Hanchi Wang

Results 40 comments of Hanchi Wang

[BUG] Running evaluate from promptflow.evals.evaluate and setting trace.destination="none" or "local" causes evaluations to not be available

@pragmatical , can you share the full stack trace and evaluate() function code?

[BUG] promptflow built in evaluator cannot take nested json outputs as column mapping

Thx for the feedback! We need a standard way to allow complex json mapping. Something like json path. If you have a suggestion of an industry standard, definitely let us...

[BUG] 'Connection aborted.', RemoteDisconnected('Remote end closed connection without response') while running promptflow eval API

This looks like a service side timeout. @wangchao1230, who can help from the PF service side? @yanggaome, can you also check if your local source folders are being uploaded unnecessarily?...

[Feature Request] pass addition inputs to target function when using the evaluate method

This is blocked by pf core/devkit.

Azure Machine Learning container registry cannot be changed due to the lack of "--yes" argument

@SatishBoddu-MSFT please confirm if this is still an active issue.

Fix CI pipeline failures

/checkpoint override

[BUG] Failed to upload run to Azure AI Project

The error indicates upload to storage account failed. Am wondering if this happens consistently? The second error is a know issue that promptflow upon error changes cwd.

azure.ai.evaluation SDK cannot handle `conversation` input from a csv file.

This is the expected behavior so far. csv files as input only support query/responese format.

Deprecation Warnings when using evaluate

The `azure-ai-ml` package needs to update its dependency on `marshmallow`. Thx for reporting this issue. We'll address this in the sprint of November.

[BUG] Running Prompt flow locally produces errors

This is fixed with promptflow-tracing 1.16.1