on_question()

Python
TypeScript

When a Guava agent is asked a question that it cannot answer from its context alone, it will invoke the on_question callback. Your Expert then has the chance to answer that question, typically using a RAG system. Our examples use the provided DocumentQA class, but you can use any RAG system you prefer.See our Q&A example for a step-by-step walkthrough.

signature

@agent.on_question
def on_question(call: guava.Call, question: str) -> str:
    # question: natural-language question from the caller
    # return: answer to relay to caller
    ...

If you want the agent to answer questions immediately, use add_info to pre-emptively add information to the context.

on_question, like all Guava callbacks, is invoked asynchronously and does not block dialog. The Guava voice agent continues to engage the caller until the question answer comes back.
on_question may be invoked multiple times, for example, if a caller asks a question and then refines it. on_question may be invoked speculatively before a caller is done talking.
on_question may be invoked simultaneously with on_action_request, as some requests can be both an “action” and a “question”. For example, “Do you have a lost and found?” In this case, the agent will synthesize both responses: “Yes, we have a lost and found. Would you like me to transfer you there?”

When a Guava agent is asked a question that it cannot answer from its context alone, it will invoke the onQuestion callback. Your Expert then has the chance to answer that question, typically using a RAG system. Our examples use the provided DocumentQA class, but you can use any RAG system you prefer.See our Q&A example for a step-by-step walkthrough.

signature

agent.onQuestion(async (call: guava.Call, question: string) => string);

If you want the agent to answer questions immediately, use addInfo to pre-emptively add information to the context.

onQuestion, like all Guava callbacks, is invoked asynchronously and does not block dialog. The Guava voice agent continues to engage the caller until the question answer comes back.
onQuestion may be invoked multiple times, for example, if a caller asks a question and then refines it. onQuestion may be invoked speculatively before a caller is done talking.
onQuestion may be invoked simultaneously with onActionRequest, as some requests can be both an “action” and a “question”. For example, “Do you have a lost and found?” In this case, the agent will synthesize both responses: “Yes, we have a lost and found. Would you like me to transfer you there?”

Example

Python
TypeScript

support_controller.py

import guava
from guava import Agent
from guava.helpers.rag import DocumentQA
from guava.examples.example_data import PROPERTY_INSURANCE_POLICY

agent = Agent(
    organization="Harper Valley Property Insurance",
    purpose="Answer questions regarding property insurance policy",
)

document_qa = DocumentQA(documents=PROPERTY_INSURANCE_POLICY)

@agent.on_question
def on_question(call: guava.Call, question: str) -> str:
    return document_qa.ask(question)

support_controller.ts

import * as guava from "@guava-ai/guava-sdk";
import { DocumentQA } from "@guava-ai/guava-sdk/helpers";
import { PROPERTY_INSURANCE_POLICY } from "@guava-ai/guava-sdk/example-data";

const agent = new guava.Agent({
  organization: "Harper Valley Property Insurance",
  purpose: "Answer questions regarding property insurance policy",
});

const documentQA = new DocumentQA({
  documents: PROPERTY_INSURANCE_POLICY,
  namespace: "harper-valley-property-insurance",
});

agent.onQuestion(async (call: guava.Call, question: string) => {
  return await documentQA.ask(question);
});

Getting started

Agent SDK

CLI reference

WebRTC

SIP calling

Phone numbers

Deployments

Compliance

Release notes

Example

​Example

Example