Class ChatConversationalAgent

constructor

• new ChatConversationalAgent(
      input: ChatConversationalAgentInput,
  ): ChatConversationalAgent

  Parameters

  • input: ChatConversationalAgentInput

  Returns ChatConversationalAgent

lc_namespace

ToolType

_agentType

• _agentType(): "chat-conversational-react-description"

  Return the string type key uniquely identifying this class of agent.

  Returns "chat-conversational-react-description"

_stop

• _stop(): string[]

  Returns string[]

constructScratchPad

• constructScratchPad(steps: AgentStep[]): Promise<BaseMessage[]>

  Constructs the agent scratchpad based on the agent steps. It returns an array of base messages representing the thoughts of the agent.

  Parameters

  • steps: AgentStep[]

    The agent steps to construct the scratchpad from.

  Returns Promise<BaseMessage[]>

  An array of base messages representing the thoughts of the agent.

llmPrefix

• llmPrefix(): string

  Prefix to append the LLM call with.

  Returns string

observationPrefix

• observationPrefix(): string

  Prefix to append the observation with.

  Returns string

StaticcreatePrompt

• createPrompt(
      tools: ToolInterface[],
      args?: ChatConversationalCreatePromptArgs,
  ): any

  Create prompt in the style of the ChatConversationAgent.

  Parameters

  • tools: ToolInterface[]

    List of tools the agent will have access to, used to format the prompt.

  • Optionalargs: ChatConversationalCreatePromptArgs

    Arguments to create the prompt with.

    Interface defining the structure of arguments used to create a prompt for the ChatConversationalAgent class.

    • OptionalhumanMessage?: string

      String to put before the list of tools.

    • OptionalinputVariables?: string[]

      List of input variables the final prompt will expect.

    • OptionaloutputParser?: AgentActionOutputParser

      Output parser to use for formatting.

    • OptionalsystemMessage?: string

      String to put after the list of tools.

  Returns any

StaticfromLLMAndTools

• fromLLMAndTools(
      llm: BaseLanguageModelInterface,
      tools: ToolInterface[],
      args?: ChatConversationalCreatePromptArgs & AgentArgs,
  ): ChatConversationalAgent

  Creates an instance of the ChatConversationalAgent class from a BaseLanguageModel and a set of tools. It takes optional arguments to customize the agent.

  Parameters

  • llm: BaseLanguageModelInterface

    The BaseLanguageModel to create the agent from.

  • tools: ToolInterface[]

    The set of tools to create the agent from.

  • Optionalargs: ChatConversationalCreatePromptArgs & AgentArgs

    Optional arguments to customize the agent.

  Returns ChatConversationalAgent

  An instance of the ChatConversationalAgent class.

StaticgetDefaultOutputParser

• getDefaultOutputParser(
      fields?: OutputParserArgs & { toolNames: string[] },
  ): AgentActionOutputParser

  Returns the default output parser for the ChatConversationalAgent class. It takes optional fields as arguments to customize the output parser.

  Parameters

  • Optionalfields: OutputParserArgs & { toolNames: string[] }

    Optional fields to customize the output parser.

  Returns AgentActionOutputParser

  The default output parser for the ChatConversationalAgent class.

Staticlc_name

• lc_name(): string

  Returns string

StaticvalidateTools

• validateTools(tools: ToolInterface[]): void

  Validate that appropriate tools are passed in

  Parameters

  • tools: ToolInterface[]

  Returns void