Can you add langsmith/wandb for tracing and ragas for evaluation metrics?
vitalyshalumov opened this issue · comments
vitalyshalumov commented
PSEUDOTENSOR / Jonathan McKinney commented
I have some code in WIP for verifiers that include such things, but not done. RAGAS is ok, but it's a bit loose compared to specific checking of actual specific faqs like done here: https://github.com/h2oai/enterprise-h2ogpte/tree/main/rag_benchmark