Abstract
Construct a scratchpad to let the agent continue its thought process
Abstract
llmAbstract
observationDecide what to do given some input.
Steps the LLM has taken so far, along with observations from each.
User inputs.
Optional
callbackManager: CallbackManagerCallback manager to use for this call.
Action specifying what tool to use.
Prepare the agent for output, if needed
Return response when agent has been stopped due to max iterations
Optional
callbackManager: CallbackManagerStatic
createCreate a prompt for this class
List of tools the agent will have access to, used to format the prompt.
Optional
_fields: Record<string, any>Additional fields used to format the prompt.
A PromptTemplate assembled from the given tools and fields.
Static
deserializeLoad an agent from a json-like object describing it.
Static
fromLLMAndStatic
getGet the default output parser for this agent.
Optional
_fields: OutputParserArgsStatic
validate
Class responsible for calling a language model and deciding an action.
Remarks
This is driven by an LLMChain. The prompt in the LLMChain must include a variable called "agent_scratchpad" where the agent can put its intermediary work.
Deprecated
Use new agent creation methods.