dhSSKJr SSKJrJrJrJrJr SSKJ r J r SSK J r SSK Jr SSKJr \"SS\55r"S S \ 5rg ) )abstractmethod)AnyOptionalProtocolSequenceruntime_checkable)AsyncCallbackManagerForToolRunCallbackManagerForToolRun)BaseTool)Field) TrainResultcd\rSrSrSr\S\\S\S\ 4Sj5r \S\\S\S\ 4Sj5r Sr g ) TrainableLLMz'Protocol for trainable language models.inputskwargsreturnc gNselfrrs _/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/tools/memorize/tool.pytrain_unsupervisedTrainableLLM.train_unsuperviseds c # g7frrrs ratrain_unsupervised TrainableLLM.atrain_unsuperviseds srN) __name__ __module__ __qualname____firstlineno____doc__rrstrrr rr__static_attributes__rrrrrsk1       rrc\rSrSr%SrSr\\S'Sr\\S'\ "5r \ \S'SS \S \ \ S \4S jjrSS \S \ \S \4S jjrSrg)Memorize!z"Tool that trains a language model.memorizenamezUseful whenever you observed novel information from previous conversation history, i.e., another tool's action outputs or human comments. The action input should include observed information in detail, then the tool will fine-tune yourself to remember it. descriptionllmNinformation_to_learn run_managerrcJURRU45nSUS3$NzTrain complete. Loss: loss)r-rrr.r/ train_results r_run Memorize._run.s/ xx224H3JK ' V(<'=>>rcf# URRU45IShvN nSUS3$N 7fr1)r-rr3s r_arunMemorize._arun6s; "XX99;O:QRR ' V(<'=>>Ss 1/ 1rr)r r!r"r#r$r+r%__annotations__r,r r-rrr r5r r8r&rrrr(r(!s,D# @C <@?!?78? ?AE?!?<=? ??rr(N)abcrtypingrrrrrlangchain_core.callbacksr r langchain_core.toolsr pydanticr $langchain_community.llms.gradient_air rr(rrrrAsEGG*<8$?x?r