Skip to main content

​
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

If no knowledge sources are configured
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]}")