Skip to content

[Bug]: Multi turn conversation eval metrics issue #2979

Description

@guruvittal

File Name

multi_turn_agent_evaluation_with_user_simulation_metric_registration_auto_loss_analysis.ipynb

What happened?

A bug happened!
WHen running this notebook: https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/evaluation/multi_turn_agent_evaluation_with_user_simulation_metric_registration_auto_loss_analysis.ipynb

Multi turn metrics are not being defined both locally and on cloud.

Loss Analysis fails completely both locally and on cloud.

Log:
Evaluation job completed in 11 seconds.
ERROR:vertexai._genai._evals_common:Failed to load evaluation result from GCS: gs://vertexsearch-447722-jul14-eval-bucket/result_861893970874073088.json. Error: 1 validation error for EvaluationItemResult
request.candidateResponses.0.error
Extra inputs are not permitted [type=extra_forbidden, input_value={'code': 13, 'message': "...has no attribute 'get'"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.13/v/extra_forbidden
ERROR:vertexai._genai._evals_common:Failed to load evaluation result from GCS: gs://vertexsearch-447722-jul14-eval-bucket/result_8902508155590672384.json. Error: 1 validation error for EvaluationItemResult
request.candidateResponses.0.error
Extra inputs are not permitted [type=extra_forbidden, input_value={'code': 13, 'message': "...has no attribute 'get'"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.13/v/extra_forbidden
ERROR:vertexai._genai._evals_common:Failed to load evaluation result from GCS: gs://vertexsearch-447722-jul14-eval-bucket/result_4682072354791096320.json. Error: 1 validation error for EvaluationItemResult
request.candidateResponses.0.error
Extra inputs are not permitted [type=extra_forbidden, input_value={'code': 13, 'message': "...has no attribute 'get'"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.13/v/extra_forbidden
ERROR:vertexai._genai._evals_common:Failed to load evaluation result from GCS: gs://vertexsearch-447722-jul14-eval-bucket/result_2833907657708929024.json. Error: 1 validation error for EvaluationItemResult
request.candidateResponses.0.error
Extra inputs are not permitted [type=extra_forbidden, input_value={'code': 13, 'message': "...has no attribute 'get'"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.13/v/extra_forbidden
ERROR:vertexai._genai._evals_common:Failed to load evaluation result from GCS: gs://vertexsearch-447722-jul14-eval-bucket/result_4750189299155075072.json. Error: 1 validation error for EvaluationItemResult
request.candidateResponses.0.error
Extra inputs are not permitted [type=extra_forbidden, input_value={'code': 13, 'message': "...has no attribute 'get'"}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.13/v/extra_forbidden
Status: FAILED

Error:

code=9 details

Relevant log output

Code of Conduct

  • I agree to follow this project's Code of Conduct

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions