Assigned
Status Update
No update yet.
Comments
va...@google.com
pu...@google.com
Hello,
Thank you for reaching out to us with your request.
We have duly noted your feedback and will thoroughly validate it. While we cannot provide an estimated time of implementation or guarantee the fulfillment of the issue, please be assured that your input is highly valued. Your feedback enables us to enhance our products and services.
We appreciate your continued trust and support in improving our Google Cloud Platform products. In case you want to report a new issue, Please do not hesitate to create a new issue on the
Once again, we sincerely appreciate your valuable feedback; Thank you for your understanding and collaboration.
Description
What you would like to accomplish: We would like to have a 1-to-1 mapping between request-response logs from the Vertex AI Endpoint with the audit logging.
How this might work: 1-to-1 mapping of audit logs and request-response logging can be accomplished by adding the request_id present in the request-response logging to the audit logs.
If applicable, reasons why alternative solutions are not sufficient: Both logs contain information on the endpoint resource and deployed model id. However, timestamps do not align which makes mapping between audit logs and prediction requests difficult as multiple requests can be submitted in a short timeframe. Our experiment showed a delay of approx ~70ms between the timestamp in the request-response logs and audit logs.
Other information (workarounds you have tried, documentation consulted, etc): Documentation consulted:https://cloud.google.com/vertex-ai/docs/predictions/online-prediction-logging