Assigned
Status Update
No update yet.
Comments
va...@google.com
ds...@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
UNJOINED_WITH_CATALOG error appears on products that are present in the catalog in Retail API. Testing on the same products multiple times, this error doesn't happen every time.
Error:
"message": "UNJOINED_WITH_CATALOG userEvent_productDetails_product_id",
"status": {
"code": 3,
"message": "The predict request has 1 product(s) that are not in the catalog. This will result in degraded model performance. List of missing product IDs: [xxx]."
}
severity is WARRNING
What you expected to happen:
Products that are available in the catalog in Retail API should not give UNJOINED_WITH_CATALOG error.
Steps to reproduce:
google.cloud.retail.v2main.PredictionService.Predict
For products that are present in Retail API catalog with request:
"requestPayload": {
"userEvent": {
"eventType": "home-page-view",
"productDetails": [
{
"quantity": 1,
"product": {
"id": "xxx"
}
},
{
"quantity": 1,
"product": {
"id": "xxx"
}
}
],
"visitorId": "xxx",
"userInfo": {
"userId": "xxx"
}
},
"placement": "projects/xxx/locations/global/catalogs/default_catalog/placements/xxx"
}
Calling API multiple times on the same 'missing' products (that are actually present in the catalog) - the error rarely appears the 2nd time.
Currently about 99% of our prediction errors should not have happened.
According to documentation this has negative effect on our models.