QAVE Studio Docs
QAVE Studio Docs
Sign inGet started — the Studio loop
Getting StartedFirst assurance runQuick assure
ConceptsLifecycleGlossaryHow QAVE Studio worksComing soon
Account & workspaceSignup and loginPeopleDemo creditsRolesSettings
Generate simulation suitesContext templatePII and field enhanceDimensionsAgents and plannerDraft review and Save
ExportExport formatsExport formats (detail)
Assurance SDKSDK overviewQAVE Studio suite fetch APIAgent and JSONL queueLangfuse bridge
Execute and tracesRecipe chatbot (reference SUT)TracingFetch tracing
AssureEvaluate APIRubrics and evidenceReading scores
History
WorkbenchGolden data
CoverageCoverage dashboardCoverage strategiesCoverage advisorTest case quality
RAG AssuranceRAG runsRAG datasetsRAG analytics
Project evalsError analysisUnderstanding scores
Studio guidesDimensionsTuplesConversation modesMulti-lingual testingWorkflowsHuman reviewBest practices
ReferenceAPI and packagesTroubleshooting
RAG Assurance

RAG runs

Score a retrieval dump for Hit@k, Recall@k, MRR, and more.

How to score a run

  1. Open RAG Assurance → Runs (/rag-assurance/runs).
  2. Drop or upload a retrieval dump in the supported format, or expand the API section for a curl example.
  3. Start the run and wait for metrics to appear.
  4. Open the run detail to inspect per-query hits and failures.

Tips

  • Keep dump schemas consistent across runs so Analytics stays comparable.
  • Prefer named datasets when you will re-run the same queries (see Datasets).

Related

  • Datasets
  • Analytics

RAG Assurance

Score retrieval quality with runs, datasets, and analytics.

RAG datasets

Manage reusable retrieval evaluation datasets.

On this page

How to score a runTipsRelated