how to call another tool from within a tool?

[stewones]

So I have a use case where a tool must find information somewhere, and if the information is not found, it must call another tool to escalate support to a human. is there a way to do this?

I'm using initializeAgentExecutorWithOptions with agentType openai-functions

[dosubot]

🤖

Hello,

Based on the current implementation of initializeAgentExecutorWithOptions in the LangChainJS framework, there isn't a built-in method to call another tool from within a tool in the event that the initial tool fails to find the required information. The initializeAgentExecutorWithOptions function is used to initialize an agent executor with a specific agent type and set of tools, but it does not provide functionality for switching to a different tool if the initial tool fails.

However, you can handle this in your application logic. For instance, you could catch any errors thrown by the initial tool, and in the catch block, re-initialize the agent executor with a different tool. Here's a rough example of how you might implement this:

try {
  // Initialize your agent executor with the initial tool
  const executor = initializeAgentExecutorWithOptions({ agentType: 'openai-functions', tool: 'initialTool' });
  // Use the executor to find the required information
  const info = executor.findInformation();
} catch (error) {
  // If the initial tool fails, re-initialize the executor with a different tool
  const executor = initializeAgentExecutorWithOptions({ agentType: 'openai-functions', tool: 'fallbackTool' });
  // Use the fallback tool to escalate support to a human
  executor.escalateSupport();
}

Please note that this would require modifications to your application code and is not a feature provided by the initializeAgentExecutorWithOptions function itself.

I hope this helps! If you have any other questions or need further clarification, feel free to ask.

Best regards.

Sources

• langchain/src/agents/initialize.ts

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.