Zj@^SSKJrJr SSKJr SSKJrJr SSKJ r J r J r J r SSK JrJrJr SSKJrJr \"5(aSSKr"S S \ S S 9rS r\"S5Vs/sH nSUSS3PM sn\"S5Vs/sH nSUSS3PM sn-rSr\"SS\ 55rS/rgs snfs snf))OptionalUnion) BatchFeature) ImageInputmake_flat_list_of_images)MultiModalDataProcessingKwargsProcessorMixinUnpack) AddedTokenPreTokenizedInput TextInput)auto_docstringis_torch_availableNc.\rSrSrSS0SSS.SS0S .rS rg ) ColPaliProcessorKwargs#paddinglongestchannels_firstT) data_formatdo_convert_rgbreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__r/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/colpali/processing_colpali.pyrr#s, y ," +D1 Ir&rF)totalziz4>z3cX2-U-UUS3$)a Builds a string from the input prompt and image tokens. For example, for the call: build_string_from_input( prompt="Prefix str" bos_token="", image_seq_len=3, image_token="", ) The output will be: "Initial str" Args: prompt (`list[Union[str, ImageInput]]`): The input prompt. bos_token (`str`): The beginning of sentence token. image_seq_len (`int`): The length of the image sequence. image_token (`str`): The image token. num_images (`int`): Number of images in the prompt.  rprompt bos_token image_seq_len image_token num_imagess r'build_string_from_inputr34s"&)J6 7 {6(" MMr&c v^\rSrSrSS\S\4U4Sjjjr\SS\S-S\\ -\ \-\ \ -S\ \ S \ 4S jj5rSS jr\S 5r\S \4S j5rSS\S-S\ \ S \ 4SjjrS\\ \-S\ \ S \ 4SjrSS\S\ S4S\S\ S4S\S\SS\S\4S S4 SjjrSrU=r$)ColPaliProcessorJNvisual_prompt_prefix query_prefixc>X@lXPl[US5(d [S5eURUl[US5(dK[ [ SSS9nSU/0nURU5 UR[ 5Ul [ Ul O"URUl URUl UR[5 SUl SUl[TU]AXUS9 g ) z 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.r1FT) normalizedspecialadditional_special_tokens) chat_templateN)r7r8hasattr ValueErrorr:r IMAGE_TOKENadd_special_tokensconvert_tokens_to_idsimage_token_idr1 add_tokens EXTRA_TOKENS add_bos_token add_eos_tokensuper__init__) selfimage_processor tokenizerr>r7r8r1 tokens_to_add __class__s r'rJColPaliProcessor.__init__Ls%9!((:;;Z[ [ / @ @y-00$[UDQK8;-HM  ( ( 7"+"A"A+"ND *D "+":":D (44D \*"' "'  =Qr&imagestextkwargsreturnc UR"[4SURR0UD6nUSR SS5nSnUcUc [ S5eUbUb [ S5eUGb|UR RU5n[U5nUR/[U5-nUVs/sHoR RU5PM nn[Xq5V V s/sHTup[U URRUR[ [#U [$5(a [U 5OSS 9PMV n n n UR "U40US D6S n USR'S S5bUSS ==UR- ss'UR"U 4S U0USD6n 0U ES U 0EnU(a.U SR)U SS:HS5nUR+SU05 [-US9$Ub[#U[.5(aU/nO8[#U[$5(a[#US[.5(d [ S5eUcUR0S-n/nUH@nURRUR2-U-U-S-nUR5U5 MB USR'S S5USS 'UR"U4S U0USD6nU$gs snfs sn n f)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 timer-r pixel_values max_lengthreturn_token_type_ids input_idstoken_type_idsrilabels)dataz*Text must be a string or a list of strings r,2) _merge_kwargsrrM init_kwargspopr@rL fetch_imagesrr7len process_imagezipr3r/r:rA isinstancelistget masked_fillupdaterstrquery_augmentation_tokenr8append)rKrQrRrS output_kwargsrWr[ texts_docimager. image_list input_stringsrYinputs return_datar^ texts_queryquery batch_querys r'__call__ColPaliProcessor.__call__qs#"** " "&.."<"<  }-11(DA $ F-f5F223c&kAIMSTVE**88?VFT+.i*@ +A&F(!"nn66"&"7"7 +2S>SS:^^&; .F CVB^\BK$ ,88@P9QUV9VX\]""Hf#56[1 1  $$$v t,,DGS1I1I !MNN~66;%'K0043D3DDuLvUX\\""5):G}9U9Y9YZfhj9kM- ( 6..&; .K  -AU s .$K "AKc 0nUb;UR/[U5-nS/[U5-nURXES.5 [S0UD6$)ax 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. rX)num_image_tokensnum_image_patchesr)r:rfrmr )rK image_sizesrS vision_datar~rs r'_get_num_multimodal_tokens+ColPaliProcessor._get_num_multimodal_tokenssZ  " $ 5 56[9II !"c+&6 6    4Dm n, ,,r&c~URRSS/-nURRn[X-5$)Nr]r^)rMmodel_input_namesrLrj)rKtokenizer_input_namesimage_processor_input_namess r'r"ColPaliProcessor.model_input_namess? $ @ @DTV^C_ _&*&:&:&L&L#)GHHr&c.URR$)zr Return the query augmentation token. Query augmentation buffers are used as reasoning buffers during inference. )rM pad_token)rKs r'ro)ColPaliProcessor.query_augmentation_tokens~~'''r&c *UR"SSU0UD6$)av 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`. rQrr{)rKrQrSs r'process_imagesColPaliProcessor.process_imagess>}}5F5f55r&c *UR"SSU0UD6$)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 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`). rRrr)rKrRrSs r'process_queries ColPaliProcessor.process_queriess<}}1$1&11r&query_embeddingsz torch.Tensorpassage_embeddings batch_size output_dtypez torch.dtype output_devicez torch.devicec [U5S:Xa [S5e[U5S:Xa [S5eUSRUSR:wa [S5eUSRUSR:wa [S5eUcUSRn/n[ S[U5U5GHn/n[ R RRRXXs-SSS9n [ S[U5U5H}n [ R RRRX*X-SSS9n UR[ R"SX5RS S 9SRS S 95 M UR[ R"US S 9RU5RU55 GM [ R"USS 9$) a 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)dimrX)rfr@devicedtyperangetorchnnutilsrnn pad_sequencerpeinsummaxsumcatto) rKrrrrrscoresi batch_scores batch_queriesjbatch_passagess r'score_retrieval ColPaliProcessor.score_retrieval.s@  A %23 3 ! "a '34 4 A  % %);A)>)E)E ENO O A  $ $(:1(=(C(C CLM M  +A.44L%'q#./:\]"A"##LL-PTTYZT[\]^bbghbi C MM%))La8;;LILL][ \=yyQ''r&)r:r1rDr8r7)NNNzDescribe the image.z Question: )NN)N)r*Ncpu)r r!r"r#rnrJrrrrrjr rrr{rpropertyrrorrrintrrr% __classcell__)rOs@r'r5r5Js$9( #R " #R  #R#RJ%)Z^XT!X++d9o=EV@WWX/0 X  XXt-$II (#((%)6T!6/06  6B2$y/)2/02  2H0449 >(^0D DE>(".$~2F"FG>( >( }- >( ^S01 >( >(>(r&r5)typingrrfeature_extraction_utilsr image_utilsrrprocessing_utilsr r r r tokenization_utils_baser rrrrrrrrArrFr3r5__all__)rs0r'rs,#4?XXOO7 -U  ).t5A$qgQ5RWX[R\8]R\Q4#waR\8]] N,a(~a(a(H  } 68]s B%8B*