FAQBotAgent | SignalWire

Answers frequently asked questions by matching user queries against a provided knowledge base. Optionally suggests related questions from the database.

1 from signalwire.prefabs import FAQBotAgent

faqs

list[dict[str, str]]Required

List of FAQ items. Each dict must have question and answer keys; an optional categories key (list of strings) enables category-based filtering.

suggest_related

boolDefaults to True

When True, the agent suggests related questions from the FAQ database after answering.

persona

str

Custom personality description for the bot. Defaults to a generic helpful FAQ bot persona.

name

strDefaults to faq_bot

Agent name for identification and logging.

route

strDefaults to /faq

HTTP route for this agent.

Built-in Tools

Tool	Description	Parameters
`search_faqs`	Search FAQs by query or category	`query` (str), `category` (str, optional)

FAQBot works best with up to 50 FAQs. For larger knowledge bases, use the native_vector_search skill instead.

Example

1 from signalwire.prefabs import FAQBotAgent
2 
3 agent = FAQBotAgent(
4     faqs=[
5         {
6             "question": "What is the warranty period?",
7             "answer": "All products come with a 2-year warranty.",
8             "categories": ["warranty", "products"]
9         },
10         {
11             "question": "How do I return a product?",
12             "answer": "Start a return within 30 days at returns.example.com.",
13             "categories": ["returns", "products"]
14         },
15         {
16             "question": "Do you ship internationally?",
17             "answer": "Yes, we ship to over 50 countries.",
18             "categories": ["shipping"]
19         }
20     ],
21     suggest_related=True,
22     persona="You are a helpful product specialist for TechGadgets Inc."
23 )
24 
25 if __name__ == "__main__":
26     agent.run()