d5ddlZddlmZmZmZmZmZddlmZm Z m Z m Z ddl m Z mZe rddlZe rddlZe jeZGddZee d Gd d eZdS) N)AnyDictListOptionalUnion)add_end_docstringsis_tf_availableis_torch_availablelogging)PIPELINE_INIT_ARGSPipelinecfeZdZdZ ddedejfdZdZddede fd Z d Z d efd Z d Z dZdS) Conversationa\ Utility class containing a conversation and its history. This class is meant to be used as an input to the [`ConversationalPipeline`]. The conversation contains several utility functions to manage the addition of new user inputs and generated model responses. A conversation needs to contain an unprocessed user input before being passed to the [`ConversationalPipeline`]. This user input is either created when the class is instantiated, or by calling `conversational_pipeline.append_response("input")` after a conversation turn. Arguments: text (`str`, *optional*): The initial user input to start the conversation. If not provided, a user input needs to be provided manually using the [`~Conversation.add_user_input`] method before the conversation can begin. conversation_id (`uuid.UUID`, *optional*): Unique identifier for the conversation. If not provided, a random UUID4 id will be assigned to the conversation. past_user_inputs (`List[str]`, *optional*): Eventual past history of the conversation of the user. You don't need to pass it manually if you use the pipeline interactively but if you want to recreate history you need to set both `past_user_inputs` and `generated_responses` with equal length lists of strings generated_responses (`List[str]`, *optional*): Eventual past history of the conversation of the model. You don't need to pass it manually if you use the pipeline interactively but if you want to recreate history you need to set both `past_user_inputs` and `generated_responses` with equal length lists of strings Usage: ```python conversation = Conversation("Going to the movies tonight - any suggestions?") # Steps usually performed by the model when generating a response: # 1. Mark the user input as processed (moved to the history) conversation.mark_processed() # 2. Append a mode response conversation.append_response("The Big lebowski.") conversation.add_user_input("Is it good?") ```Ntextconversation_idcx|stj}|g}|g}||_||_||_||_dSN)uuiduuid4past_user_inputsgenerated_responsesnew_user_input)selfrrrrs Elib/python3.11/site-packages/transformers/pipelines/conversational.py__init__zConversation.__init__8sT +"jllO  #!   &"$ . +;.A -1ct|tsdS|j|jkrdS|j|jko|j|jko|j|jkS)NFT) isinstancerrrrr)rothers r__eq__zConversation.__eq__Gsh%.. 5 9 " "4  5#7 7 F%)?? F(E,EE rF overwritec|jrY|r/td|jd|d||_dStd|jd|ddS||_dS)a Add a user input to the conversation for the next round. This populates the internal `new_user_input` field. Args: text (`str`): The user input for the next conversation round. overwrite (`bool`, *optional*, defaults to `False`): Whether or not existing and unprocessed user input should be overwritten when this function is called. z8User input added while unprocessed input was existing: "z" was overwritten with: "z".z" new input ignored: "z>". Set `overwrite` to True to overwrite unprocessed user inputN)rloggerwarning)rrr#s radd_user_inputzConversation.add_user_inputRs   ' 'tOb''"''''+###ftObff!%fff #'D   rc`|jr|j|jd|_dS)z Mark the conversation as processed (moves the content of `new_user_input` to `past_user_inputs`) and empties the `new_user_input` field. N)rrappend)rs rmark_processedzConversation.mark_processedjs7   >  ! ( ()< = = ="rresponsec:|j|dS)z Append a response to the list of generated responses. Args: response (`str`): The model generated response. N)rr))rr+s rappend_responsezConversation.append_responsess!  ''11111rc#Kt|j|jD]\}}d|fVd|fV|jr d|jfVdSdS)z Iterates over all blobs of the conversation. Returns: Iterator of (is_user, text_chunk) in chronological order of the conversation. `is_user` is a `bool`, `text_chunks` is a `str`. TFN)ziprrr)r user_inputgenerated_responses r iter_textszConversation.iter_texts|s/2$2GIa.b.b , , *J* " " " "++ + + + +   ,++ + + + + + , ,rcrd|jd}|D]\}}|rdnd}||d|dz }|S)a Generates a string representation of the conversation. Return: `str`: Example: Conversation id: 7d15686b-dc94-49f2-9c4b-c9eac6a1f114 user >> Going to the movies tonight - any suggestions? bot >> The Big Lebowski zConversation id: z userbotz >> )rr2)routputis_userrnames r__repr__zConversation.__repr__sc4TY333!__.. - -MGT$/66%D ,,4,,, ,FF r)NNNN)F)__name__ __module__ __qualname____doc__strrUUIDrr"boolr'r*r-r2r9rrrrs# # Los 2 2 215 2 2 2 2    ''3'4''''0###22222 , , ,rra  min_length_for_response (`int`, *optional*, defaults to 32): The minimum length (in number of tokens) for a response. minimum_tokens (`int`, *optional*, defaults to 10): The minimum length of tokens to leave for a response. ceZdZdZfdZ ddZddeeeefffd Z dd ed e e e ffd Z dd ZddZd ed e fdZxZS)ConversationalPipelinea Multi-turn conversational pipeline. Example: ```python >>> from transformers import pipeline, Conversation >>> chatbot = pipeline(model="microsoft/DialoGPT-medium") >>> conversation = Conversation("Going to the movies tonight - any suggestions?") >>> conversation = chatbot(conversation) >>> conversation.generated_responses[-1] 'The Big Lebowski' >>> conversation.add_user_input("Is it an action movie?") >>> conversation = chatbot(conversation) >>> conversation.generated_responses[-1] "It's a comedy." ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This conversational pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"conversational"`. The models that this pipeline can use are models that have been fine-tuned on a multi-turn conversational task, currently: *'microsoft/DialoGPT-small'*, *'microsoft/DialoGPT-medium'*, *'microsoft/DialoGPT-large'*. See the up-to-date list of available models on [huggingface.co/models](https://huggingface.co/models?filter=conversational). ctj|i||jj|jj|j_dSdSr)superr tokenizer pad_token_id eos_token pad_token)rargskwargs __class__s rrzConversationalPipeline.__init__sG$)&))) > & .'+~'?DN $ $ $ / .rNc i}i}i}|||d<|||d<d|vr |d|d<|||d<|r|||||fS)Nmin_length_for_responseminimum_tokens max_lengthclean_up_tokenization_spaces)update)rrNrOrQgenerate_kwargspreprocess_paramsforward_paramspostprocess_paramss r_sanitize_parametersz+ConversationalPipeline._sanitize_parameterss " .;R 7 8  %/=N+ , ? * *+:<+HN< ( ' 3A] = >  3  ! !/ 2 2 2 .2DDDrr conversationsc tj|fd|i|}t|trt |dkr|dS|S)a, Generate responses for the conversation(s) given as inputs. Args: conversations (a [`Conversation`] or a list of [`Conversation`]): Conversations to generate responses for. 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)). Returns: [`Conversation`] or a list of [`Conversation`]: Conversation(s) with updated generated responses for those containing a new user input. num_workersr r)rE__call__r listlen)rrXrZrKoutputsrLs rr[zConversationalPipeline.__call__sY*#%''"=TTkTVTT gt $ $ W):):1: r conversationreturnct|tstd|j%tdt |jdt |jdr|j|}n| |}|j dkrtj |g}n |j dkrtj|g}||dS)Nz6ConversationalPipeline, expects Conversation as inputszConversation with UUID zl does not contain new user input to process. Add user inputs with the conversation's `add_user_input` method_build_conversation_input_idspttf) input_idsr`)r r ValueErrorrtyperhasattrrFrc_legacy_parse_and_tokenize frameworktorch LongTensorreconstant)rr`rNrfs r preprocessz!ConversationalPipeline.preprocesss, 55 WUVV V  & .R$|/@*A*ARRR  4>#B C C FDD\RRII77 EEI >T ! !()55II ^t # # YK00I& EEEr c |d|jjj}|djd}||z |kr]t d|d|d|d||z }|ddd| df|d<d|vr|ddd| df|d<|d }||d<|jjd i||}|jjj rd} n|} |dd| df|d S) NrPrfr zConversation input is to long (z), trimming it to (z - )attention_maskr`) output_idsr`rA) getmodelconfigrPshaper%r&popgenerateis_encoder_decoder) r model_inputsrOrSrPntrimr`rtstart_positions r_forwardzConversationalPipeline._forward sL$((tz7H7STT  % +A .  & * * NNsQssS]ssbpsss t t t.D(4[(A!!!dUVV)(LL %<//1=>N1OPQPQPQTXSXSYSYPY1Z -.#''77 (2 %(TZ(KK<K?KK :  / NNN(NOO);>DN; ; ;!4>#B"B"D"DEIr)NNN)r)r_)rp)T)r:r;r<r=rrWrrrr[rr>rrorrrj __classcell__)rLs@rrCrCs(>@@@@@ _cEEEE,eL$|:L,L&M4FF|FTXY\^aYaTbFFFF(\\\\&     |         rrC)rtypingrrrrrutilsr r r r baserr tensorflowrerl get_loggerr:r%rrCrArrrsS 33333333333333TTTTTTTTTTTT........?LLL  H % %EEEEEEEEPSSSSSXSSSSSr