o +i @sdZddlmZddlZddlmZddlmZmZddl m Z ddl m Z m Z mZmZGdd d e ZGd d d eZGd d d e ZGddde ZdddZdddZdddZdS)aSchema 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. ) annotationsN)Sequence)AnyLiteral) Serializable) AIMessage BaseMessageFunctionMessage HumanMessagecsxeZdZUdZded< ded< ded< dZded<dfd d ZedddZedddZ e dddZ Z S) AgentActionzRepresents 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. strtool str | dict tool_inputlogzLiteral['AgentAction']typekwargsrc stjd|||d|dS)zCreate 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. )r rrNsuper__init__)selfr rrr __class__rR/var/www/html/psymed-ai/venv/lib/python3.10/site-packages/langchain_core/agents.pyrBszAgentAction.__init__returnboolcCdS)zL`AgentAction` is serializable. Returns: `True` Trclsrrris_lc_serializableLszAgentAction.is_lc_serializable list[str]cCgdSztGet the namespace of the LangChain object. Returns: `["langchain", "schema", "agent"]` ) langchainschemaagentrrrrrget_lc_namespaceUzAgentAction.get_lc_namespaceSequence[BaseMessage]cCst|S)z3Return the messages that correspond to this action.)!_convert_agent_action_to_messagesrrrrmessages^szAgentAction.messages)r r rrrr rrrrrr!rr) __name__ __module__ __qualname____doc____annotations__rr classmethodr r'propertyr, __classcell__rrrrr *s    r c@s(eZdZUdZded< dZded<dS)AgentActionMessageLoga%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) message_logz Literal['AgentActionMessageLog']rN)r1r2r3r4r5rrrrrr9ds   r9c@s4eZdZUdZded< ded< ed dd Zd S) AgentStepz#Result of running an `AgentAction`.r actionr observationrr)cCst|j|jS)-Messages that correspond to this observation.)&_convert_agent_observation_to_messagesr<r=r+rrrr,zAgentStep.messagesNr/)r1r2r3r4r5r7r,rrrrr;~s r;csneZdZUdZded< ded< dZded<dfd d ZedddZedddZ e dddZ Z S) AgentFinishz}Final return value of an `ActionAgent`. Agents return an `AgentFinish` when they have reached a stopping condition. dict return_valuesr rzLiteral['AgentFinish']rrrc stjd||d|dS)zGOverride init to support instantiation by position for backward compat.)rCrNrr)rrCrrrrrrszAgentFinish.__init__rrcCr)z,Return `True` as this class is serializable.Trrrrrr szAgentFinish.is_lc_serializabler!cCr"r#rrrrrr'r(zAgentFinish.get_lc_namespacer)cCst|jdgS)r>content)rrr+rrrr,r@zAgentFinish.messages)rCrBrr rrr-r.r/r0rrrrrAs    rA agent_actionrr)cCst|tr|jSt|jdgS)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. rD) isinstancer9r:rr)rFrrrr*s r*r=rcCs^t|tr t||gS|}t|ts)z tj|dd}Wn ty(t|}Ynwt|dgS)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 ensure_asciirD)rGr9_create_function_messager jsondumps Exceptionr rFr=rErrrr?s      r?r cCsJt|tsz tj|dd}Wntyt|}Ynw|}t|j|dS)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. FrH)namerE)rGr rKrLrMr r rNrrrrJs   rJ)rFr rr))rFr r=rrr))rFr r=rrr )r4 __future__rrKcollections.abcrtypingrr langchain_core.load.serializablerlangchain_core.messagesrrr r r r9r;rAr*r?rJrrrrs   : ,