Assigned
Status Update
No update yet.
Comments
sa...@google.com
I've created this Public Issue Tracker for customer visibility, please share any update here
va...@google.com
je...@google.com
Hello,
This issue report has been forwarded to the Cloud Recommendations AI Product team so that they may investigate it, but there is no ETA for a resolution today. Future updates regarding this issue will be provided here.
fa...@gcp.nordstrom.com
Hi,
This is what the team is trying to accomplish for keyword search
Our digital site Merchandisers create browse categories "mothers day" , "fathers day" , "valentines day" , "anniversary sale" , "black friday", "designer sale". Each category has handpicked or rules based items that are selected to be in the category/browse page. We want the equivalent keyword search for those categories to have the same recall or close to the same recall as when the customer navigates to the browse category page.
Issue: We did a Proof of concept for one designer page and it did not work
- We took designer page category page which had 4157 items . For each of the 4157 items we tagged "designer sale" in a searchable field.
- Expected/Actual : when customer searches for "designer sale" we expect close to 4157 items showing up. Actual : we only see about 1000
Note: we are trying to do this in a scalable manner , preferably tagging search documents with data an have this be data driven. We do not want to use serving controls or boost rules.
is there a way to have a system attribute field which is weight heavily when there are certain keyterms tagged onto the document. The goal here is , there is a human in the loop that wants to influence the recall for certain search terms
This is what the team is trying to accomplish for keyword search
Our digital site Merchandisers create browse categories "mothers day" , "fathers day" , "valentines day" , "anniversary sale" , "black friday", "designer sale". Each category has handpicked or rules based items that are selected to be in the category/browse page. We want the equivalent keyword search for those categories to have the same recall or close to the same recall as when the customer navigates to the browse category page.
Issue: We did a Proof of concept for one designer page and it did not work
- We took designer page category page which had 4157 items . For each of the 4157 items we tagged "designer sale" in a searchable field.
- Expected/Actual : when customer searches for "designer sale" we expect close to 4157 items showing up. Actual : we only see about 1000
Note: we are trying to do this in a scalable manner , preferably tagging search documents with data an have this be data driven. We do not want to use serving controls or boost rules.
is there a way to have a system attribute field which is weight heavily when there are certain keyterms tagged onto the document. The goal here is , there is a human in the loop that wants to influence the recall for certain search terms
sa...@google.com
I created this pit for customer visibility and tracking purposes please share any update to the cx for this via, thanks
Description
Please provide as much information as possible. At least, this should include a description of your issue and steps to reproduce the problem. If possible please provide a summary of what steps or workarounds you have already tried, and any docs or articles you found (un)helpful.
Problem you have encountered:
Experiencing an issue where Vertex AI Search for Retail is returning fewer products than expected for a specific search query.
What you expected to happen:
A long term-fix for a scalable term handler .
Steps to reproduce:
Search a term in internal investigation
Other information (workarounds you have tried, documentation consulted, etc):
After carefully reviewed the possible options for you we found [boost] is the best option
[boost]:
By instance If you would like to ensure products are marked as "black friday" show up on top for "black friday' sales,