§ ˜Štj !ãóæ—dZddlmZddlZddlmZddlmZmZddl m Z ddl m Z m Z mZmZGd„d e ¦«ZGd „d e¦«ZGd „d e ¦«ZGd„de ¦«Zdd„Zdd„Zdd„ZdS)añSchema definitions for representing agent actions, observations, and return values. !!! warning The schema definitions are provided for backwards compatibility. !!! warning New agents should be built using the [`langchain` library](https://pypi.org/project/langchain/), which provides a simpler and more flexible way to define agents. See docs on [building agents](https://docs.langchain.com/oss/python/langchain/agents). Agents use language models to choose a sequence of actions to take. A basic agent works in the following manner: 1. Given a prompt an agent uses an LLM to request an action to take (e.g., a tool to run). 2. The agent executes the action (e.g., runs the tool), and receives an observation. 3. The agent returns the observation to the LLM, which can then be used to generate the next action. 4. When the agent reaches a stopping condition, it returns a final return value. The schemas for the agents themselves are defined in `langchain.agents.agent`. é)Ú annotationsN)ÚSequence)ÚAnyÚLiteral)Ú Serializable)Ú AIMessageÚ BaseMessageÚFunctionMessageÚ HumanMessagecó ‡—eZdZUdZded< ded< ded< dZded<dˆfd „ Zedd„¦«Zedd„¦«Z e dd„¦«Z ˆxZ S)Ú AgentActionzàRepresents a request to execute an action by an agent. The action consists of the name of the tool to execute and the input to pass to the tool. The log is used to pass along extra information about the action. ÚstrÚtoolústr | dict[Any, Any]Ú tool_inputÚlogzLiteral['AgentAction']ÚtypeÚkwargsrc óB•—t¦«jd|||dœ|¤ŽdS)zàCreate an `AgentAction`. Args: tool: The name of the tool to execute. tool_input: The input to pass in to the `Tool`. log: Additional information to log about the action. )rrrN©©ÚsuperÚ__init__)ÚselfrrrrÚ __class__s €úS/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_core/agents.pyrzAgentAction.__init__Gs1ø€ð ‰ŒÔÐM˜d¨z¸sÐMÐMÀfÐMÐMÐMÐMÐMóÚreturnÚboolcó—dS)zL`AgentAction` is serializable. Returns: `True` Tr©Úclss rÚis_lc_serializablezAgentAction.is_lc_serializableSs €ðˆtrú list[str]có —gd¢S©ztGet the namespace of the LangChain object. Returns: `["langchain", "schema", "agent"]` )Ú langchainÚschemaÚagentrr!s rÚget_lc_namespacezAgentAction.get_lc_namespace\ó€ð0Ð/Ð/Ð/rúSequence[BaseMessage]có —t|¦«S)z3Return the messages that correspond to this action.)Ú!_convert_agent_action_to_messages©rs rÚmessageszAgentAction.messageses€õ1°Ñ6Ô6Ð6r)rrrrrrrr©rr©rr$©rr,© Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú__annotations__rrÚ classmethodr#r*Úpropertyr0Ú __classcell__©rs@rr r ,síø€€€€€€ððð €I€IIØ,à$Ð$Ð$Ñ$Ø-à €H€HHðð$1€DÐ0Ð0Ð0Ñ0ð Nð Nð Nð Nð Nð Nððððñ„[ððð0ð0ð0ñ„[ð0ðð7ð7ð7ñ„Xð7ð7ð7ð7ð7rr có.—eZdZUdZded< dZded<dS)ÚAgentActionMessageLoga%Representation of an action to be executed by an agent. This is similar to `AgentAction`, but includes a message log consisting of chat messages. This is useful when working with `ChatModels`, and is used to reconstruct conversation history from the agent's perspective. r,Ú message_logz Literal['AgentActionMessageLog']rN)r5r6r7r8r9rrrrr?r?ksC€€€€€€ððð'Ð&Ð&Ñ&ðð.E€DÐDÐDÐDÑDÐDÐDrr?cóD—eZdZUdZded< ded< ed d„¦«Zd S) Ú AgentStepz#Result of running an `AgentAction`.r ÚactionrÚ observationrr,có6—t|j|j¦«S)ú-Messages that correspond to this observation.)Ú&_convert_agent_observation_to_messagesrCrDr/s rr0zAgentStep.messagesŽs€õ6°d´kÀ4ÔCSÑTÔTÐTrNr3)r5r6r7r8r9r;r0rrrrBrB…s^€€€€€€Ø-Ð-àÐÐÑØ.àÐÐÑØ*à ðUðUðUñ„XðUðUðUrrBc󔇗eZdZUdZded< ded< dZded<dˆfd „ Zedd „¦«Zedd„¦«Z e dd„¦«Z ˆxZ S)Ú AgentFinishz}Final return value of an `ActionAgent`. Agents return an `AgentFinish` when they have reached a stopping condition. údict[Any, Any]Ú return_valuesrrzLiteral['AgentFinish']rrrc ó@•—t¦«jd||dœ|¤ŽdS)zGOverride init to support instantiation by position for backward compat.)rKrNrr)rrKrrrs €rrzAgentFinish.__init__©s-ø€à‰ŒÔÐH }¸#ÐHÐHÀÐHÐHÐHÐHÐHrrrcó—dS)z,Return `True` as this class is serializable.Trr!s rr#zAgentFinish.is_lc_serializable­s €ðˆtrr$có —gd¢Sr&rr!s rr*zAgentFinish.get_lc_namespace²r+rr,có.—t|j¬¦«gS)rF©Úcontent)rrr/s rr0zAgentFinish.messages»s€õ $¤(Ð+Ñ+Ô+Ð,Ð,r)rKrJrrrrr1r2r3r4r=s@rrIrI”sáø€€€€€€ððð "Ð!Ð!Ñ!Ø&à €H€HHðð$1€DÐ0Ð0Ð0Ñ0ðIðIðIðIðIðIððððñ„[ððð0ð0ð0ñ„[ð0ðð-ð-ð-ñ„Xð-ð-ð-ð-ð-rrIÚ agent_actionrr,cóf—t|t¦«r|jSt|j¬¦«gS)a Convert an agent action to a message. This code is used to reconstruct the original AI message from the agent action. Args: agent_action: Agent action to convert. Returns: `AIMessage` that corresponds to the original tool invocation. rP)Ú isinstancer?r@rr)rRs rr.r.Ás7€õ,Õ 5Ñ6Ô6ð(ØÔ'Ð'Ý ˜lÔ.Ð /Ñ /Ô /Ð 0Ð0rrDrcó —t|t¦«rt||¦«gS|}t|t¦«s7 t j|d¬¦«}n#t $rt|¦«}YnwxYwt|¬¦«gS)aGConvert an agent action to a message. This code is used to reconstruct the original AI message from the agent action. Args: agent_action: Agent action to convert. observation: Observation to convert to a message. Returns: `AIMessage` that corresponds to the original tool invocation. F©Ú ensure_asciirP)rTr?Ú_create_function_messagerÚjsonÚdumpsÚ Exceptionr ©rRrDrQs rrGrGÓs€õ,Õ 5Ñ6Ô6ðEÝ(¨°{ÑCÔCÐDÐDØ€GÝ k¥3Ñ 'Ô 'ð'ð 'Ý”j ¸5ÐAÑAÔAˆGˆGøÝð 'ð 'ð 'ݘ+Ñ&Ô&ˆGˆGˆGð 'øøøå  Ð )Ñ )Ô )Ð *Ð*s¿AÁA2Á1A2r cóÊ—t|t¦«s7 tj|d¬¦«}n!#t$rt|¦«}YnwxYw|}t |j|¬¦«S)a!Convert agent action and observation into a function message. Args: agent_action: the tool invocation request from the agent. observation: the result of the tool invocation. Returns: `FunctionMessage` that corresponds to the original tool invocation. FrV)ÚnamerQ)rTrrYrZr[r rr\s rrXrXìs„€õ k¥3Ñ 'Ô 'ðð 'Ý”j ¸5ÐAÑAÔAˆGˆGøÝð 'ð 'ð 'ݘ+Ñ&Ô&ˆGˆGˆGð 'øøøðˆÝ Ø Ô Øð ñ ô ðs—.®A Á A )rRr rr,)rRr rDrrr,)rRr rDrrr )r8Ú __future__rrYÚcollections.abcrÚtypingrrÚ langchain_core.load.serializablerÚlangchain_core.messagesrr r r r r?rBrIr.rGrXrrrúrds¤ðððð8#Ð"Ð"Ð"Ð"Ð"à € € € Ø$Ð$Ð$Ð$Ð$Ð$ØÐÐÐÐÐÐÐà9Ð9Ð9Ð9Ð9Ð9ððððððððððððð<7ð<7ð<7ð<7ð<7,ñ<7ô<7ð<7ð~EðEðEðEðE˜KñEôEðEð4 Uð Uð Uð Uð U ñ Uô Uð Uð*-ð*-ð*-ð*-ð*-,ñ*-ô*-ð*-ðZ1ð1ð1ð1ð$+ð+ð+ð+ð2ðððððr