o hB@sddlZddlZddlmZddlmZmZmZmZddl m Z m Z er/ddl Z ddlmZer8ddlmZeeZGd d d ejZee Gd d d e Zee Gd ddeZee GdddeZdS)N)TruncationStrategy)add_end_docstringsis_tf_availableis_torch_availablelogging)PIPELINE_INIT_ARGSPipeline)/TF_MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMES),MODEL_FOR_SEQ_TO_SEQ_CAUSAL_LM_MAPPING_NAMESc@seZdZdZdZdS) ReturnTyperrN)__name__ __module__ __qualname__TENSORSTEXTrra/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/pipelines/text2text_generation.pyr sr cseZdZdZdZfddZ      dddZded ed efd d Zd dZ fddZ e j fddZ ddZejdfddZZS)Text2TextGenerationPipelineaW Pipeline for text to text generation using seq2seq models. Example: ```python >>> from transformers import pipeline >>> generator = pipeline(model="mrm8488/t5-base-finetuned-question-generation-ap") >>> generator( ... "answer: Manuel context: Manuel has created RuPERTa-base with the support of HF-Transformers and Google" ... ) [{'generated_text': 'question: Who created the RuPERTa-base?'}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial). You can pass text generation parameters to this pipeline to control stopping criteria, decoding strategy, and more. Learn more about text generation parameters in [Text generation strategies](../generation_strategies) and [Text generation](text_generation). This Text2TextGenerationPipeline pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"text2text-generation"`. The models that this pipeline can use are models that have been fine-tuned on a translation task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=text2text-generation). For a list of available parameters, see the [following documentation](https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.generation.GenerationMixin.generate) Usage: ```python text2text_generator = pipeline("text2text-generation") text2text_generator("question: What is 42 ? context: 42 is the answer to life, the universe and everything") ``` generatedcs4tj|i|||jdkrtdStdS)Ntf)super__init__check_model_type frameworkr r selfargskwargs __class__rrrBs z$Text2TextGenerationPipeline.__init__Nc Ksi}|dur ||d<|} i} |dur|dur|rtjntj}|dur&|| d<|dur.|| d<|durK|jj|dd} t| dkrEtd| d|d <|| | fS) N truncation return_typeclean_up_tokenization_spacesF)add_special_tokensrzStopping on a multiple token sequence is not yet supported on transformers. The first token of the stop sequence will be used as the stop sequence string in the interim.r eos_token_id)r rr tokenizerencodelenwarningswarn) rreturn_tensors return_textr#r$r" stop_sequencegenerate_kwargspreprocess_paramsforward_paramspostprocess_paramsstop_sequence_idsrrr_sanitize_parametersKs&    z0Text2TextGenerationPipeline._sanitize_parameters input_length min_length max_lengthcCsdS)j Checks whether there might be something wrong with given input with regard to the model. Trrr5r6r7rrr check_inputsosz(Text2TextGenerationPipeline.check_inputscs|jjjdur |jjjndt|dtr.|jjdurtdfdd|dDf}d}nt|dtr?|df}d}n td|dd |j||||j d }d |vr[|d =|S) NrzOPlease make sure that the tokenizer has a pad_token_id when using a batch inputcsg|]}|qSrr).0argprefixrr zzCText2TextGenerationPipeline._parse_and_tokenize..TFz `args[0]`: zI have the wrong format. The should be either of type `str` or type `list`)paddingr"r,token_type_ids) modelconfigr? isinstancelistr' pad_token_id ValueErrorstrr)rr"rrBinputsrr>r_parse_and_tokenizeus  z/Text2TextGenerationPipeline._parse_and_tokenizecsZtj|i|}t|dtr+tdd|dDr+tdd|Dr+dd|DS|S)a Generate the output text(s) using text(s) given as inputs. Args: args (`str` or `List[str]`): Input text for the encoder. return_tensors (`bool`, *optional*, defaults to `False`): Whether or not to include the tensors of predictions (as token indices) in the outputs. return_text (`bool`, *optional*, defaults to `True`): Whether or not to include the decoded texts in the outputs. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the potential extra spaces in the text output. truncation (`TruncationStrategy`, *optional*, defaults to `TruncationStrategy.DO_NOT_TRUNCATE`): The truncation strategy for the tokenization within the pipeline. `TruncationStrategy.DO_NOT_TRUNCATE` (default) will never truncate, but it is sometimes desirable to truncate the input to fit the model's max_length instead of throwing an error down the line. generate_kwargs: Additional keyword arguments to pass along to the generate method of the model (see the generate method corresponding to your framework [here](./model#generative-models)). Return: A list or a list of list of `dict`: Each result comes as a dictionary with the following keys: - **generated_text** (`str`, present when `return_text=True`) -- The generated text. - **generated_token_ids** (`torch.Tensor` or `tf.Tensor`, present when `return_tensors=True`) -- The token ids of the generated text. rcss|]}t|tVqdS)N)rFrJ)r<elrrr sz7Text2TextGenerationPipeline.__call__..css|] }t|dkVqdS)rN)r)r<resrrrrNscSsg|]}|dqS)rrrOrrrr@rAz8Text2TextGenerationPipeline.__call__..)r__call__rFrGall)rrrresultr rrrQs z$Text2TextGenerationPipeline.__call__cKs|j|fd|i|}|S)Nr")rL)rrKr"rrrr preprocesssz&Text2TextGenerationPipeline.preprocesscKs|jdkr |dj\}}n|jdkrt|d\}}|||d|jjj|d|jjj |jj d i||}|jd}|jdkr\|j |||g|jddR}d|iS|jdkrst ||||g|jddR}d|iS) Npt input_idsrr6r7rr output_idsr) rshapernumpyr:getrDrEr6r7generatereshape)r model_inputsr/in_br5rWout_brrr_forwards"    " $z$Text2TextGenerationPipeline._forwardFcCshg}|ddD])}|tjkr|jd|i}n|tjkr,|jd|jj|d|di}||q|S)NrWr _token_ids_textT)skip_special_tokensr$)r r return_namerr'decodeappend)r model_outputsr#r$recordsrWrecordrrr postprocesss   z'Text2TextGenerationPipeline.postprocess)NNNNNN)rrr__doc__rdrr4intr:rLrQrDO_NOT_TRUNCATErTr`r rrj __classcell__rrr rrs"%   $ &rcs>eZdZdZdZfddZdedededefd d ZZ S) SummarizationPipelinea[ Summarize news articles and other documents. This summarizing pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"summarization"`. The models that this pipeline can use are models that have been fine-tuned on a summarization task, which is currently, '*bart-large-cnn*', '*t5-small*', '*t5-base*', '*t5-large*', '*t5-3b*', '*t5-11b*'. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=summarization). For a list of available parameters, see the [following documentation](https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.generation.GenerationMixin.generate) Usage: ```python # use bart in pytorch summarizer = pipeline("summarization") summarizer("An apple a day, keeps the doctor away", min_length=5, max_length=20) # use t5 in tf summarizer = pipeline("summarization", model="t5-base", tokenizer="t5-base", framework="tf") summarizer("An apple a day, keeps the doctor away", min_length=5, max_length=20) ```summaryctj|i|S)a Summarize the text(s) given as inputs. Args: documents (*str* or `List[str]`): One or several articles (or one list of articles) to summarize. return_text (`bool`, *optional*, defaults to `True`): Whether or not to include the decoded texts in the outputs return_tensors (`bool`, *optional*, defaults to `False`): Whether or not to include the tensors of predictions (as token indices) in the outputs. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the potential extra spaces in the text output. generate_kwargs: Additional keyword arguments to pass along to the generate method of the model (see the generate method corresponding to your framework [here](./model#generative-models)). Return: A list or a list of list of `dict`: Each result comes as a dictionary with the following keys: - **summary_text** (`str`, present when `return_text=True`) -- The summary of the corresponding input. - **summary_token_ids** (`torch.Tensor` or `tf.Tensor`, present when `return_tensors=True`) -- The token ids of the summary. rrQrr rrrQszSummarizationPipeline.__call__r5r6r7returnc CsR||krtd|d|d||kr'td|d|d|ddd Sd S) r8zYour min_length=z' must be inferior than your max_length=.zYour max_length is set to z , but your input_length is only z. Since this is a summarization task, where outputs shorter than the input are typically wanted, you might consider decreasing max_length manually, e.g. summarizer('...', max_length=r)Nloggerwarningr9rrrr:sz"SummarizationPipeline.check_inputs) rrrrkrdrQrlboolr:rnrrr rros  "rocs`eZdZdZdZdededefddZejddd fd d Z dfd d Z fddZ Z S)TranslationPipelinea Translates from one language to another. This translation pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"translation_xx_to_yy"`. The models that this pipeline can use are models that have been fine-tuned on a translation task. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=translation). For a list of available parameters, see the [following documentation](https://huggingface.co/docs/transformers/en/main_classes/text_generation#transformers.generation.GenerationMixin.generate) Usage: ```python en_fr_translator = pipeline("translation_en_to_fr") en_fr_translator("How old are you?") ``` translationr5r6r7cCs(|d|krtd|d|ddS)Ng?zYour input_length: z" is bigger than 0.9 * max_length: z`. You might consider increasing your max_length manually, e.g. translator('...', max_length=400)Trvr9rrrr:5s z TranslationPipeline.check_inputsN)r"src_langtgt_langcs:t|jddr|jj||j|||dStj|d|iS)N_build_translation_inputs)r,r"r|r}r")getattrr'r~rrrL)rr"r|r}rr rrrT=s  zTranslationPipeline.preprocessc  stjdi|\}}}|dur||d<|dur||d<|durD|durD|d|j}|d}|rDt|dkrD|d|d<|d|d<|||fS) Nr|r}task_rr)rr4rZrsplitr)) rr|r}rr0r1r2ritemsr rrr4Es    z(TranslationPipeline._sanitize_parameterscrq)a Translate the text(s) given as inputs. Args: args (`str` or `List[str]`): Texts to be translated. return_tensors (`bool`, *optional*, defaults to `False`): Whether or not to include the tensors of predictions (as token indices) in the outputs. return_text (`bool`, *optional*, defaults to `True`): Whether or not to include the decoded texts in the outputs. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the potential extra spaces in the text output. src_lang (`str`, *optional*): The language of the input. Might be required for multilingual models. Will not have any effect for single pair translation models tgt_lang (`str`, *optional*): The language of the desired output. Might be required for multilingual models. Will not have any effect for single pair translation models generate_kwargs: Additional keyword arguments to pass along to the generate method of the model (see the generate method corresponding to your framework [here](./model#generative-models)). Return: A list or a list of list of `dict`: Each result comes as a dictionary with the following keys: - **translation_text** (`str`, present when `return_text=True`) -- The translation. - **translation_token_ids** (`torch.Tensor` or `tf.Tensor`, present when `return_tensors=True`) -- The token ids of the translation. rrrr rrrQUszTranslationPipeline.__call__)NN) rrrrkrdrlr:rrmrTr4rQrnrrr rrzsrz)enumr*tokenization_utilsrutilsrrrrbaser r tensorflowrmodels.auto.modeling_tf_autor models.auto.modeling_autor get_loggerrrwEnumr rrorzrrrrs&    ?E