-
Epic
-
Resolution: Unresolved
-
Undefined
-
None
-
Run lightspeed eval against developer lightspeed 1.9
-
False
-
-
False
-
-
In Progress
-
RHDHPLAN-930 - Lightspeed Evaluation Data Update and Public Consumption
-
QE Needed, Docs Needed, TE Needed, Customer Facing, PX Needed
-
50% To Do, 50% In Progress, 0% Done
-
-
EPIC Goal
with https://issues.redhat.com/browse/RHDHPLAN-261 being done, we consider the 1.8 Eval result as a dry run. in the 1.10 timeframe, we will run the dataset generate & lightspeed evaluation against Developer Lightspeed 1.9 RAG.
Acceptance Criteria
500+ single-run Q&A dataset need to be generated against RHDH 1.9 docs
run the evaluation with 2-3 large/medium models, 2 small models