T^(h?i ddlZddlZddlmZmZmZmZddlZddl m Z ddl m Z m Z mZmZddlmZmZmZmZer ddlZddlmZer ddlZdd lmZGd d eZGd d e Ze eddGddeZeZy)N)ListOptionalTupleUnion)BasicTokenizer) ExplicitEnumadd_end_docstringsis_tf_availableis_torch_available)ArgumentHandler ChunkPipelineDatasetbuild_pipeline_init_args)/TF_MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMES),MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMESc,eZdZdZdeeeeffdZy)"TokenClassificationArgumentHandlerz5 Handles arguments for token classification. inputsc |;t|ttfr%t|dkDrt|}t|}nUt|tr|g}d}n?t t|t st|t jr|dfStd|jd}|r?t|trt|dtr|g}t||k7r td||fS)Nrr zAt least one input is required.offset_mappingz;offset_mapping should have the same batch size as the input) isinstancelisttuplelenstrrtypes GeneratorType ValueErrorget)selfrkwargs batch_sizers i/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/pipelines/token_classification.py__call__z+TokenClassificationArgumentHandler.__call__ s  *VdE]"CF VW&\FVJ  $XFJ  Z%@JvW\WjWjDk4< >? ?$45 .$/J~a?PRW4X"0!1>"j0 !^__~%%N)__name__ __module__ __qualname____doc__rrrr&r'r%rrs &uS$s)^4&r'rc$eZdZdZdZdZdZdZdZy)AggregationStrategyzDAll the valid aggregation strategies for TokenClassificationPipelinenonesimplefirstaveragemaxN) r(r)r*r+NONESIMPLEFIRSTAVERAGEMAXr,r'r%r.r.5sN D F EG Cr'r.T) has_tokenizera ignore_labels (`List[str]`, defaults to `["O"]`): A list of labels to ignore. grouped_entities (`bool`, *optional*, defaults to `False`): DEPRECATED, use `aggregation_strategy` instead. Whether or not to group the tokens corresponding to the same entity together in the predictions or not. stride (`int`, *optional*): If stride is provided, the pipeline is applied on all the text. The text is split into chunks of size model_max_length. Works only with fast tokenizers and `aggregation_strategy` different from `NONE`. The value of this argument defines the number of overlapping tokens between chunks. In other words, the model will shift forward by `tokenizer.model_max_length - stride` tokens each step. aggregation_strategy (`str`, *optional*, defaults to `"none"`): The strategy to fuse (or not) tokens based on the model prediction. - "none" : Will simply not do any aggregation and simply return raw results from the model - "simple" : Will attempt to group entities following the default schema. (A, B-TAG), (B, I-TAG), (C, I-TAG), (D, B-TAG2) (E, B-TAG2) will end up being [{"word": ABC, "entity": "TAG"}, {"word": "D", "entity": "TAG2"}, {"word": "E", "entity": "TAG2"}] Notice that two consecutive B tags will end up as different entities. On word based languages, we might end up splitting words undesirably : Imagine Microsoft being tagged as [{"word": "Micro", "entity": "ENTERPRISE"}, {"word": "soft", "entity": "NAME"}]. Look for FIRST, MAX, AVERAGE for ways to mitigate that and disambiguate words (on languages that support that meaning, which is basically tokens separated by a space). These mitigations will only work on real words, "New york" might still be tagged with two different entities. - "first" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. Words will simply use the tag of the first token of the word when there is ambiguity. - "average" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. scores will be averaged first across tokens, and then the maximum label is applied. - "max" : (works only on word based models) Will use the `SIMPLE` strategy except that words, cannot end up with different tags. Word entity will simply be the token with the maximum score.ceZdZdZdZeffd Z d deedeedee dee e e e fd ee f d Z d eee efffd Zd!d ZdZe j&dfdZdZdedej.dej.dee e e e fdej.de de efdZde ede de efdZde ede defdZde ede de efdZde edefdZdede eeffdZde ede efdZxZ S)"TokenClassificationPipelineuv Named Entity Recognition pipeline using any `ModelForTokenClassification`. See the [named entity recognition examples](../task_summary#named-entity-recognition) for more information. Example: ```python >>> from transformers import pipeline >>> token_classifier = pipeline(model="Jean-Baptiste/camembert-ner", aggregation_strategy="simple") >>> sentence = "Je m'appelle jean-baptiste et je vis à montréal" >>> tokens = token_classifier(sentence) >>> tokens [{'entity_group': 'PER', 'score': 0.9931, 'word': 'jean-baptiste', 'start': 12, 'end': 26}, {'entity_group': 'LOC', 'score': 0.998, 'word': 'montréal', 'start': 38, 'end': 47}] >>> token = tokens[0] >>> # Start and end provide an easy way to highlight words in the original text. >>> sentence[token["start"] : token["end"]] ' jean-baptiste' >>> # Some models use the same idea to do part of speech. >>> syntaxer = pipeline(model="vblagoje/bert-english-uncased-finetuned-pos", aggregation_strategy="simple") >>> syntaxer("My name is Sarah and I live in London") [{'entity_group': 'PRON', 'score': 0.999, 'word': 'my', 'start': 0, 'end': 2}, {'entity_group': 'NOUN', 'score': 0.997, 'word': 'name', 'start': 3, 'end': 7}, {'entity_group': 'AUX', 'score': 0.994, 'word': 'is', 'start': 8, 'end': 10}, {'entity_group': 'PROPN', 'score': 0.999, 'word': 'sarah', 'start': 11, 'end': 16}, {'entity_group': 'CCONJ', 'score': 0.999, 'word': 'and', 'start': 17, 'end': 20}, {'entity_group': 'PRON', 'score': 0.999, 'word': 'i', 'start': 21, 'end': 22}, {'entity_group': 'VERB', 'score': 0.998, 'word': 'live', 'start': 23, 'end': 27}, {'entity_group': 'ADP', 'score': 0.999, 'word': 'in', 'start': 28, 'end': 30}, {'entity_group': 'PROPN', 'score': 0.999, 'word': 'london', 'start': 31, 'end': 37}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This token recognition pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"ner"` (for predicting the classes of tokens in a sequence: person, organisation, location or miscellaneous). The models that this pipeline can use are models that have been fine-tuned on a token classification task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=token-classification). sequencesct||i||j|jdk(rtnt t d|_||_y)NtfF) do_lower_case) super__init__check_model_type frameworkrrr_basic_tokenizer _args_parser)r" args_parserargsr# __class__s r%rAz$TokenClassificationPipeline.__init__sN $)&) ~~% <= !/U C'r'Ngrouped_entitiesignore_subwordsaggregation_strategyrstrideci}|||d<i}||p|r|rtj}n%|r|stj}ntj}|t j d|d|t j d|d|~t |trt|j}|tjtjtjhvr!|jjs td||d<|||d<|s||jjk\r td|tjk(rtd |d |jjr d d |d } | |d <n td|i|fS)Nrzl`grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="z "` instead.zk`ignore_subwords` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy="z{Slow tokenizers cannot handle subwords. Please set the `aggregation_strategy` option to `"simple"` or use a fast tokenizer.rK ignore_labelszl`stride` must be less than `tokenizer.model_max_length` (or even lower if the tokenizer adds special tokens)zI`stride` was provided to process all the text but `aggregation_strategy="z&"`, please select another one instead.T)return_overflowing_tokenspaddingrLtokenizer_paramszm`stride` was provided to process all the text but you're using a slow tokenizer. Please use a fast tokenizer.)r.r6r5r4warningswarnrrupperr8r7 tokenizeris_fastr model_max_length) r"rNrIrJrKrrLpreprocess_paramspostprocess_paramsrQs r%_sanitize_parametersz0TokenClassificationPipeline._sanitize_parameterss  %2@ . /  '?+FO':'@'@$!/':'A'A$':'?'?$+ //C.DKQ* //C.DKQ +.4':;O;U;U;W'X$$'--/B/F/FH[HcHcde.. >:N 5 6  $2?  /  888 C$':'?'?? ,--SU >>))59#'"(($ =M%&89$8!"&888r'rc ^|j|fi|\}}|r||d<t||fi|S)a Classify each token of the text(s) given as inputs. Args: inputs (`str` or `List[str]`): One or several texts (or one list of texts) for token classification. Return: A list or a list of list of `dict`: Each result comes as a list of dictionaries (one for each token in the corresponding input, or each entity if this pipeline was instantiated with an aggregation_strategy) with the following keys: - **word** (`str`) -- The token/word classified. This is obtained by decoding the selected tokens. If you want to have the exact string in the original sentence, use `start` and `end`. - **score** (`float`) -- The corresponding probability for `entity`. - **entity** (`str`) -- The entity predicted for that token/word (it is named *entity_group* when *aggregation_strategy* is not `"none"`. - **index** (`int`, only present when `aggregation_strategy="none"`) -- The index of the corresponding token in the sentence. - **start** (`int`, *optional*) -- The index of the start of the corresponding entity in the sentence. Only exists if the offsets are available within the tokenizer - **end** (`int`, *optional*) -- The index of the end of the corresponding entity in the sentence. Only exists if the offsets are available within the tokenizer r)rEr@r&)r"rr#_inputsrrHs r%r&z$TokenClassificationPipeline.__call__sD4#4$"3"3F"Ef"E '5F# $w1&11r'c +K|jdi}|jjr|jjdkDrdnd}|j|f|j|d|jjd|}|jddt |d}t |D]}|jdk(r;|jD cic]\} } | tj| |d!} } } n5|jD cic]\} } | | |jd} } } ||| d <|dk(r|nd| d <||d z k(| d <| ycc} } wcc} } ww) NrQrTF)return_tensors truncationreturn_special_tokens_maskreturn_offsets_mappingoverflow_to_sample_mapping input_idsr>rsentencer is_last) poprUrWrCrVrrangeitemsr> expand_dims unsqueeze) r"rdrrXrQr_r num_chunksikv model_inputss r% preprocessz&TokenClassificationPipeline.preprocesss^,001CRH!^^<<A`A`cdAdTjo   >>!'+#'>>#9#9      /6 ,- z" A~~%GM||~Vtq!2>>!A$#: :V VAGPA1Q4>>!#4 4P P)1? -.346xtL $&':>&9L #  VPsC E$E2E E(4EcB|jd}|jdd}|jd}|jd}|jdk(r|jd i|d}n,|jd i|}t|tr|dn|d}|||||d|S) Nspecial_tokens_maskrrdrer>rlogits)rsrrrrdrer,)rfrCmodelrdict)r"rorrrrdrersoutputs r%_forwardz$TokenClassificationPipeline._forwards*../DE%))*:DA##J/""9- >>T !TZZ/,/2FTZZ/,/F)3FD)AVH%vayF#6,      r'c |dg}g}|D]}|jdk(rf|ddjtjtjfvr4|ddj tj j}n|ddj}|dd}|dd}|d|ddnd} |ddj} tj|d d } tj|| z } | | jd d z } |jd k(r$|j}| | jnd} |j||| | | |}|j||}|Dcgc],}|jd d|vr|jdd|vr|.}}|j|t!|}|dkDr|j#|}|Scc}w)NOptrsrrdrcrrrT)axiskeepdimsr>entity entity_groupr )rCdtypetorchbfloat16float16tofloat32numpynpr3expsumgather_pre_entities aggregater!extendraggregate_overlapping_entities)r" all_outputsrKrN all_entities model_outputsrsrdrcrrrmaxes shifted_expscores pre_entitiesrIr~entitiesrks r% postprocessz'TokenClassificationPipeline.postprocess+s   EM ( *M~~%-*A!*D*J*Ju~~_d_l_lNm*m&x0366u}}EKKM&x0399;"1~j1H%k215I6CDT6U6a ./2gk #00E"Fq"I"O"O"Q FF6T:E&&%0K ;??T?#JJF~~%%OO- ;I;U!5!5!7[_33)V^=PRfL $~~l>>|LLs31Gc:t|dk(r|St|d}g}|d}|D]_}|d|dcxkr|dkr6nn3|d|dz }|d|dz }||kDr|}8||k(s>|d|dkDsJ|}M|j||}a|j||S)Nrc |dS)Nstartr,)xs r%zLTokenClassificationPipeline.aggregate_overlapping_entities..Xs !G*r'keyrendscore)rsortedappend)r"raggregated_entitiesprevious_entityr~current_lengthprevious_lengths r%rz:TokenClassificationPipeline.aggregate_overlapping_entitiesUs x=A O((<= "1+ )Fw'6'?S_U=SS!'!@"1%"8?7;S"S!O3&,O#66'?_]dMe;e&,O#**?;"( ) ""?3""r'rdrcrrrreturnc2g}t|D]\}} ||r |jjt||} |/||\} } t | ts/|j dk(r | j } | j } || | } t|jddrCt|jjjddrt| t| k7}n_|tjtjtjhvrtj dt"| dkDxr d|| dz | dzv}t|||jj$k(r | } d }nd} d} d }| | | | ||d }|j'||S) zTFuse various numpy arrays into dicts with all the information needed for aggregationNrz _tokenizercontinuing_subword_prefixz?Tokenizer does not support real words, using fallback heuristicr r F)wordrrrindex is_subword) enumeraterUconvert_ids_to_tokensintrrCitemgetattrrrtrr.r6r7r8rRrS UserWarning unk_token_idr)r"rdrcrrrrrKridx token_scoresr start_indend_indword_refr pre_entitys r%rz/TokenClassificationPipeline.gather_pre_entitiesis !*6!20 , C"3'>>77IcN8KLD)%3C%8" 7!)S1~~-$-NN$4 "),,.#Ig64>><>7NN--335PRVD "%Tc(m!;J,+11+33+//0 ! ]'"+Q!e3hyST}W`cdWd>e3eJy~&$..*E*EE#D!&J " &"( J    +a0 ,br'rc|tjtjhvrlg}|D]d}|dj}|d|}|jj j |||d|d|d|dd}|j|fn|j||}|tjk(r|S|j|S)Nrrrrr)r~rrrrr) r.r4r5argmaxrtconfigid2labelraggregate_wordsgroup_entities)r"rrKrr entity_idxrr~s r%rz%TokenClassificationPipeline.aggregates $7$<$<>Q>X>X#Y YH* ( '188: "8,Z8"jj//88D"'0&v.'0%e, ' (++L:NOH #6#;#; ;O""8,,r'rc(|jj|Dcgc]}|d c}}|tjk(rA|dd}|j }||}|j j j|}n|tjk(rLt|d}|d}|j }||}|j j j|}n|tjk(rvtj|Dcgc]}|d c}}tj|d} | j } |j j j| }| | }n td||||dd|d d d } | Scc}wcc}w) Nrrrc(|djS)Nr)r3)r~s r%rz.s&:J:N:N:Pr'r)r|zInvalid aggregation_strategyrr{r)r~rrrr)rUconvert_tokens_to_stringr.r6rrtrrr8r3r7rstacknanmeanr ) r"rrKr~rrrr max_entityaverage_scoresr new_entitys r%aggregate_wordz*TokenClassificationPipeline.aggregate_words|~~66U]7^6v7^_ #6#<#< <a[*F--/C3KEZZ&&//4F !%8%<%< <X+PQJ)F--/C3KEZZ&&//4F !%8%@%@ @XXhGFvh/GHFZZQ7N'..0JZZ&&// ;F":.E;< <a[)B<&  78_Hs F  Fc>|tjtjhvr tdg}d}|D]C}||g} |dr|j | |j |j |||g}E|!|j |j |||S)z Override tokens from a given word that disagree to force agreement on word boundaries. Example: micro|soft| com|pany| B-ENT I-NAME I-ENT I-ENT will be rewritten with first strategy as microsoft| company| B-ENT I-ENT z;NONE and SIMPLE strategies are invalid for word aggregationNr)r.r4r5r rr)r"rrK word_entities word_groupr~s r%rz+TokenClassificationPipeline.aggregate_wordss  $ $  & &$  Z[ [   &F!$X  %!!&)$$T%8%8EY%Z[$X  &  !  !4!4ZAU!V Wr'c@|ddjddd}tj|Dcgc]}|d c}}|Dcgc]}|d }}tj||jj ||dd|dd d }|Scc}wcc}w) z Group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. rr~-r r{rrrr)rrrrr)splitrrmeanrUr)r"rr~rtokensrs r%group_sub_entitiesz.TokenClassificationPipeline.group_sub_entitiess!X&,,S!4R88DVG_DE/78V&.88#WWV_NN;;FCa[)B<&  E8s B B entity_namec|jdr d}|dd}||fS|jdr d}|dd}||fSd}|}||fS)NzB-BrzI-I) startswith)r"rbitags r%get_tagz#TokenClassificationPipeline.get_tag sk  ! !$ 'Bab/C3w # #D )Bab/C 3wBC3wr'chg}g}|D]}|s|j||j|d\}}|j|dd\}}||k(r|dk7r|j|d|j|j||g}|r |j|j||S)z Find and group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. r~r{r)rrr) r"r entity_groupsentity_group_disaggr~rrlast_bilast_tags r%rz*TokenClassificationPipeline.group_entitiess   /F&#**62 ll6(#34GB $ -@-DX-N O GXh29#**62$$T%<%<=P%QR'-h#' /(   !8!89L!M Nr')NNNNNN)N)!r(r)r*r+default_input_namesrrArboolr.rrrrZrrr&rprwr4rrrndarrayrurrrrrrr __classcell__)rHs@r%r;r;?sF"H&#E#G (+/*.>B:> $G9#4.G9"$ G9 '':; G9 !eCHo!67 G9 G9R2uS$s)^42@4 *=Pmodels.auto.modeling_tf_autorrmodels.auto.modeling_autorrr.r; NerPipeliner,r'r%rs //: TS^X&&4,40n!D\-\E!D\~* r'