fThtQSSKrSSKrSSKrSSKJr SSKJrJrJ r J r SSK J r J r JrJrJr \ "5(a SSKrSSKJrJr \"5(a SSKrSSKJrJr "S S \ 5r\"\"S S 95"S S\55rg)N)GenerationConfig)add_end_docstringsis_tf_availableis_torch_availablerequires_backends)ArgumentHandlerDatasetPipelinePipelineExceptionbuild_pipeline_init_args),MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES0MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMES)/TF_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES3TF_MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMESc"\rSrSrSrSSjrSrg)%TableQuestionAnsweringArgumentHandler!z: Handles arguments for the TableQuestionAnsweringPipeline Nc T[US5 SSKnUc [S5eUGc/[U[5(a(UR S5bUR S5bU/nO[U[ 5(a[U5S:ay[SU55(d[SSU535eUSR S5bUSR S5bUnOz[S USR5S 35e[b[U[5(d[U[R5(aU$[S [U5S 35eXS ./nUHKn[USUR5(aM#USc [S5eURUS5US'MM U$)Npandasrz(Keyword argument `table` cannot be None.querytablec3B# UHn[U[5v M g7fN) isinstancedict.0ds g/var/www/auris/envauris/lib/python3.13/site-packages/transformers/pipelines/table_question_answering.py ATableQuestionAnsweringArgumentHandler.__call__..6s>1:a..sz:Keyword argument `table` should be a list of dict, but is c38# UHn[U5v M g7fr)typers r!r"r#8sUmglbcVZ[\V]V]glszIf keyword argument `table` is a list of dictionaries, each dictionary should have a `table` and `query` key, but only dictionary has keys z `table` and `query` keys.zZInvalid input. Keyword argument `table` should be either of type `dict` or `list`, but is ))rrzTable cannot be None.)rr ValueErrorrrgetlistlenallkeysr types GeneratorTyper% DataFrame)selfrrkwargspdtqa_pipeline_inputstqa_pipeline_inputs r!__call__.TableQuestionAnsweringArgumentHandler.__call__&s $) =GH H ]%&&599W+=+IeiiX_N`Nl',g#E4((SZ!^>>>>$TUmglUmTno8<<(4qg9N9Z*/'$JJOPQ(--/IZZtv$E7)C)CzRWY^YlYlGmGm  u+a) .3#C"D "5 092<<HH%g.6$%<==.0ll;Mg;V.W"7+ #6#")NN)__name__ __module__ __qualname____firstlineno____doc__r5__static_attributes__r8r7r!rr!s -#r7rT) has_tokenizerc^\rSrSrSrSrSr\"SS9r\ "54U4Sjjr Sr S r U4S jr SS jrSS jrSS jrSrSrU=r$)TableQuestionAnsweringPipelineVah Table Question Answering pipeline using a `ModelForTableQuestionAnswering`. This pipeline is only available in PyTorch. Unless the model you're using explicitly sets these generation parameters in its configuration files (`generation_config.json`), the following default values will be used: - max_new_tokens: 256 Example: ```python >>> from transformers import pipeline >>> oracle = pipeline(model="google/tapas-base-finetuned-wtq") >>> table = { ... "Repository": ["Transformers", "Datasets", "Tokenizers"], ... "Stars": ["36542", "4512", "3934"], ... "Contributors": ["651", "77", "34"], ... "Programming language": ["Python", "Python", "Rust, Python and NodeJS"], ... } >>> oracle(query="How many stars does the transformers repository have?", table=table) {'answer': 'AVERAGE > 36542', 'coordinates': [(0, 1)], 'cells': ['36542'], 'aggregator': 'AVERAGE'} ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This tabular question answering pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"table-question-answering"`. The models that this pipeline can use are models that have been fine-tuned on a tabular question answering task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=table-question-answering). z table,queryT)max_new_tokenscF>[TU]"U0UD6 XlURS:Xa+[R "5nUR [5 O*[R "5nUR [5 URU5 [[URRSS55=(a* [[URRSS55Ul[!URRS5(aSUlgSUlg)Ntfaggregation_labelsnum_aggregation_labelstapas)super__init__ _args_parser frameworkrcopyupdaterrrcheck_model_typeboolgetattrmodelconfig aggregatehasattrr%)r0 args_parserargsr1mapping __class__s r!rK'TableQuestionAnsweringPipeline.__init__s $)&)' >>T !INNPG NNJ KFKKMG NNG H g&gdjj&7&79MtTU Z^ DJJ%%'? F[  'tzz'8'8:NOOG UY r7c &UR"S0UD6$)Nr8)rS)r0inputss r!batch_inference.TableQuestionAnsweringPipeline.batch_inferenceszz#F##r7c URS:XGa/n/nSnUSRSnUSRUR5nUSRUR5nUSRUR5nSn [ U5GH=n UGb.U SS2S4n [ R "U R5R55n Xn [ U RS5Hn U SS2S4R5U nU SS2S4R5U S- nU SS2S 4R5U S- nUS:dM_US:dMgUS:XdMo[XOU45X'M [R"U 5R[R5RUR5U SS2S4'XjnXznXn URUR!S5UR!S5U R!S5S 9nUR"nUR$(aUR'UR(5 UR'U5 [R*R-US 9nUR.UR[R05RUR.R5-n[2R4"[65n[9UR;5R55Hun nU SS2S4R5U nU SS2S4R5U S- nU SS2S 4R5U S- nUS:dMbUS:dMjUS:XdMrUUU4R'U5 M UVs0sH.nU[ R<"UU5R?5S :_M0 nnGM@ [R@"[CU5S5nUR$(dU4$U[R@"[CU5S54$/n/nSnUSRSnUSnUSnUSR5nSn [ U5GHn UbU SS2S4n [ R "U [ RDS 9n Xn [ U RS5Hn U SS2S4R5U nU SS2S4R5U S- nU SS2S 4R5U S- nUS:dM_US:dMgUS:XdMo[XOU45X'M XSS2S4'XjnXznXn UR[ RF"USS9[ RF"USS9[ RF"U SS9S 9nUR"nUR$(aUR'UR(5 UR'U5 [HRJRM[HRN"U[HR055[HRN"U[HR05-n[2R4"[65nU n [9[HR:"U5R5R55Hun nU SS2S4R5U nU SS2S4R5U S- nU SS2S 4R5U S- nUS:dMbUS:dMjUS:XdMrUUU4R'U5 M UVs0sH.nU[ R<"UU5R?5S :_M0 nnGM [HRP"[CU5S5nUR$(dU4$U[HRP"[CU5S54$s snfs snf)z Inference used for models that need to process sequences in a sequential fashion, like the SQA models which handle conversational query related to a table. ptN input_idsrattention_masktoken_type_idsr r)rbrcrd)logitsg?)dtype)axis))rMshapetodevicerangenp zeros_likecpunumpytolistinttorch from_numpyr%longrS unsqueezerfrUappendlogits_aggregation distributions Bernoulliprobsfloat32 collections defaultdictr) enumeratesqueezearraymeancattupleint32 expand_dimsrFmathsigmoidcastconcat)r0r] all_logitsall_aggregations prev_answers batch_sizerbrcrdtoken_type_ids_exampleindexprev_labels_example model_labelsi segment_idcol_idrow_idinput_ids_exampleattention_mask_exampleoutputsrfdist_per_token probabilitiescoords_to_probspcolrowkey logits_batchs r!sequential_inference3TableQuestionAnsweringPipeline.sequential_inferencesL >>T !J! L ,2215J{+..t{{;I#$4588EN#$4588EN%) "z* +*@A*F'#%==1D1H1H1J1P1P1R#SL-;-B*"<#5#5a#89%;AqD%A%H%H%J1%M !71!=!D!D!Fq!IA!M!71!=!D!D!Fq!IA!M!Q;6Q;:?.1,?O2P.QLO :493C3CL3Q3V3VW\WaWa3b3e3efjfqfq3r*1a40$-$4!)7)>&)7)>&**/99!<#9#C#CA#F#9#C#CA#F% !>>$++G,F,FG!!&)!&!4!4!>!>f!>!M . 4 47M7R7RSXS`S`7a7d7d"((//8! #."9"9$"?%m&;&;&=&D&D&FGDAq!71!=!D!D!Fq!IJ0A6==?BQFC0A6==?BQFCaxC1Hq'c 3::1= H]ll\kUXRXXoc.B%C%H%H%JS%P P\k l ]+`!99U:%6:L*...L? s|UYYW\]mWnpqMr>s sJ! L ,2215J{+I#$45N#$45;;=N%) "z* +*@A*F'#%==1DBHH#UL-;-B*"<#5#5a#89%;AqD%A%H%H%J1%M !71!=!D!D!Fq!IA!M!71!=!D!D!Fq!IA!M!Q;6Q;:?.1,?O2P.QLO :4@1a40$-$4!)7)>&)7)>&** nn->QG#%>>2Hq#Q#%>>2Hq#Q% !>>$++G,F,FG!!&) " 0K Lrww*BJJP! #."9"9$"?)?&%bjj&?&E&E&G&N&N&PQDAq!71!=!D!D!Fq!IJ0A6==?BQFC0A6==?BQFCaxC1Hq'c 3::1= R]ll\kUXRXXoc.B%C%H%H%JS%P P\k l ]+`99U:%6:L*...L? s|RYYW\]mWnpqMr>s sE m| ms 5_45_ cv>UR"U0UD6n[TU]"U40UD6n[U5S:XaUS$U$)a2 Answers queries according to a table. The pipeline accepts several types of inputs which are detailed below: - `pipeline(table, query)` - `pipeline(table, [query])` - `pipeline(table=table, query=query)` - `pipeline(table=table, query=[query])` - `pipeline({"table": table, "query": query})` - `pipeline({"table": table, "query": [query]})` - `pipeline([{"table": table, "query": query}, {"table": table, "query": query}])` The `table` argument should be a dict or a DataFrame built from that dict, containing the whole table: Example: ```python data = { "actors": ["brad pitt", "leonardo di caprio", "george clooney"], "age": ["56", "45", "59"], "number of movies": ["87", "53", "69"], "date of birth": ["7 february 1967", "10 june 1996", "28 november 1967"], } ``` This dictionary can be passed in as such, or can be converted to a pandas DataFrame: Example: ```python import pandas as pd table = pd.DataFrame.from_dict(data) ``` Args: table (`pd.DataFrame` or `Dict`): Pandas DataFrame or dictionary that will be converted to a DataFrame containing all the table values. See above for an example of dictionary. query (`str` or `List[str]`): Query or list of queries that will be sent to the model alongside the table. sequential (`bool`, *optional*, defaults to `False`): Whether to do inference sequentially or as a batch. Batching is faster, but models like SQA require the inference to be done sequentially to extract relations within sequences, given their conversational nature. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`): Activates and controls padding. Accepts the following values: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). truncation (`bool`, `str` or [`TapasTruncationStrategy`], *optional*, defaults to `False`): Activates and controls truncation. Accepts the following values: - `True` or `'drop_rows_to_fit'`: Truncate to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. This will truncate row by row, removing rows from the table. - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size). Return: A dictionary or a list of dictionaries containing results: Each result is a dictionary with the following keys: - **answer** (`str`) -- The answer of the query given the table. If there is an aggregator, the answer will be preceded by `AGGREGATOR >`. - **coordinates** (`List[Tuple[int, int]]`) -- Coordinates of the cells of the answers. - **cells** (`List[str]`) -- List of strings made up of the answer cell values. - **aggregator** (`str`) -- If the model has an aggregator, this returns the aggregator. r r)rLrJr5r*)r0rXr1pipeline_inputsresultsrZs r!r5'TableQuestionAnsweringPipeline.__call__sJV++T>#/97;7M7M 34jj))LLLOLG)5RYZ r7chUSnUSnUSnURS:XGaUR(aUSSupVURRX%U5nUup[ U 5V V s0sH(upXR R RU _M* n n n UR R Rn [ U 5V V s0sHupX:wdM XU S-_M nn n O)USnURRX%5nUSn0n 0n/n[ U5HunnUVs/sHnURUPM nnU RUS5nURUS5nUS RU5-UUVs/sHnURUPM snS .nU(aUUS 'URU5 M [W5S:Xa [S 5eO,URRUS S9Vs/sHnSU0PM nn[U5S:aU$US$s sn n fs sn n fs snfs snfs snf)NrrrrIrz > rrz, )answer coordinatescells aggregatorz Empty answerT)skip_special_tokensrr )r%rUrconvert_logits_to_predictionsrrSrTrGno_aggregation_label_indexiatr(joinrwr*r batch_decode)r0rr]rrrf logits_agg predictionsanswer_coordinates_batchagg_predictionsrpred aggregatorsno_agg_label_indexaggregators_prefixanswersrr coordinaterraggregator_prefixrs r! postprocess*TableQuestionAnsweringPipeline.postprocesssS~.g& * 99 ~~%,Ra[""nnJJ6[ef ( %'"G&/0H&I"{ALM::.M(__UB7 $6$:$:5"$E!/$))E2BB#.FQRk eii 3kR +5F<(v&'J6{a'77 9=8S8ST[qu8S8vw8vf&)8vGwg,*w: :?x&N Sxs$'/H H H&H%=H* 3H/)rLrUr%)NNN)NTN)F)r9r:r;r<r=default_input_names_pipeline_calls_generater_default_generation_configrrKr^rr5rrrrr> __classcell__)rZs@r!rArAVsa D(#!1"$I#JZ"$@tDPd5& "(;(;r7rA)r}r-rprm generationrutilsrrrrbaser r r r rrsmodels.auto.modeling_autorr tensorflowrFmodels.auto.modeling_tf_autorrrrAr8r7r!rs ) ba  2#O2#j,4@Ao;Xo;Bo;r7