You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am running a few dozen cases using gemini mode for evaluation, I run each case with each metric successfully. However when I run all of them in async mode together using the code below: result: EvaluationResult = evaluate( test_cases=test_cases, metrics=[claim_metric, answer_relevancy, faithfulness, contextual_relevancy], async_config=AsyncConfig( throttle_value=2, max_concurrent=4 ) )
I sometimes get none verdicts or claims or truths. When I debug debug, sometimes the code return None for res. res, cost = await self.model.a_generate( prompt, schema=ContextualRelevancyVerdicts )
Anyone has the same experience? I did play with throttle_value or max_concurrent, it helps, but does not completely eradict the issue.
Any suggestions?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I am running a few dozen cases using gemini mode for evaluation, I run each case with each metric successfully. However when I run all of them in async mode together using the code below:
result: EvaluationResult = evaluate( test_cases=test_cases, metrics=[claim_metric, answer_relevancy, faithfulness, contextual_relevancy], async_config=AsyncConfig( throttle_value=2, max_concurrent=4 ) )
I sometimes get none verdicts or claims or truths. When I debug debug, sometimes the code return None for res.
res, cost = await self.model.a_generate( prompt, schema=ContextualRelevancyVerdicts )
Anyone has the same experience? I did play with throttle_value or max_concurrent, it helps, but does not completely eradict the issue.
Any suggestions?
Beta Was this translation helpful? Give feedback.
All reactions