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
Assurance SDK

Langfuse bridge

Fetch SUT traces from Langfuse, normalize, and submit to the assure Gateway.

This is the most complete working path from a live SUT to scored History when Langfuse is configured.

Steps

  1. Run the SUT with Langfuse keys so sessions emit traces (recipe-chatbot uses names like recipe-chatbot-session).
  2. Ensure the QAVE Studio / Gateway stack is up.
  3. Run the bridge:
PYTHONPATH=src python -m qurator.sdk.langfuse_to_qurator \
  --name-filter recipe-chatbot-session
  1. Open History to inspect scores.

The bridge normalizes common Langfuse shapes (messages, conversation.messages, turns, input/output) before POST /v1/assure/evaluate.

API keys on the bridge must match Gateway configuration or requests return 401.

Agent and JSONL queue

Poll inputs.jsonl, call MCP evaluate_conversation, and record traces.

Execute and traces

Drive the system under test and capture traces for assurance.

On this page

Steps