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