Constructs the agent's scratchpad, which is a string representation of the agent's previous steps.
Array of AgentStep instances representing the agent's previous steps.
Promise resolving to a string representing the agent's scratchpad.
Decide 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 prompt in the style of the zero shot agent.
List of tools the agent will have access to, used to format the prompt.
Optional
args: ChatCreatePromptArgsArguments to create the prompt with.
Static
deserializeLoad an agent from a json-like object describing it.
Static
fromLLMAndCreates a ChatAgent instance using a language model, tools, and optional arguments.
BaseLanguageModelInterface instance to use in the agent.
Array of Tool instances to include in the agent.
Optional
args: ChatCreatePromptArgs & AgentArgsOptional arguments to customize the agent and prompt.
ChatAgent instance
Static
getReturns a default output parser for the ChatAgent.
Optional
_fields: OutputParserArgsOptional OutputParserArgs to customize the output parser.
ChatAgentOutputParser instance
Static
validate
Agent for the MRKL chain.
Deprecated
Use the method instead.