Class RunnableAgent

ToolType

defaultRunName

runnable

Optionalstop

streamRunnable

allowedTools

• get allowedTools(): undefined | string[]

• Returns undefined | string[]

inputKeys

• get inputKeys(): string[]

• Returns string[]

returnValues

• get returnValues(): string[]

• Returns string[]

plan

• plan(steps, inputs, callbackManager?, config?): Promise<AgentFinish | AgentAction[]>

• Decide what to do, given some input.

  Parameters

  • steps: AgentStep[]

    Steps the LLM has taken so far, along with observations from each.
  • inputs: ChainValues

    User inputs.
  • OptionalcallbackManager: CallbackManager

    Callback manager.
  • Optionalconfig: RunnableConfig<Record<string, any>>

  Returns Promise<AgentFinish | AgentAction[]>

  Actions specifying what tools to use.

prepareForOutput

• prepareForOutput(_returnValues, _steps): Promise<Record<string, any>>

• Prepare the agent for output, if needed

  Parameters

  • _returnValues: Record<string, any>
  • _steps: AgentStep[]

  Returns Promise<Record<string, any>>

returnStoppedResponse

• returnStoppedResponse(earlyStoppingMethod, _steps, _inputs, _callbackManager?): Promise<AgentFinish>

• Return response when agent has been stopped due to max iterations

  Parameters

  • earlyStoppingMethod: StoppingMethod
  • _steps: AgentStep[]
  • _inputs: ChainValues
  • Optional_callbackManager: CallbackManager

  Returns Promise<AgentFinish>

toJSON

• toJSON(): Serialized

• Returns Serialized

toJSONNotImplemented

• toJSONNotImplemented(): SerializedNotImplemented

• Returns SerializedNotImplemented