tj@<ddlmZmZddlmZddlmZmZddlm Z m Z m Z m Z ddl mZmZmZddlmZmZerddlZGd d e d Zd ZdedDdedDzZdZeGdde ZdgZdS))OptionalUnion) BatchFeature) ImageInputmake_flat_list_of_images)MultiModalDataProcessingKwargsProcessorMixinUnpack) AddedTokenPreTokenizedInput TextInput)auto_docstringis_torch_availableNc(eZdZddidddddidZd S) ColPaliProcessorKwargspaddinglongestchannels_firstT) data_formatdo_convert_rgbreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname__ _defaultsl/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/colpali/processing_colpali.pyrr#sB y ,"  +D1  IIIr#rF)totalzcg|] }d|dd S)z4>r".0is r$ r+1s"555Aq555r#icg|] }d|dd S)z3r'r"r(s r$r+r+1s"8]8]8]Q8]8]8]r#c ||z|z||dS)aZ Builds a string from the input prompt and image tokens. For example, for the call: build_string_from_input( prompt="Prefix str" bos_token="", image_seq_len=3, image_token="", ) The output will be: "Initial str" Args: prompt (`list[Union[str, ImageInput]]`): The input prompt. bos_token (`str`): The beginning of sentence token. image_seq_len (`int`): The length of the image sequence. image_token (`str`): The image token. num_images (`int`): Number of images in the prompt.  r"prompt bos_token image_seq_len image_token num_imagess r$build_string_from_inputr64s'&M)J6 M M6 M M MMr#c eZdZ ddedeffd Ze ddedzdeeze eze ezd e e d e fd Z dd Zed Zed efdZ ddedzd e e d e fdZdee ezd e e d e fdZ ddede dfdede dfdededdedefd df dZxZS) ColPaliProcessorNDescribe the image. Question: visual_prompt_prefix query_prefixc||_||_t|dstd|j|_t|ds]t t dd}d|gi}|||t |_ t |_ n|j |_ |j |_ | td|_ d|_t|||d S) a! visual_prompt_prefix (`str`, *optional*, defaults to `"Describe the image."`): A string that gets tokenized and prepended to the image tokens. query_prefix (`str`, *optional*, defaults to `"Question: "`): A prefix to be used for the query. image_seq_lengthz;Image processor is missing an `image_seq_length` attribute.r4FT) normalizedspecialadditional_special_tokens) chat_templateN)r;r<hasattr ValueErrorr>r IMAGE_TOKENadd_special_tokensconvert_tokens_to_idsimage_token_idr4 add_tokens EXTRA_TOKENS add_bos_token add_eos_tokensuper__init__) selfimage_processor tokenizerrBr;r<r4 tokens_to_add __class__s r$rNzColPaliProcessor.__init__Ls %9!((:;; \Z[[ [ / @y-00 5$[UDQQQK8;-HM  ( ( 7 7 7"+"A"A+"N"ND *D  "+":D (4D \***"' "'  )=QQQQQr#imagestextkwargsreturnc jtfdjji|}|ddd}d}||t d||t d|)j|}t|}j gt|z}fd|D}fd t||D}j|fi|d d } |d d d|dd xxj z cc<j|fd |i|d} i| d | i} |r=| d| ddkd} | d| it!| S|t#|t$r|g}n?t#|t&rt#|dt$st d| jdz}g} |D]4}jjjz|z|zdz}| |5|d d d|dd <j| fd |i|d}|SdS)a 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_kwargsrsuffixNTz&Either text or images must be providedz5Only one of text or images can be processed at a timecDg|]}j|Sr")rP process_image)r)imagerOs r$r+z-ColPaliProcessor.__call__..s*TTTEd*88??TTTr#c g|]Q\}}t|jjjtt |t rt|ndRS)r0)r6rQr2r>rE isinstancelistlen)r)r1 image_listrOs r$r+z-ColPaliProcessor.__call__..so   'FJ(!"n6"&"7 +2 masked_fillupdaterr`strraquery_augmentation_tokenr2r<append)rOrTrUrV output_kwargsrZrf texts_doc input_stringsrdinputs return_datari texts_queryquery batch_querys` r$__call__zColPaliProcessor.__call__qsC"+* "  "&."<   }-11(DAA $ >F-f55F23c&kkAITTTTVTTTF    +.i*@*@   M04/YY-:XYYZhiL]+// dCCOm,\:::d>SS:::#T^&; .F CVB^\BBK$ 7 ,88@P9QUV9VX\]]""Hf#5666[111 1  $$$ Ov t,, ODGS1I1I O !MNNN~6;%'K * *043DDuLvUX\\""5))))9F}9U9Y9YZfhj9k9kM- ( 6($.&; .K  - r#c i}|C|jgt|z}dgt|z}|||dtdi|S)a Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (list[list[str]], *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. Nr_)num_image_tokensnum_image_patchesr")r>rbrtr )rO image_sizesrV vision_datarrs r$_get_num_multimodal_tokensz+ColPaliProcessor._get_num_multimodal_tokensso  " $ 56[9I9II !"c+&6&6 6    4D[lmm n n n,, ,,,r#c`|jjddgz}|jj}t||zS)Nrhri)rQmodel_input_namesrPra)rOtokenizer_input_namesimage_processor_input_namess r$rz"ColPaliProcessor.model_input_namess: $ @DTV^C_ _&*&:&L#),GGHHHr#c|jjS)z Return the query augmentation token. Query augmentation buffers are used as reasoning buffers during inference. )rQ pad_token)rOs r$rvz)ColPaliProcessor.query_augmentation_tokens~''r#c |jdd|i|S)a Prepare for the model one or several image(s). This method is a wrapper around the `__call__` method of the ColPaliProcessor's [`ColPaliProcessor.__call__`]. This method forwards the `images` and `kwargs` arguments to the image processor. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `list[PIL.Image.Image]`, `list[np.ndarray]`, `list[torch.Tensor]`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. rTr"r)rOrTrVs r$process_imageszColPaliProcessor.process_imagess!>t}55F5f555r#c |jdd|i|S)ag 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 the tokenizer. 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: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.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`). rUr"r)rOrUrVs r$process_queriesz ColPaliProcessor.process_queriess!<t}11$1&111r#r-cpuquery_embeddingsz torch.Tensorpassage_embeddings batch_size output_dtypez torch.dtype output_devicez torch.devicec 8t|dkrtdt|dkrtd|dj|djkrtd|dj|djkrtd| |dj}g}t dt||D]:}g}t jjj ||||zdd} t dt||D]} t jjj || | |zdd} | t j d | |  d d d | t j|d || usually obtained by padding the list of tensors. Args: query_embeddings (`Union[torch.Tensor, list[torch.Tensor]`): Query embeddings. passage_embeddings (`Union[torch.Tensor, list[torch.Tensor]`): Passage embeddings. batch_size (`int`, *optional*, defaults to 128): Batch size for computing scores. output_dtype (`torch.dtype`, *optional*, defaults to `torch.float32`): The dtype of the output tensor. If `None`, the dtype of the input embeddings is used. output_device (`torch.device` or `str`, *optional*, defaults to "cpu"): The device of the output tensor. Returns: `torch.Tensor`: A tensor of shape `(n_queries, n_passages)` containing the scores. The score tensor is saved on the "cpu" device. rzNo queries providedzNo passages providedz/Queries and passages must be on the same devicez-Queries and passages must have the same dtypeNT) batch_first padding_valuez bnd,csd->bcnsr)dimr_)rbrDdevicedtyperangetorchnnutilsrnn pad_sequencerweinsummaxsumcatto) rOrrrrrscoresr* batch_scores batch_queriesjbatch_passagess r$score_retrievalz ColPaliProcessor.score_retrieval.s*@  A % %233 3 ! " "a ' '344 4 A  %);A)>)E E ENOO O A  $(:1(=(C C CLMM M  +A.4L%'q#.//<< ] ]A/1L!HN.;; Q^!34$VW<M1c"455zBB  !&!3!@!@&q1z>'9:\]"A""##L-PPTTYZT[[\]^bbghbii MM%)La888;;LIILL][[ \ \ \ \yQ''''r#)NNNr9r:)NN)N)r-Nr)rrr rurNrrrrrar rrrrpropertyrrvrrrintrr __classcell__)rSs@r$r8r8Js]$9( #R#R " #R  #R#R#R#R#R#RJ%)Z^XXT!X++d9o=EV@WWX/0 X  XXX^Xt----$IIXI (#(((X(%)66T!6/06  6666B2$y/)2/02  2222H0449 >(>(^0D DE>(".$~2F"FG>( >( }- >( ^S01 >( >(>(>(>(>(>(>(>(r#r8)typingrrfeature_extraction_utilsr image_utilsrrprocessing_utilsr r r r tokenization_utils_baser rrrrrrrrErrJr6r8__all__r"r#r$rs,#"""""""444444????????XXXXXXXXXXXXOOOOOOOOOO77777777LLL     -U     55t5558]8]RWRWX[R\R\8]8]8]] NNN,a(a(a(a(a(~a(a(a(H  r#