tjdZddlmZddlmZmZddlmZddlm Z ddl m Z ddl m Z ddlmZe d d d d Gdde eZdS)z**Memory** maintains Chain state, incorporating context from past runs. This module contains memory abstractions from LangChain v0.0.x. These abstractions are now deprecated and will be removed in LangChain v1.0.0. ) annotations)ABCabstractmethod)Any) deprecated) Serializable)run_in_executor) ConfigDictz0.3.3z2.0.0zlangchain.agents.create_agentzFor agents that need to remember prior interactions, use `create_agent` with checkpointing or the `Store` API. See https://docs.langchain.com/oss/python/langchain/short-term-memory and https://docs.langchain.com/oss/python/langchain/long-term-memory)sinceremoval alternativeaddendumceZdZdZedZeeddZedd Z dd Z eddZ ddZ eddZ ddZdS) BaseMemorya9Abstract base class for memory in Chains. Memory refers to state in Chains. Memory can be used to store information about past executions of a Chain and inject that information into the inputs of future executions of the Chain. For example, for conversational Chains Memory can be used to store conversations and automatically add them to future model prompts so that the model has the necessary context to respond coherently to the latest input. Example: ```python class SimpleMemory(BaseMemory): memories: dict[str, Any] = dict() @property def memory_variables(self) -> list[str]: return list(self.memories.keys()) def load_memory_variables(self, inputs: dict[str, Any]) -> dict[str, str]: return self.memories def save_context( self, inputs: dict[str, Any], outputs: dict[str, str] ) -> None: pass def clear(self) -> None: pass ``` T)arbitrary_types_allowedreturn list[str]cdS)z;The string keys this memory class will add to chain inputs.Nselfs [/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_classic/base_memory.pymemory_variableszBaseMemory.memory_variablesBinputsdict[str, Any]cdS)zReturn key-value pairs given the text input to the chain. Args: inputs: The inputs to the chain. Returns: A dictionary of key-value pairs. Nrrrs rload_memory_variablesz BaseMemory.load_memory_variablesGrrc>Ktd|j|d{VS)zAsync return key-value pairs given the text input to the chain. Args: inputs: The inputs to the chain. Returns: A dictionary of key-value pairs. N)r r rs raload_memory_variablesz!BaseMemory.aload_memory_variablesRs/%T4+EvNNNNNNNNNroutputsdict[str, str]NonecdS)zSave the context of this chain run to memory. Args: inputs: The inputs to the chain. outputs: The outputs of the chain. Nrrrr#s r save_contextzBaseMemory.save_context]rrcDKtd|j||d{VdS)zAsync save the context of this chain run to memory. Args: inputs: The inputs to the chain. outputs: The outputs of the chain. N)r r(r's r asave_contextzBaseMemory.asave_contextfs7dD$5vwGGGGGGGGGGGrcdS)zClear memory contents.Nrrs rclearzBaseMemory.clearqrrc@Ktd|jd{VdS)zAsync clear memory contents.N)r r,rs raclearzBaseMemory.aclearus0dDJ///////////rN)rr)rrrr)rrr#r$rr%)rr%)__name__ __module__ __qualname____doc__r model_configpropertyrrr r"r(r*r,r.rrrrrs >: $LJJJ^XJ   ^  O O O O   ^  H H H H%%%^%000000rrN)r2 __future__rabcrrtypingrlangchain_core._apir langchain_core.load.serializablerlangchain_core.runnablesr pydanticr rrrrr<s#"""""########******999999444444   / K   Y0Y0Y0Y0Y0sY0Y0  Y0Y0Y0r