Open pamelafox opened 5 months ago
hi @pamelafox , thanks for the feedback; i will work on fixing this.
Hi, we're sending this friendly reminder because we haven't heard back from you in 30 days. We need more information about this issue to help address it. Please be sure to give us your input. If we don't hear back from you within 7 days of this comment, the issue will be automatically closed. Thank you!
I dont think you need more of my input. I havent checked to see if this is fixed in new promptflow-evals.
Hi, we're sending this friendly reminder because we haven't heard back from you in 30 days. We need more information about this issue to help address it. Please be sure to give us your input. If we don't hear back from you within 7 days of this comment, the issue will be automatically closed. Thank you!
I already replied.
Describe the bug
When I use the azure-ai-generative SDK's evaluate function(), it calls PromptFlow code which results in this warning in my logs:
/Users/pamelafox/ai-rag-chat-evaluator/.venv/lib/python3.11/site-packages/promptflow/_sdk/operations/_local_storage_operations.py:516: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise an error in a future version of pandas. Value '(Failed)' has dtype incompatible with float64, please explicitly cast to a compatible dtype first. outputs.fillna(value="(Failed)", inplace=True) # replace nan with explicit prompt
I am on promptflow 1.6 due to an issue with 1.7 and evaluate SDK, but I don't know if this warning is fixed yet, as the code seems to be similar in main.
How To Reproduce the bug
I experience it when I'm using https://github.com/Azure-Samples/ai-rag-chat-evaluator, which calls the evaluate function from azure-ai-generative, which uses promptflow behind the scenes.
Expected behavior
I expect no warnings.