HioddlZddlZddlmZmZddlZddlmZddl m Z m Z m Z ddl mZmZmZmZe r ddlZddlmZGd d eZGd d e Ze ed dGddeZeZy)N)Anyoverload)BasicTokenizer) ExplicitEnumadd_end_docstringsis_torch_available)ArgumentHandler ChunkPipelineDatasetbuild_pipeline_init_args),MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMESc(eZdZdZdeeezfdZy)"TokenClassificationArgumentHandlerz5 Handles arguments for token classification. inputsc |jdd}|jd}|;t|ttfr%t |dkDrt|}t |}nWt|t r|g}d}nAt t|t st|tjr||d|fStd|jd}|r?t|trt|dtr|g}t ||k7r td||||fS) Nis_split_into_wordsF delimiterrr zAt least one input is required.offset_mappingz;offset_mapping should have the same batch size as the input) get isinstancelisttuplelenstrr types GeneratorType ValueError)selfrkwargsrr batch_sizers m/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/transformers/pipelines/token_classification.py__call__z+TokenClassificationArgumentHandler.__call__s$jj)>FJJ{+  *VdE]"CF VW&\FVJ  $XFJ  Z%@JvW\WjWjDk.i? ?>? ?$45 .$/J~a?PRW4X"0!1>"j0 !^__*NIEEN)__name__ __module__ __qualname____doc__rrr$r%r#rrsFsT#YFr%rc$eZdZdZdZdZdZdZdZy)AggregationStrategyzDAll the valid aggregation strategies for TokenClassificationPipelinenonesimplefirstaveragemaxN) r&r'r(r)NONESIMPLEFIRSTAVERAGEMAXr*r%r#r,r,3sN D F EG Cr%r,T) has_tokenizera ignore_labels (`list[str]`, defaults to `["O"]`): A list of labels to ignore. 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.ceZdZdZdZdZdZdZdZe ffd Z d'de dzde e eefdzd ed edzd edzf d Zed edede eeeffdZed e edede e eeeffdZd ee ezdede eeefe e eeefzffd Zd(dZdZe j0dfdZdZ d)dedej8dej8de e eefdzdej8de de edzdzde e eefdzde efdZde ede de efdZd e ede defd!Zd e ede de efd"Z d e edefd#Z!d$ede eeffd%Z"d e ede efd&Z#xZ$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). sequencesFTc ~t|di||jtt d|_||_y)NF) do_lower_caser*)super__init__check_model_typerr_basic_tokenizer _args_parser)r args_parserr! __class__s r#r>z$TokenClassificationPipeline.__init__s7 "6" JK .U C'r%Naggregation_strategyrrstriderc:i}||d<|r |dn||d<|||d<i}|~t|trt|j}|tjtj tj hvr!|jjs td||d<|||d<|s||jjk\r td|tjk(rtd |d |jjr d d |d } | |d <n td|i|fS)Nr rrz{Slow tokenizers cannot handle subwords. Please set the `aggregation_strategy` option to `"simple"` or use a fast tokenizer.rD 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_tokenspaddingrEtokenizer_paramszm`stride` was provided to process all the text but you're using a slow tokenizer. Please use a fast tokenizer.) rrr,upperr4r6r5 tokenizeris_fastrmodel_max_lengthr2) r rHrDrrrErpreprocess_paramspostprocess_paramsrKs r#_sanitize_parametersz0TokenClassificationPipeline._sanitize_parameterss}3F/0 4=4ES9 k *  %2@ . /  +.4':;O;U;U;W'X$$'--/B/F/FH[HcHcde.. >:N 5 6  $2?  /  888 C$':'?'?? ,--SU >>))59#'"(($ =M%&89$8!"&888r%rr!returnc yNr*r rr!s r#r$z$TokenClassificationPipeline.__call__sLOr%c yrUr*rVs r#r$z$TokenClassificationPipeline.__call__sX[r%c |j|fi|\}}}}||d<||d<|r#td|Dst| |gfi|S|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. Can be pre-tokenized when `is_split_into_words=True`. 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 rrc3<K|]}t|tywrU)rr).0inputs r# z7TokenClassificationPipeline.__call__..s*Wu:eT+B*Wsr)rAallr=r$)r rr!_inputsrrrrCs r#r$z$TokenClassificationPipeline.__call__s6CT$BSBSTZBe^dBe?$ni(;$%'{ s*WPV*W'W7#VH77 7 '5F# $w1&11r%c +K|jdi}|jjxr|jjdkD}d}|d}|r|d}t|ts t d|} |j | }g}t|} d} | D]2} |j| | t| zf| t| | zz } 4| } d|d<nt|ts t d|} |j| fd|d|jjd |}|r!|jjs t d |jd dt|d }t|D]t}|jDcic]\}}|||jd}}}|||d <|dk(r|nd|d<||dz k(|d<||j||d<||d<|vycc}}ww)NrKrrrzEWhen `is_split_into_words=True`, `sentence` must be a list of tokens.TzKWhen `is_split_into_words=False`, `sentence` must be an untokenized string.pt)return_tensors truncationreturn_special_tokens_maskreturn_offsets_mappingz@is_split_into_words=True is only supported with fast tokenizers.overflow_to_sample_mapping input_idsrsentencer is_lastword_idsword_to_chars_map)poprMrOrrrjoinrappendrrNrangeitems unsqueezeri)r rgrrPrKrbrjrrwords delimiter_len char_offsetwordtext_to_tokenizer num_chunksikv model_inputss r# preprocessz&TokenClassificationPipeline.preprocesss!,001CRH^^44\9X9X[\9\  /0EF )+6Ih- !hiiE ~~e,H "  NMK 9!((+{SY7N)OPs4y=88  9 % 6: 2 3h, !noo'   !'+#'>>#9#9     t~~'='=_` ` /6 ,- z" A=C\\^LTQAqt~~a00LLL)1? -.346xtL $&':>&9L # ,+1??1+= Z(4E 01  LsE;G%=GA G%cD|jd}|jdd}|jd}|jd}|jdd}|jdd}|jd i|}t|tr|dn|d} | ||||||d |S) Nspecial_tokens_maskrrgrhrirjlogitsr)r~r}rrgrhrirjr*)rkmodelrdict) r rzr}rrgrhrirjoutputr~s r#_forwardz$TokenClassificationPipeline._forward.s*../DE%))*:DA##J/""9-##J5(,,-@$G+l+%/%=!6!9#6,  !2    r%c |dg}g}|djd}|D]~}|ddjtjtjfvr4|ddj tj j}n|ddj}|dd}|dd} |d|ddnd} |ddj} |jd } tj|d d } tj|| z }||jd d z }|j|| || | || | }|j||}|Dcgc],}|jdd|vr|jdd|vr|.}}|j|t|}|dkDr|j!|}|Scc}w)NOrrjr~rgrfrr}riT)axiskeepdims)rirjentity entity_groupr )rdtypetorchbfloat16float16tofloat32numpynpr1expsumgather_pre_entities aggregateextendraggregate_overlapping_entities)r all_outputsrDrH all_entitiesrj model_outputsr~rgrfrr}rimaxes shifted_expscores pre_entitiesgrouped_entitiesrentitiesrvs r# postprocessz'TokenClassificationPipeline.postprocessEs    EM (N../BC($ *MX&q)//ENNEMM3RR&x0366u}}EKKM&x0399;"1~j1H%k215I6CDT6U6a ./2gk #00E"Fq"I"O"O"Q $((4HFF6T:E&&%0K ;??T?#JJF33#$!"34 L $~~l>>|LLs1Gc4t|dk(r|St|d}g}|d}|D]\}|d|dcxkr|dkr3nn0|d|dz }|d|dz }||kDs||k(s;|d|dkDsG|}J|j||}^|j||S)Nrc |dS)Nstartr*)xs r#zLTokenClassificationPipeline.aggregate_overlapping_entities..zs !G*r%keyrendscore)rsortedrm)r raggregated_entitiesprevious_entityrcurrent_lengthprevious_lengths r#rz:TokenClassificationPipeline.aggregate_overlapping_entitiesws x=A O((<= "1+ )Fw'6'?S_U=SS!'!@"1%"8?7;S"S"_4%8w/'*BB&,O#**?;"( ) ""?3""r%rgrfrr}rirjc Ng} t|D]\} } || r |jjt|| } |=|| \} }|||| }|||\}}| |z } ||z }t | ts | j } |j }|| |}t |jddrCt |jjjddrt| t|k7}n_|tjtjtjhvrtjdt | 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 aggregationN _tokenizercontinuing_subword_prefixz?Tokenizer does not support real words, using fallback heuristicrrGr F)rtrrrindex is_subword) enumeraterMconvert_ids_to_tokensintritemgetattrrrrr,r4r5r6warningswarn UserWarning unk_token_idrm)r rgrfrrr}rDrirjridx token_scoresrt start_indend_ind word_index start_char_word_refr pre_entitys r#rz/TokenClassificationPipeline.gather_pre_entitiess !*6!28 , C"3'>>77IcN8KLD)%3C%8" 7',=,I!)#J!-(9*(E A!Z/ :-!)S1 ) 0I%llnG#Ig64>><>7NN--335PRVD "%Tc(m!;J,+11+33+//0 ! ]'"+Q!e3hyST}W`cdWd>e3eJy~&$..*E*EE#D!&J " &"( J    +q8 ,rr%rc|tjtjhvrlg}|D]d}|dj}|d|}|jj j |||d|d|d|dd}|j|fn|j||}|tjk(r|S|j|S)Nrrrtrr)rrrrtrr) r,r2r3argmaxrconfigid2labelrmaggregate_wordsgroup_entities)r rrDrr entity_idxrrs 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) Nrtrrc(|djS)Nr)r1)rs r#rz.s&:J:N:N:Pr%r)rzInvalid aggregation_strategyrrr)rrrtrr)rMconvert_tokens_to_stringr,r4rrrrr6r1r5rstacknanmeanr) r rrDrrtrrr 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,r2r3rrmr)r rrD word_entities word_grouprs r#rz+TokenClassificationPipeline.aggregate_words s  $ $  & &$  Z[ [   &F!$X  %!!&)$$T%8%8EY%Z[$X  &  !  !4!4ZAU!V Wr%c@|ddjddd}tj|Dcgc]}|d c}}|Dcgc]}|d }}tj||jj ||dd|dd d }|Scc}wcc}w) z Group together the adjacent tokens with the same entity predicted. Args: entities (`dict`): The entities predicted by the pipeline. rr-r rrrtrr)rrrtrr)splitrrmeanrMr)r rrrtokensrs r#group_sub_entitiesz.TokenClassificationPipeline.group_sub_entities%s!X&,,S!4R88DVG_DE/78V&.88#WWV_NN;;FCa[)B<&  E8s B B entity_namec|jdr d}|dd}||fS|jdr d}|dd}||fSd}|}||fS)NzB-BrzI-I) startswith)r rbitags r#get_tagz#TokenClassificationPipeline.get_tag:sk  ! !$ '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. rrr)rmrr) r r entity_groupsentity_group_disaggrrrlast_bilast_tags r#rz*TokenClassificationPipeline.group_entitiesHs   /F&#**62 ll6(#34GB $ -@-DX-N O GXh29#**62$$T%<%<=P%QR'-h#' /(   !8!89L!M Nr%)NNNFNNrU)NN)%r&r'r(r)default_input_names_load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr>r,rrrboolrrRrrrr$r{rr2rrrndarrayrrrrrrr __classcell__)rCs@r#r9r9=s@"H&O!#O#E#G(;?7;$)! $992D899U38_-4 99 " 99 d 99:99vOsOcOd4S>6JOO [tCy[C[Dd3PS8nAUFF::F F U38_-4 F  ZZ F2FsTz"T)F c3h047F dFP-d4j-H[-`dei`j-,tDzI\ae<T J]bfgkbl84:$* 3 5c? #tDz#d4j#r%r9)rrtypingrrrr$models.bert.tokenization_bert_legacyrutilsrrr baser r r rrmodels.auto.modeling_autorrr,r9 NerPipeliner*r%r#rs  A TSXFF:,40n>O-O?>Od* r%