPaliProcessora Constructs a ColPali processor which wraps a PaliGemmaProcessor and special methods to process images and queries, as well as to compute the late-interaction retrieval score. [`ColPaliProcessor`] offers all the functionalities of [`PaliGemmaProcessor`]. See the [`~PaliGemmaProcessor.__call__`] for more information. Args: image_processor ([`SiglipImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`], *optional*): The tokenizer is a required input. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. zDescribe the image.visual_prompt_prefixz Question: query_prefixreturnc.|jjS)z Return the query augmentation token. Query augmentation buffers are used as reasoning buffers during inference. ) tokenizer pad_token)selfs r'query_augmentation_tokenz)ColPaliProcessor.query_augmentation_tokenQs~~'''r&Nimagestextkwargsc |jtfd|jji|}|dj dd}|dnd}| | t d| | t d|t |r|g}n^t|trt |d rn?t|tr$t|d trt |d d s t d |jgt|z} |D cgc]} | jd }} t| |D cgc]R\} } t| |jj|jt t| tr t| nd T} } } t#|}|j$|fi|dd}|dj'dd|ddxx|jz cc<|j| fddi|d}i|d|i}|r.|dj)|dd k(d}|j+d|it-|S|t|t.r|g}n.t|trt|d t.s t d||j0dz}g}|D]C}|jj|j2z|z}||z }|dz }|j5|E|dj'dd|dd<|j|fddi|d}|Sycc} wcc} } w)a Main method to prepare for the model either (1) one or several texts, either (2) one or several image(s). This method is custom wrapper around the PaliGemmaProcessor's [`~PaliGemmaProcessor.__call__`] method adapted for the ColPali model. It cannot process both text and images at the same time. When preparing the text(s), this method forwards the `text` and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`]. When preparing the image(s), this method forwards the `images` and `kwargs` arguments to SiglipImageProcessor's [`~SiglipImageProcessor.__call__`]. Please refer to the docstring of the above two methods for more information. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. text (`str`, `List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. tokenizer_init_kwargsrsuffixNTFz&Either text or images must be providedz5Only one of text or images can be processed at a timerzAimages must be an image, list of images or list of list of imagesRGB)prompt bos_token image_seq_len image_token num_imagesr pixel_values max_lengthreturn_token_type_ids input_idstoken_type_idsilabels)dataz*Text must be a string or a list of strings  2) _merge_kwargsrr/ init_kwargspop ValueErrorr isinstancelistr+lenconvertzipr r<image_seq_lengthrrimage_processorget masked_fillupdater strr2r,append)r1r3r4audiovideosr5 output_kwargsr8rB texts_docimager; image_list input_stringsr@inputs return_datarE texts_queryquery batch_querys r'__call__zColPaliProcessor.__call__ZsqZ+** " "&.."<"<  }-11(DA(.(: ?uemmE*?F?+.i*@ 'FJ(!"nn66"&"7"7 +2S>SS:#T^^&+ .F CVB^\BK$ ,88@P9QUV9VX\]""Hf#56[1 1  $$v t,DGS1I !MNN~66;%'K *0043D3DDuL ""5)  * :G}9U9Y9YZfhj9kM- ( 6($..&+ .K  1C@ s 4K;ALc *|jdd|i|S)a Prepare for the model one or several image(s). This method is a wrapper around the `__call__` method of the ColPaliProcessor's [`ColPaliProcessor.__call__`]. This method forwards the `images` and `kwargs` arguments to SiglipImageProcessor's [`~SiglipImageProcessor.__call__`]. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. r3r%rf)r1r3r5s r'process_imageszColPaliProcessor.process_imagessBt}}5F5f55r&c *|jdd|i|S)a Prepare for the model one or several texts. This method is a wrapper around the `__call__` method of the ColPaliProcessor's [`ColPaliProcessor.__call__`]. This method forwards the `text` and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`]. Args: text (`str`, `List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). r4r%rh)r1r4r5s r'process_queriesz ColPaliProcessor.process_queriess@t}}1$1&11r&query_embeddingsz torch.Tensorpassage_embeddings batch_size output_dtypez torch.dtype output_devicez torch.devicec t|dk(r tdt|dk(r td|dj|djk7r td|dj|djk7r td||dj}g}t dt||D]%}g}t j jjj||||zdd} t dt||D]} t j jjj|| | |zdd} |jt jd| | jd djd |jt j|d j|j|(t j|d S) aZ Compute the late-interaction/MaxSim score (ColBERT-like) for the given multi-vector query embeddings (`qs`) and passage embeddings (`ps`). For ColPali, a passage is the image of a document page. Because the embedding tensors are multi-vector and can thus have different shapes, they should be fed as: (1) a list of tensors, where the i-th tensor is of shape (sequence_length_i, embedding_dim) (2) a single tensor of shape (n_passages, max_sequence_length, embedding_dim) -> usually obtained by padding the list of tensors. Args: query_embeddings (`Union[torch.Tensor, List[torch.Tensor]`): Query embeddings. passage_embeddings (`Union[torch.Tensor, List[torch.Tensor]`): Passage embeddings. batch_size (`int`, *optional*, defaults to 128): Batch size for computing scores. output_dtype (`torch.dtype`, *optional*, defaults to `torch.float32`): The dtype of the output tensor. If `None`, the dtype of the input embeddings is used. output_device (`torch.device` or `str`, *optional*, defaults to "cpu"): The device of the output tensor. Returns: `torch.Tensor`: A tensor of shape `(n_queries, n_passages)` containing the scores. The score tensor is saved on the "cpu" device. rzNo queries providedzNo passages providedz/Queries and passages must be on the same devicez-Queries and passages must have the same dtypeT) batch_first padding_valuez bnd,csd->bcnsr )dimr:)rPrMdevicedtyperangetorchnnutilsrnn pad_sequencerYeinsummaxsumcatto) r1rlrmrnrorpscoresi batch_scores batch_queriesjbatch_passagess r'score_retrievalz ColPaliProcessor.score_retrievals@  A %23 3 ! "a '34 4 A  % %);A)>)E)E ENO O A  $ $(:1(=(C(C CLM M  +A.44L%'q#./< ]A/1L!HHNN..;; Q^4$VW<M1c"45zB !&!3!3!@!@&q1z>:\]"A"##LL-PTTYZT[\]^bbghbi   MM%))La8;;LILL][ \ ]yyQ''r&)NNNN)N)Ncpu)r!r"r#__doc__r+rrX__annotations__r,propertyr2r rrrrrrr rfrirkintrrr%r&r'r*r*=sx +@(3-?".L(3-. (#(("^b }}I0$y/4HYCZZ[} /0 } }B"!6!6/0!6  !6F 2ItI./ 2/0 2  2L0449 >(^0D DE>(".$~2F"FG>( >( }- >( ^S01 >( >(r&r*)typingrrrr2transformers.models.paligemma.processing_paligemmarrr feature_extraction_utilsr image_utilsr r rprocessing_utilsrrtokenization_utils_baserrr{rrry get_loggerr!loggerrr*__all__r%r&r'rs{"32 5OO    H % -U _()_(F  r&