RAG Query • AI Agent SDK

rag_query: Query knowledge using RAG pipeline with citations.

rag_query

Method

This is a method of the Agent class in the agent module.

Query knowledge using RAG pipeline with citations.

This is the recommended way to get answers with citations from an agent’s knowledge.

Signature

def rag_query(question: str) -> 'RAGResult'

Parameters

question · str · required

The question to answer **kwargs: Additional arguments passed to RAG.query()

Returns

Returns · 'RAGResult'

RAGResult with answer, citations, context_used, and metadata

Exceptions

ValueError

If no knowledge sources are configured

ImportError

If RAG module is not available

Usage

agent = Agent(knowledge=["doc.pdf"], rag_config={"include_citations": True})
    result = agent.rag_query("What is the main finding?")
    print(result.answer)
    for citation in result.citations:
        print(f"[{citation.id}] {citation.source}: {citation.text[:100]}")

Uses

• ValueError
• ImportError
• kwargs.setdefault
• query

Source

View on GitHub

praisonaiagents/agent/agent.py at line 3131

---

Related Documentation

RAG Concept

RAG Overview

Chunking Strategies