The outcome

Create a reproducible retrieval workflow that answers from approved sources instead of model memory alone.

Step by step

A workflow you can repeat.

  1. 01

    Define the corpus owner, allowed questions, freshness rules, access policy, citation requirements, and a benchmark with expected sources.

  2. 02

    Load clean documents with stable IDs and metadata, remove duplicates and secrets, then choose chunking and embedding settings deliberately.

  3. 03

    Build and persist the index, configure retrieval depth and filters, and ensure tenant or document permissions apply before generation.

  4. 04

    Run the benchmark and inspect retrieved nodes separately from final answers for relevance, missed evidence, conflicts, and leakage.

  5. 05

    Tune one retrieval variable at a time, version the corpus and index configuration, and schedule refresh and regression evaluation.

Working standard

What good use looks like.

  • Evaluate retrieval before generation.
  • Preserve source IDs and metadata.
  • Enforce permissions during retrieval.

Official references

Check the current product documentation.