Skip to main content

Knowledge-Grounded Answer

Learning goals​

Compose retrieval and generation while preserving source metadata.

Quick reference: Level 4; advanced; output type grounded_answer; estimated cost: embedding and LLM provider dependent.

Architecture​

Text alternative: The graph contains FlowBeads/input, Memory/KnowledgeQuery, LLMBeads/LLMProcess, FlowBeads/output. It accepts public input and returns a public result.

Prerequisites​

None.

Connections​

  • One configured Knowledge Base

Secrets​

  • One supported LLM secret

Build and run​

  1. Select a Knowledge Base.
  2. Select an LLM model and secret.
  3. Run and compare sources with the answer.

Use this fixture in the Test panel:

Knowledge question
What are the main obligations described in the indexed documents?

Expected result​

  • retrieval results are recorded
  • answer uses retrieved context

Open the persisted run and verify the node timeline. Browser sinks appear in the Inspector; public output appears in the run result when enabled.

Side effects and cost​

This Braid has no external side effect.

Cost: embedding and LLM provider dependent. DataBraid stores summaries and structured errors, not secret values.

Extensions​

  • Change the fixture and compare the node-level timeline.
  • Add a Data Probe before the final output.
  • Save a known-good fixture for regression testing.