9i8ddlZddlmZmZmZmZddlmZmZm Z m Z ddl m Z m Z erddlZe rddlZe j"eZGddZee d Gd d e Zy) N)AnyDictListUnion)add_end_docstringsis_tf_availableis_torch_availablelogging)PIPELINE_INIT_ARGSPipelineceZdZdZ ddeeeeeeffdejfdZ dZ deeeffdZ dd ed e fd Zd efd ZdZdZdZdZdZdZdZedZedZedZedZy) 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. Arguments: messages (Union[str, List[Dict[str, str]]], *optional*): The initial messages to start the conversation, either a string, or a list of dicts containing "role" and "content" keys. If a string is passed, it is interpreted as a single message with the "user" role. conversation_id (`uuid.UUID`, *optional*): Unique identifier for the conversation. If not provided, a random UUID4 id will be assigned to the conversation. Usage: ```python conversation = Conversation("Going to the movies tonight - any suggestions?") conversation.add_message({"role": "assistant", "content": "The Big lebowski."}) conversation.add_message({"role": "user", "content": "Is it good?"}) ```Nmessagesconversation_idc 6|stj}||jdd}|d|dg}ng}nt|trd|dg}d|_|jdd}|jdd}| | t d|g}|g}ttt|t|gD]M}|t|kr|jd||d|t|ks7|jd||dO||z}||_||_ y) Ntextuserrolecontentrgenerated_responsespast_user_inputsz>generated_responses cannot be passed without past_user_inputs! assistant) uuiduuid4pop isinstancestr_num_processed_user_inputs ValueErrorrangemaxlenappendr) selfrrdeprecated_kwargsrrrlegacy_messagesis o/var/www/html/backtest/airagagent/rag_env/lib/python3.12/site-packages/transformers/pipelines/conversational.py__init__zConversation.__init__(sP"jjlO  $((6D%+=> # &!'H=>H+,'/334I4P,001CTJ  */?/G]^ ^  ' O"*&(#3$4 5s;N7OPQR es+,,#**FGWXYGZ+[\s.//#**KL_`aLb+cd  e '1H#   ct|tsy|j|jk(xs|j|jk(S)NF)rrrr)r'others r+__eq__zConversation.__eq__Ms4%.yyEJJ&I$--5>>*IIr-messagect|jddhk(s td|ddvr td|jj |y)Nrrz6Message should contain only 'role' and 'content' keys!)rrsystemzBOnly 'user', 'assistant' and 'system' roles are supported for now!)setkeysr"rr&r'r1s r+ add_messagezConversation.add_messageRsQ7<<>"vy&99UV V 6?"A Aab b W%r-r overwritect|dkDr[|dddk(rP|r+tjd|ddd|d||dd<y tjd|ddd |d y |jj d|d y ) a3 Add a user input to the conversation for the next round. This is a legacy method that assumes that inputs must alternate user/assistant/user/assistant, and so will not add multiple user messages in succession. We recommend just using `add_message` with role "user" instead. rrrz8User input added while unprocessed input was existing: "rz" was overwritten with: "z".z" new input ignored: "z>". Set `overwrite` to True to overwrite unprocessed user inputrN)r%loggerwarningrr&)r'rr8s r+add_user_inputzConversation.add_user_inputYs t9q=T"Xf-7NtTVxXaObNcd"V2''+R#NtTVxXaObNcd!!%&df MM &T!B Cr-responsec@|jjd|dy)zr This is a legacy method. We recommend just using `add_message` with an appropriate role instead. rrN)rr&)r'r>s r+append_responsezConversation.append_responsens khGHr-c8t|j|_y)a) This is a legacy method, as the Conversation no longer distinguishes between processed and unprocessed user input. We set a counter here to keep behaviour mostly backward-compatible, but in general you should just read the messages directly when writing new code. N)r%_user_messagesr!r's r+mark_processedzConversation.mark_processedts +.d.A.A*B'r-c#6K|jD]}|ywNrr6s r+__iter__zConversation.__iter__|s}} GM sc |j|SrFrG)r'items r+ __getitem__zConversation.__getitem__s}}T""r-c"||j|<yrFrG)r'keyvalues r+ __setitem__zConversation.__setitem__s" cr-c,t|jSrF)r%rrCs r+__len__zConversation.__len__s4==!!r-cjd|jd}|jD]}||dd|ddz }|S)a Generates a string representation of the conversation. Returns: `str`: Example: Conversation id: 7d15686b-dc94-49f2-9c4b-c9eac6a1f114 user: Going to the movies tonight - any suggestions? bot: The Big Lebowski zConversation id:  rz: r)rr)r'outputr1s r+__repr__zConversation.__repr__sR%TYYKr2}} CG )GI,>+?rB BF C r-c#LK|jD]}|ddk(|dfywNrrrrGr6s r+ iter_textszConversation.iter_textss6}} @G&/V+WY-?? ? @s"$cX|jDcgc]}|ddk(s |dc}Scc}wrWrGr6s r+rBzConversation._user_messagess-37--]w76?V\C\ "]]] ''c|jsgS|jdddk7s"|jt|jk(r |jS|jddS)Nr:rr)rBrr!r%rCs r+rzConversation.past_user_inputssc ""I == V $ .$2Q2QUXY]YlYlUm2m&& &""3B''r-cX|jDcgc]}|ddk(s |dc}Scc}w)NrrrrGr6s r+rz Conversation.generated_responsess-37--bw76?VaCa "bbbrZc |jdS)Nr:)rBrCs r+new_user_inputzConversation.new_user_inputs""2&&r-)NN)F)__name__ __module__ __qualname____doc__rr rrrUUIDr,r0r7boolr=r@rDrHrKrOrQrUrXpropertyrBrrr^r-r+rrs ,_c#!c4S#X#778#!RVR[R[#!JJ &4S>&D3D4D*II C##" @ ^^  ( (cc ''r-ra  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 d dZd deeee ee fffd Z d de dee e ffdZ dd Zdd ZxZS)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). ct||i||jj&|jj|j_yyrF)superr, tokenizer pad_token_id eos_token pad_token)r'argskwargs __class__s r+r,zConversationalPipeline.__init__s@ $)&) >> & & .'+~~'?'?DNN $ /r-c i}i}i}|||d<|||d<d|vr|d|d<|||d<|r|j||||fS)Nmin_length_for_responseminimum_tokens max_lengthclean_up_tokenization_spaces)update)r'rsrtrvgenerate_kwargspreprocess_paramsforward_paramspostprocess_paramss r+_sanitize_parametersz+ConversationalPipeline._sanitize_parameterss " .;R 7 8  %/=N+ , ? *+:<+HN< ( ' 3A] = >   ! !/ 2 .2DDDr- conversationsc Pt|trt|dtr t|}n;t|tr+t|dtr|Dcgc] }t|}}t ||fd|i|}t|trt |dk(r|dS|Scc}w)a/ Generate responses for the conversation(s) given as inputs. Args: conversations (a [`Conversation`] or a list of [`Conversation`]): Conversation to generate responses for. Inputs can also be passed as a list of dictionaries with `role` and `content` keys - in this case, they will be converted to `Conversation` objects automatically. Multiple conversations in either format may be passed as a list. 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. r num_workersr )rlistdictrrj__call__r%)r'r}rrpconvoutputsrqs r+rzConversationalPipeline.__call__s. mT *z-:JD/Q(7M  t ,M!>T !(()5I ^^t # YK0I& EEr-c |djd}|jd}d|vr d|vrd|d<|jjdi||}|jjj rd}n|}|dd|df|dS) Nrr rrumax_new_tokens) output_idsrrf)shapermodelgenerateconfigis_encoder_decoder)r' model_inputsrtrxnrrstart_positions r+_forwardzConversationalPipeline._forward/s  % + +A .#''7  .3C?3Z03O, -(TZZ((K<K?K ::   / /NN(NO);@ _cE,eDJ drsw ))TT.   H %m'm'`yXyyr-